@agentjido/llmdb 2026.8.2

package/dist/providers/openrouter.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://openrouter.ai/api/v1","config_schema":null,"doc":"https://openrouter.ai/docs","env":["OPENROUTER_API_KEY"],"exclude_models":["~deepseek/deepseek-v4-flash-latest","~x-ai/grok-latest","~anthropic/claude-fable-latest","~anthropic/claude-haiku-latest","~openai/gpt-mini-latest","~google/gemