{"data":[{"id":"anthropic/claude-fable-5.1","canonical_slug":"anthropic/claude-fable-5.1","hugging_face_id":null,"name":"anthropic: Claude Fable 5.1","created":1788134400,"description":"Claude Fable 5.1 is Anthropic's model for the most demanding reasoning and long-horizon agentic work, above Opus 5.5 in the Claude lineup. It suits long-running agentic coding, multistep research, and document and spreadsheet work, with a 1M-token context.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"completion":"0.00005","image_token":"0.00001","input_cache_read":"0.00000025","input_cache_write":"0.0000125","input_cache_write_1h":"0.00002","internal_reasoning":"0.00005","prompt":"0.00001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-06-01","expiration_date":null,"links":{"details":"/v1/models/anthropic/claude-fable-5.1"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","supports_max_tokens":false}},{"id":"anthropic/claude-fable-5.2","canonical_slug":"anthropic/claude-fable-5.2","hugging_face_id":null,"name":"anthropic: Claude Fable 5.2","created":1794182400,"description":"Claude Fable 5.2 is Anthropic's model for the most demanding reasoning and long-horizon agentic work, the successor to Fable 5.1 at a lower price. It suits long-running agentic coding, multistep research, and document and spreadsheet work, with a 1M-token context and 128K output.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"completion":"0.00004","image_token":"0.000008","input_cache_read":"0.0000002","input_cache_write":"0.00001","input_cache_write_1h":"0.000016","internal_reasoning":"0.00004","prompt":"0.000008"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-06-01","expiration_date":null,"links":{"details":"/v1/models/anthropic/claude-fable-5.2"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","supports_max_tokens":false}},{"id":"anthropic/claude-haiku-5.5","canonical_slug":"anthropic/claude-haiku-5.5","hugging_face_id":null,"name":"anthropic: Claude Haiku 5.5","created":1791331200,"description":"Claude Haiku 5.5 is Anthropic's fastest current model, built for high-volume, latency-sensitive work such as classification, extraction, routing and subagent tasks. It supports adaptive thinking, tool use, and text, image and PDF input with a 1M-token context and 128K output; prompts over 100,000 tokens are billed at a higher rate.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"completion":"0.0000005","image_token":"0.0000001","input_cache_read":"0.00000001","input_cache_write":"0.000000125","input_cache_write_1h":"0.0000002","internal_reasoning":"0.0000005","overrides":[{"completion":"0.0000025","image_token":"0.0000005","input_cache_read":"0.00000005","input_cache_write":"0.000000625","input_cache_write_1h":"0.000001","internal_reasoning":"0.0000025","min_prompt_tokens":100001,"prompt":"0.0000005"}],"prompt":"0.0000001"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-06-01","expiration_date":null,"links":{"details":"/v1/models/anthropic/claude-haiku-5.5"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"anthropic/claude-opus-5.5","canonical_slug":"anthropic/claude-opus-5.5","hugging_face_id":null,"name":"anthropic: Claude Opus 5.5","created":1790035200,"description":"Claude Opus 5.5 is built for long-running agentic coding and knowledge work, sitting between Sonnet 5.5 and Fable 5.1 in Anthropic's lineup. Thinking is always on and adaptive, with text, image and PDF input, a 1M-token context and 128K output.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"completion":"0.00002","image_token":"0.000004","input_cache_read":"0.0000002","input_cache_write":"0.000005","input_cache_write_1h":"0.000008","internal_reasoning":"0.00002","prompt":"0.000004"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-06-01","expiration_date":null,"links":{"details":"/v1/models/anthropic/claude-opus-5.5"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"anthropic/claude-sonnet-5","canonical_slug":"anthropic/claude-sonnet-5","hugging_face_id":null,"name":"anthropic: Claude Sonnet 5","created":1782777600,"description":"Claude Sonnet 5 is the previous Sonnet model, released June 2026 and now marked legacy, with Sonnet 5.5 as its successor. It offers adaptive thinking, text, image and PDF input, a 1M-token context and an earlier January 2026 knowledge cutoff.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"completion":"0.00001","image_token":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","internal_reasoning":"0.00001","prompt":"0.000002"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-01-01","expiration_date":null,"links":{"details":"/v1/models/anthropic/claude-sonnet-5"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","supports_max_tokens":false}},{"id":"anthropic/claude-sonnet-5.5","canonical_slug":"anthropic/claude-sonnet-5.5","hugging_face_id":null,"name":"anthropic: Claude Sonnet 5.5","created":1790553600,"description":"Claude Sonnet 5.5 is Anthropic's current Sonnet model, positioned for a balance of speed and intelligence below Opus 5.5. It supports adaptive thinking, tool use, and text, image and PDF input with a 1M-token context and 128K output.","context_length":1000000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"claude","instruct_type":null},"pricing":{"completion":"0.00001","image_token":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000025","input_cache_write_1h":"0.000004","internal_reasoning":"0.00001","prompt":"0.000002"},"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-06-01","expiration_date":null,"links":{"details":"/v1/models/anthropic/claude-sonnet-5.5"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high","supports_max_tokens":false}},{"id":"bytedance/seed-2.1-lite","canonical_slug":"bytedance/seed-2.1-lite","hugging_face_id":null,"name":"bytedance: Seed 2.1 Lite","created":1789430400,"description":"Seed 2.1 Lite is the low-cost model of ByteDance's Seed 2.1 family, built for high-volume work. It takes text and image input with a 1M-token context, up to 256K output, tool calling, structured output and adjustable reasoning effort.","context_length":1024000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"completion":"0.00000041","image_token":"0.00000012","input_cache_read":"0.000000024","internal_reasoning":"0.00000041","prompt":"0.00000012"},"top_provider":{"context_length":1024000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/bytedance/seed-2.1-lite"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"bytedance/seed-2.1-pro","canonical_slug":"bytedance/seed-2.1-pro","hugging_face_id":null,"name":"bytedance: Seed 2.1 Pro","created":1789430400,"description":"Seed 2.1 Pro is ByteDance's flagship multimodal model for long-running agent work, research and coding. It takes text and image input with a 1M-token context, up to 256K output, tool calling, structured output and adjustable reasoning effort.","context_length":1024000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"completion":"0.0000045","image_token":"0.0000009","input_cache_read":"0.00000018","internal_reasoning":"0.0000045","prompt":"0.0000009"},"top_provider":{"context_length":1024000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/bytedance/seed-2.1-pro"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"bytedance/seed-2.1-turbo","canonical_slug":"bytedance/seed-2.1-turbo","hugging_face_id":null,"name":"bytedance: Seed 2.1 Turbo","created":1782604800,"description":"Seed 2.1 Turbo balances quality and cost in ByteDance's Seed 2.1 family, with upgraded coding, agent and multimodal ability. It takes text and image input with a 256K-token context, tool calling, structured output and adjustable reasoning effort.","context_length":256000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"doubao","instruct_type":null},"pricing":{"completion":"0.0000025","image_token":"0.0000005","input_cache_read":"0.0000001","internal_reasoning":"0.0000025","prompt":"0.0000005"},"top_provider":{"context_length":256000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/bytedance/seed-2.1-turbo"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash","hugging_face_id":null,"name":"deepseek: DeepSeek V4 Flash 0731","created":1785456000,"description":"DeepSeek V4 Flash is the fast, low-cost model of the DeepSeek V4 generation, switching between deep thinking and plain chat. Text input with a 1M-token context, up to 384K output, tool calling, structured output and adjustable reasoning effort.","context_length":1024000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"completion":"0.00000132","input_cache_read":"0.000000014","internal_reasoning":"0.00000132","prompt":"0.00000044"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","stop","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/deepseek/deepseek-v4-flash"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"deepseek/deepseek-v4-pro","canonical_slug":"deepseek/deepseek-v4-pro","hugging_face_id":null,"name":"deepseek: DeepSeek V4 Pro 0813","created":1786579200,"description":"DeepSeek V4 Pro is DeepSeek's flagship hybrid reasoning model, tuned for code generation, mathematical reasoning and agent tool use. Text input with a 1M-token context, up to 384K output, tool calling, structured output and adjustable reasoning effort.","context_length":1024000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"completion":"0.00000396","input_cache_read":"0.000000044","internal_reasoning":"0.00000396","prompt":"0.00000132"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","stop","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/deepseek/deepseek-v4-pro"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek/deepseek-v4.1-flash","hugging_face_id":null,"name":"deepseek: DeepSeek V4.1 Flash 0910","created":1788998400,"description":"DeepSeek V4.1 Flash 0910 is the September 10 release of DeepSeek V4.1 Flash, the hybrid reasoning model, with higher reasoning accuracy and faster responses than V4. It takes text and image input with a 1M-token context, up to 384K output, tool calling, structured output and adjustable reasoning effort.","context_length":1024000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"completion":"0.0000012","image_token":"0.0000003","input_cache_read":"0.000000006","internal_reasoning":"0.0000012","prompt":"0.0000003"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","stop","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/deepseek/deepseek-v4.1-flash"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"deepseek/deepseek-v4.1-flash-1017","canonical_slug":"deepseek/deepseek-v4.1-flash-1017","hugging_face_id":null,"name":"deepseek: DeepSeek V4.1 Flash 1017","created":1792195200,"description":"DeepSeek V4.1 Flash 1017 is the October 17 update of DeepSeek V4.1 Flash, the hybrid reasoning model. It takes text and image input with a 1M-token context, up to 384K output, tool calling, structured output and adjustable reasoning effort.","context_length":1024000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"deepseek","instruct_type":null},"pricing":{"completion":"0.0000012","image_token":"0.0000003","input_cache_read":"0.000000006","internal_reasoning":"0.0000012","prompt":"0.0000003"},"top_provider":{"context_length":1024000,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","stop","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/deepseek/deepseek-v4.1-flash-1017"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"google/gemini-3-pro-image","canonical_slug":"google/gemini-3-pro-image","hugging_face_id":null,"name":"google: Nano Banana Pro","created":1779926400,"description":"Nano Banana Pro is Google's reasoning-driven image generation and editing model for professional work, the higher-end counterpart to Nano Banana 2. It is suited to complex graphic design, product mockups and data visualizations that need accurate text rendering.","context_length":65536,"architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"completion":"0.000012","image_output":"0.00012","image_token":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","prompt":"0.000002"},"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","seed","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-3-pro-image"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":[],"supports_max_tokens":false}},{"id":"google/gemini-3.1-flash-image","canonical_slug":"google/gemini-3.1-flash-image","hugging_face_id":null,"name":"google: Nano Banana 2","created":1779926400,"description":"Nano Banana 2 is Google's high-efficiency image generation and conversational editing model, the faster, lower-cost counterpart to Nano Banana Pro. Built for high-volume use, it outputs images from 0.5K up to 4K and accepts text and image input.","context_length":131072,"architecture":{"modality":"text+image+file+video-\u003eimage","input_modalities":["text","image","file","video"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"completion":"0.000003","image_output":"0.00006","image_token":"0.0000005","input_cache_read":"0.00000005","internal_reasoning":"0.000003","prompt":"0.0000005"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","seed","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-3.1-flash-image"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","minimal"],"default_effort":"minimal","supports_max_tokens":false}},{"id":"google/gemini-3.1-flash-lite-image","canonical_slug":"google/gemini-3.1-flash-lite-image","hugging_face_id":null,"name":"google: Nano Banana 2 Lite","created":1782777600,"description":"Nano Banana 2 Lite is the lowest-latency, lowest-cost model in Google's Nano Banana image family, targeting under 2 seconds end to end. It fits high-volume interactive apps and fast multi-turn edits such as color swaps or background changes, at 1K (1024px) resolution.","context_length":65536,"architecture":{"modality":"text+image+file+video-\u003eimage","input_modalities":["text","image","file","video"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"completion":"0.0000015","image_output":"0.00003","image_token":"0.00000025","input_cache_read":"0.000000025","internal_reasoning":"0.0000015","prompt":"0.00000025"},"top_provider":{"context_length":65536,"max_completion_tokens":4096,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","seed","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-3.1-flash-lite-image"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","minimal"],"default_effort":"minimal","supports_max_tokens":false}},{"id":"google/gemini-3.1-pro-preview","canonical_slug":"google/gemini-3.1-pro-preview","hugging_face_id":null,"name":"google: Gemini 3.1 Pro Preview","created":1771459200,"description":"Gemini 3.1 Pro Preview is Google's Pro reasoning model in preview, built for software engineering, agentic workflows and complex multimodal analysis. It supports low, medium and high thinking levels, text, image, PDF, audio and video input, and a 1M-token context; prompts over 200K tokens bill at a higher rate.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.000002","completion":"0.000012","image_token":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.000000375","internal_reasoning":"0.000012","overrides":[{"audio":"0.000004","completion":"0.000018","image_token":"0.000004","input_cache_read":"0.0000004","input_cache_write":"0.000000375","internal_reasoning":"0.000018","min_prompt_tokens":200001,"prompt":"0.000004"}],"prompt":"0.000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","temperature","top_p","seed","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-3.1-pro-preview"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"high","supports_max_tokens":false}},{"id":"google/gemini-3.5-flash","canonical_slug":"google/gemini-3.5-flash","hugging_face_id":null,"name":"google: Gemini 3.5 Flash","created":1779148800,"description":"Gemini 3.5 Flash is an earlier Flash model in Google's Gemini 3 series, now listed as legacy, aimed at sub-agents, multi-step workflows and fast agentic coding loops. It accepts text, image, audio, video and PDF input with a 1M-token context and up to 65K output tokens.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.0000015","completion":"0.000009","image_token":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.0000000833","internal_reasoning":"0.000009","prompt":"0.0000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","temperature","top_p","seed","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-3.5-flash"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium","supports_max_tokens":false}},{"id":"google/gemini-3.5-flash-lite","canonical_slug":"google/gemini-3.5-flash-lite","hugging_face_id":null,"name":"google: Gemini 3.5 Flash Lite","created":1784592000,"description":"Gemini 3.5 Flash Lite is the fastest, most cost-effective model in Google's Gemini 3.5 family. It is designed for high-volume sub-agent tasks, document parsing and simple data extraction, with multimodal input and a 1M-token context.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.0000003","completion":"0.0000025","image_token":"0.0000003","input_cache_read":"0.00000003","input_cache_write":"0.0000000833","internal_reasoning":"0.0000025","prompt":"0.0000003"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","temperature","top_p","seed","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-3.5-flash-lite"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal","supports_max_tokens":false}},{"id":"google/gemini-3.6-flash","canonical_slug":"google/gemini-3.6-flash","hugging_face_id":null,"name":"google: Gemini 3.6 Flash","created":1784592000,"description":"Gemini 3.6 Flash is a previous-generation Gemini Flash model that balances speed and multimodal capability for general agentic and everyday tasks. Google highlights code generation, agentic execution and spatial reasoning; it takes text, image, audio, video and PDF input.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.0000015","completion":"0.0000075","image_token":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.0000000833","internal_reasoning":"0.0000075","prompt":"0.0000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","temperature","top_p","seed","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2026-11-19","links":{"details":"/v1/models/google/gemini-3.6-flash"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium","supports_max_tokens":false}},{"id":"google/gemini-3.7-flash","canonical_slug":"google/gemini-3.7-flash","hugging_face_id":null,"name":"google: Gemini 3.7 Flash","created":1786579200,"description":"Gemini 3.7 Flash is the Flash release just before 3.8 in Google's Gemini 3 series, aimed at complex coding, agentic workflows and reliable multi-step execution. It supports low, medium and high thinking levels, multimodal input and a 1M-token context with 65K output.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.0000015","completion":"0.0000075","image_token":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.0000000833","internal_reasoning":"0.0000075","prompt":"0.0000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","temperature","top_p","seed","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":"2027-01-28","links":{"details":"/v1/models/google/gemini-3.7-flash"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"google/gemini-3.8-flash","canonical_slug":"google/gemini-3.8-flash","hugging_face_id":null,"name":"google: Gemini 3.8 Flash","created":1788307200,"description":"Gemini 3.8 Flash is the newest Flash model, which Google calls its most intelligent, built for long-horizon software engineering, autonomous agents and complex enterprise workflows. It supports low, medium and high thinking levels and a 1M-token context with multimodal input.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.0000015","completion":"0.0000075","image_token":"0.0000015","input_cache_read":"0.00000015","input_cache_write":"0.0000000833","internal_reasoning":"0.0000075","prompt":"0.0000015"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","temperature","top_p","seed","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-3.8-flash"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"google/gemini-4-argon","canonical_slug":"google/gemini-4-argon","hugging_face_id":null,"name":"google: Gemini 4 Argon","created":1791849600,"description":"Gemini 4 Argon is Google's frontier model and the first in the Gemini 4 family, built for deep work on complex real-world tasks in coding, finance, law, cybersecurity and science. It supports low, medium and high thinking levels, multimodal input including PDF, audio and video, and a 1M-token context.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.000004","completion":"0.00002","image_token":"0.000004","input_cache_read":"0.0000002","internal_reasoning":"0.00002","prompt":"0.000004"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-4-argon"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"google/gemini-4-carbon","canonical_slug":"google/gemini-4-carbon","hugging_face_id":null,"name":"google: Gemini 4 Carbon","created":1794268800,"description":"Gemini 4 Carbon is Google's most capable Gemini 4 model, built for the hardest work: complex multi-step coding and debugging, long-horizon agentic workflows, scientific reasoning and cybersecurity defense. It thinks longer than Gemini 4 Argon, supports low, medium and high thinking levels, multimodal input including PDF, audio and video, and a 1M-token context.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video-\u003etext","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"gemini","instruct_type":null},"pricing":{"audio":"0.000004","completion":"0.00002","image_token":"0.000004","input_cache_read":"0.0000002","internal_reasoning":"0.00002","prompt":"0.000004"},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","stop","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-4-carbon"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"google/gemini-nano-banana-2.1","canonical_slug":"google/gemini-nano-banana-2.1","hugging_face_id":null,"name":"google: Nano Banana 2.1","created":1791244800,"description":"Nano Banana 2.1 is Google's upgrade to Nano Banana 2, keeping Flash-level speed and cost while improving visual quality, prompt adherence, multi-turn character consistency and text rendering. It outputs 1K, 2K and 4K images and accepts up to 14 reference images.","context_length":131072,"architecture":{"modality":"text+image+file+video-\u003eimage","input_modalities":["text","image","file","video"],"output_modalities":["image"],"tokenizer":"gemini","instruct_type":null},"pricing":{"completion":"0.0000075","image_output":"0.00003","image_token":"0.0000015","input_cache_read":"0.00000015","internal_reasoning":"0.0000075","prompt":"0.0000015"},"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/google/gemini-nano-banana-2.1"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","minimal"],"default_effort":"medium","supports_max_tokens":false}},{"id":"microsoft/mai-image-2.6","canonical_slug":"microsoft/mai-image-2.6","hugging_face_id":null,"name":"microsoft: MAI-Image-2.6","created":1785456000,"description":"MAI-Image-2.6 is Microsoft's in-house image generation and editing model, with strong text rendering, portraits and photorealistic commercial output. It returns one PNG per call; set the picture size with size (up to about 2.4 megapixels, each side at least 768; larger sizes are scaled down to fit), and edit from up to five reference images.","architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"other","instruct_type":null},"pricing":{"completion":"0","image_output":"0.000038","image_token":"0.000008","prompt":"0.000005"},"top_provider":{"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/microsoft/mai-image-2.6"}},{"id":"microsoft/mai-image-2.6-flash","canonical_slug":"microsoft/mai-image-2.6-flash","hugging_face_id":null,"name":"microsoft: MAI-Image-2.6 Flash","created":1785456000,"description":"MAI-Image-2.6 Flash is the faster, lower-cost variant of Microsoft's MAI-Image-2.6, with the same generation and editing abilities. It returns one PNG per call; set the picture size with size (up to about 2.4 megapixels, each side at least 768; larger sizes are scaled down to fit), and edit from up to five reference images.","architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"other","instruct_type":null},"pricing":{"completion":"0","image_output":"0.000019","image_token":"0.0000025","prompt":"0.00000175"},"top_provider":{"is_moderated":false},"per_request_limits":null,"supported_parameters":[],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/microsoft/mai-image-2.6-flash"}},{"id":"moonshotai/kimi-k3.1-pro","canonical_slug":"moonshotai/kimi-k3.1-pro","hugging_face_id":null,"name":"moonshot: Kimi K3.1 Pro","created":1792800000,"description":"Kimi K3.1 Pro is the October 24 update of Moonshot AI's flagship Kimi K3 model, with stronger coding and agentic work. It takes text and image input with a 1M-token context, up to 128K output, tool calling, structured output and adjustable reasoning effort.","context_length":1048576,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"kimi","instruct_type":null},"pricing":{"completion":"0.00001","image_token":"0.000002","input_cache_read":"0.0000002","internal_reasoning":"0.00001","prompt":"0.000002"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","stop","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/moonshotai/kimi-k3.1-pro"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-5.4","canonical_slug":"openai/gpt-5.4","hugging_face_id":null,"name":"openai: GPT-5.4","created":1772668800,"description":"GPT-5.4 is the flagship of OpenAI's GPT-5.4 family, aimed at complex coding and professional work one step below GPT-5.5. It accepts text and image input with a 1.05M-token context, 128K output, and reasoning effort from none to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.000015","image_token":"0.0000025","input_cache_read":"0.00000025","input_cache_write":"0.000003125","internal_reasoning":"0.000015","overrides":[{"completion":"0.0000225","image_token":"0.000005","input_cache_read":"0.0000005","input_cache_write":"0.00000625","internal_reasoning":"0.0000225","min_prompt_tokens":272000,"prompt":"0.000005"}],"prompt":"0.0000025"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-08-31","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-5.4"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","minimal","none"],"default_effort":"none","supports_max_tokens":false}},{"id":"openai/gpt-5.4-mini","canonical_slug":"openai/gpt-5.4-mini","hugging_face_id":null,"name":"openai: GPT-5.4 Mini","created":1773705600,"description":"GPT-5.4 Mini brings GPT-5.4's strengths to a faster, more efficient model for high-volume coding, computer use and subagent work. It sits between GPT-5.4 and GPT-5.4 Nano, with a 400K-token context, image input and 128K output.","context_length":400000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.0000045","image_token":"0.00000075","input_cache_read":"0.000000075","input_cache_write":"0.0000009375","internal_reasoning":"0.0000045","prompt":"0.00000075"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-08-31","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-5.4-mini"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","minimal","none"],"default_effort":"none","supports_max_tokens":false}},{"id":"openai/gpt-5.4-nano","canonical_slug":"openai/gpt-5.4-nano","hugging_face_id":null,"name":"openai: GPT-5.4 Nano","created":1773705600,"description":"GPT-5.4 Nano is the smallest and lowest-priced model in the GPT-5.4 family, built for tasks where speed and cost matter most. Good fits are classification, data extraction, ranking and sub-agents, with a 400K-token context, image input and 128K output.","context_length":400000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.00000125","image_token":"0.0000002","input_cache_read":"0.00000002","input_cache_write":"0.00000025","internal_reasoning":"0.00000125","prompt":"0.0000002"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-08-31","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-5.4-nano"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","minimal","none"],"default_effort":"none","supports_max_tokens":false}},{"id":"openai/gpt-5.5","canonical_slug":"openai/gpt-5.5","hugging_face_id":null,"name":"openai: GPT-5.5","created":1776988800,"description":"GPT-5.5 is OpenAI's flagship for the most complex professional work and coding, positioned above GPT-5.4. It takes text and image input with a 1.05M-token context, 128K output and reasoning effort from none to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.00003","image_token":"0.000005","input_cache_read":"0.0000005","input_cache_write":"0.00000625","internal_reasoning":"0.00003","overrides":[{"completion":"0.000045","image_token":"0.00001","input_cache_read":"0.000001","input_cache_write":"0.0000125","internal_reasoning":"0.000045","min_prompt_tokens":272000,"prompt":"0.00001"}],"prompt":"0.000005"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2025-12-01","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-5.5"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-5.6-luna","canonical_slug":"openai/gpt-5.6-luna","hugging_face_id":null,"name":"openai: GPT-5.6 Luna","created":1783555200,"description":"GPT-5.6 Luna is the cost-sensitive model in the GPT-5.6 family, roughly matching the nano models of earlier GPT-5 releases. It suits high-volume workloads and still offers a 1.05M-token context, image input and reasoning effort up to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.0000012","image_token":"0.0000002","input_cache_read":"0.00000002","input_cache_write":"0.00000025","internal_reasoning":"0.0000012","overrides":[{"completion":"0.0000018","image_token":"0.0000004","input_cache_read":"0.00000004","input_cache_write":"0.0000005","internal_reasoning":"0.0000018","min_prompt_tokens":272000,"prompt":"0.0000004"}],"prompt":"0.0000002"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-5.6-luna"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-5.6-sol","canonical_slug":"openai/gpt-5.6-sol","hugging_face_id":null,"name":"openai: GPT-5.6 Sol","created":1783555200,"description":"GPT-5.6 Sol is the flagship of the GPT-5.6 family for complex professional work, comparable to the unsuffixed models of earlier GPT-5 releases. It offers a 1.05M-token context, 128K output, image input and reasoning effort from none to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.00002","image_token":"0.000004","input_cache_read":"0.0000004","input_cache_write":"0.000005","internal_reasoning":"0.00002","overrides":[{"completion":"0.00003","image_token":"0.000008","input_cache_read":"0.0000008","input_cache_write":"0.00001","internal_reasoning":"0.00003","min_prompt_tokens":272000,"prompt":"0.000008"}],"prompt":"0.000004"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-5.6-sol"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-5.6-terra","canonical_slug":"openai/gpt-5.6-terra","hugging_face_id":null,"name":"openai: GPT-5.6 Terra","created":1783555200,"description":"GPT-5.6 Terra is the mid-range GPT-5.6 model, balancing intelligence and cost and roughly matching the mini models of earlier GPT-5 releases. It sits between Sol and Luna, with a 1.05M-token context, image input and reasoning effort from low to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.000012","image_token":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.0000025","internal_reasoning":"0.000012","overrides":[{"completion":"0.000018","image_token":"0.000004","input_cache_read":"0.0000004","input_cache_write":"0.000005","internal_reasoning":"0.000018","min_prompt_tokens":272000,"prompt":"0.000004"}],"prompt":"0.000002"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-02-16","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-5.6-terra"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-6-astra","canonical_slug":"openai/gpt-6-astra","hugging_face_id":null,"name":"openai: GPT-6 Astra","created":1788393600,"description":"GPT-6 Astra is the most capable GPT-6 model, made for the most demanding work. Use it for complex reasoning, coding, computer use, research and document creation, with a 1.05M-token context and reasoning effort from low to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.00005","image_token":"0.00001","input_cache_read":"0.000001","input_cache_write":"0.0000125","internal_reasoning":"0.00005","overrides":[{"completion":"0.000075","image_token":"0.00002","input_cache_read":"0.000002","input_cache_write":"0.000025","internal_reasoning":"0.000075","min_prompt_tokens":272000,"prompt":"0.00002"}],"prompt":"0.00001"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-04-30","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-6-astra"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-6-luna","canonical_slug":"openai/gpt-6-luna","hugging_face_id":null,"name":"openai: GPT-6 Luna","created":1790035200,"description":"GPT-6 Luna is the most efficient GPT-6 model, made for focused, high-volume tasks. It keeps a 1.05M-token context, image input, 128K output and reasoning effort from none to xhigh, so it handles long inputs at low cost.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.0000005","image_token":"0.0000001","input_cache_read":"0.00000001","input_cache_write":"0.000000125","internal_reasoning":"0.0000005","overrides":[{"completion":"0.00000075","image_token":"0.0000002","input_cache_read":"0.00000002","input_cache_write":"0.00000025","internal_reasoning":"0.00000075","min_prompt_tokens":272000,"prompt":"0.0000002"}],"prompt":"0.0000001"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-05-18","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-6-luna"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-6-sol","canonical_slug":"openai/gpt-6-sol","hugging_face_id":null,"name":"openai: GPT-6 Sol","created":1790035200,"description":"GPT-6 Sol is the GPT-6 model built for complex coding and agentic workflows, between Luna and Astra in the family. It has a 1.05M-token context, image input, 128K output and reasoning effort from none to xhigh; GPT-6.1 Sol is its newer version.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.00001","image_token":"0.000002","input_cache_read":"0.0000002","input_cache_write":"0.0000025","internal_reasoning":"0.00001","overrides":[{"completion":"0.000015","image_token":"0.000004","input_cache_read":"0.0000004","input_cache_write":"0.000005","internal_reasoning":"0.000015","min_prompt_tokens":272000,"prompt":"0.000004"}],"prompt":"0.000002"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-04-20","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-6-sol"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-6.1-sol","canonical_slug":"openai/gpt-6.1-sol","hugging_face_id":null,"name":"openai: GPT-6.1 Sol","created":1790640000,"description":"GPT-6.1 Sol is the newer Sol model, which OpenAI says delivers near-Astra performance at lower cost for complex coding, computer use and professional work. It has a 1.05M-token context, image input and reasoning effort from low to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.00001","image_token":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000025","internal_reasoning":"0.00001","overrides":[{"completion":"0.000015","image_token":"0.000004","input_cache_read":"0.0000002","input_cache_write":"0.000005","internal_reasoning":"0.000015","min_prompt_tokens":272000,"prompt":"0.000004"}],"prompt":"0.000002"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-04-30","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-6.1-sol"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-6.1-terra","canonical_slug":"openai/gpt-6.1-terra","hugging_face_id":null,"name":"openai: GPT-6.1 Terra","created":1792972800,"description":"GPT-6.1 Terra is OpenAI's mid-tier GPT-6.1 model, priced below GPT-6.1 Sol and built for fast visual reasoning, precise computer use and clear, natural writing. It has a 1.05M-token context, image input and reasoning effort from none to xhigh.","context_length":1050000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0.000005","image_token":"0.000001","input_cache_read":"0.00000005","input_cache_write":"0.00000125","internal_reasoning":"0.000005","overrides":[{"completion":"0.0000075","image_token":"0.000002","input_cache_read":"0.0000001","input_cache_write":"0.0000025","internal_reasoning":"0.0000075","min_prompt_tokens":272000,"prompt":"0.000002"}],"prompt":"0.000001"},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","seed","reasoning","include_reasoning","stream","n","verbosity"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":"2026-06-01","expiration_date":null,"links":{"details":"/v1/models/openai/gpt-6.1-terra"},"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"openai/gpt-image-2","canonical_slug":"openai/gpt-image-2","hugging_face_id":null,"name":"openai: GPT Image 2","created":1776729600,"description":"GPT Image 2 is OpenAI's image generation and editing model. It turns text prompts and reference images into images at flexible sizes, with high-fidelity image input, and bills by text and image tokens.","architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0","image_output":"0.00003","image_token":"0.000008","input_cache_read":"0.00000125","prompt":"0.000005"},"top_provider":{"is_moderated":false},"per_request_limits":null,"supported_parameters":["stream","n"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/openai/gpt-image-2"}},{"id":"openai/gpt-image-2.5-flare","canonical_slug":"openai/gpt-image-2.5-flare","hugging_face_id":null,"name":"openai: GPT Image 2.5 Flare","created":1788825600,"description":"GPT Image 2.5 Flare is OpenAI's fastest model for everyday, high-quality image generation and editing. Pick it when speed matters most; it takes text and image input, offers quality from low to max, and bills at the same token rates as GPT Image 2.","architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0","image_output":"0.00003","image_token":"0.000008","input_cache_read":"0.00000125","prompt":"0.000005"},"top_provider":{"is_moderated":false},"per_request_limits":null,"supported_parameters":["stream","n"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/openai/gpt-image-2.5-flare"}},{"id":"openai/gpt-image-2.5-sunburst","canonical_slug":"openai/gpt-image-2.5-sunburst","hugging_face_id":null,"name":"openai: GPT Image 2.5 Sunburst","created":1788825600,"description":"GPT Image 2.5 Sunburst is OpenAI's most capable image generation and editing model, built for work where image quality and editing precision matter most. It takes text and image input, offers quality from low to max, and bills at the same token rates as GPT Image 2.","architecture":{"modality":"text+image-\u003eimage","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"gpt","instruct_type":null},"pricing":{"completion":"0","image_output":"0.00003","image_token":"0.000008","input_cache_read":"0.00000125","prompt":"0.000005"},"top_provider":{"is_moderated":false},"per_request_limits":null,"supported_parameters":["stream","n"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/openai/gpt-image-2.5-sunburst"}},{"id":"xai/grok-4.6","canonical_slug":"xai/grok-4.6","hugging_face_id":null,"name":"xai: Grok 4.6","created":1786492800,"description":"Grok 4.6 is the previous Grok generation, built for coding, agentic tasks and knowledge work. It takes text and image input with a 500K-token context, tool calling, structured output and reasoning effort from low to xhigh.","context_length":500000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"grok","instruct_type":null},"pricing":{"completion":"0.000006","image_token":"0.000002","input_cache_read":"0.0000005","internal_reasoning":"0.000006","overrides":[{"completion":"0.000012","image_token":"0.000004","input_cache_read":"0.000001","internal_reasoning":"0.000012","min_prompt_tokens":200000,"prompt":"0.000004"}],"prompt":"0.000002"},"top_provider":{"context_length":500000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/xai/grok-4.6"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high","supports_max_tokens":false}},{"id":"xai/grok-4.7","canonical_slug":"xai/grok-4.7","hugging_face_id":null,"name":"xai: Grok 4.7","created":1791158400,"description":"Grok 4.7 is the newest Grok model, built for coding, agentic tasks and knowledge work. It takes text and image input with a 500K-token context, tool calling, structured output and reasoning effort from low to xhigh.","context_length":500000,"architecture":{"modality":"text+image-\u003etext","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"grok","instruct_type":null},"pricing":{"completion":"0.000006","image_token":"0.000002","input_cache_read":"0.0000005","internal_reasoning":"0.000006","overrides":[{"completion":"0.000012","image_token":"0.000004","input_cache_read":"0.000001","internal_reasoning":"0.000012","min_prompt_tokens":200000,"prompt":"0.000004"}],"prompt":"0.000002"},"top_provider":{"context_length":500000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","seed","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/xai/grok-4.7"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high","supports_max_tokens":false}},{"id":"z-ai/glm-5.2","canonical_slug":"z-ai/glm-5.2","hugging_face_id":null,"name":"zai: GLM 5.2","created":1781654400,"description":"GLM 5.2 is Z.ai's model for complex development work, with clear gains in coding, long-context understanding and long-running tasks. Text input with a 1M-token context, up to 128K output, tool calling and adjustable reasoning effort.","context_length":1024000,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"completion":"0.0000044","input_cache_read":"0.00000026","internal_reasoning":"0.0000044","prompt":"0.0000014"},"top_provider":{"context_length":1024000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","max_completion_tokens","temperature","top_p","seed","stop","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/z-ai/glm-5.2"},"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium","supports_max_tokens":false}},{"id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3","hugging_face_id":null,"name":"zai: GLM 5.3","created":1787011200,"description":"GLM 5.3 is a text model from Z.ai in the GLM 5 family. Text input with a 1M-token context, up to 128K output, tool calling and structured output, and it always reasons before it answers.","context_length":1048576,"architecture":{"modality":"text-\u003etext","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"completion":"0.0000044","input_cache_read":"0.00000026","internal_reasoning":"0.0000044","prompt":"0.0000014"},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","response_format","structured_outputs","max_tokens","max_completion_tokens","temperature","top_p","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/z-ai/glm-5.3"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}},{"id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash","hugging_face_id":null,"name":"zai: GLM 5.3 Flash","created":1787875200,"description":"GLM 5.3 Flash is the first natively multimodal model of the GLM 5 family, built on a low-cost architecture. It takes text and image input with a 1M-token context, up to 128K output and tool calling, and always reasons before it answers.","context_length":1024000,"architecture":{"modality":"text+image+file-\u003etext","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"glm","instruct_type":null},"pricing":{"completion":"0.0000005","image_token":"0.00000015","input_cache_read":"0.00000003","internal_reasoning":"0.0000005","prompt":"0.00000015"},"top_provider":{"context_length":1024000,"max_completion_tokens":128000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["tools","tool_choice","parallel_tool_calls","max_tokens","max_completion_tokens","temperature","top_p","seed","stop","logprobs","top_logprobs","reasoning","include_reasoning","stream"],"default_parameters":{},"supported_voices":null,"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/v1/models/z-ai/glm-5.3-flash"},"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium","supports_max_tokens":false}}]}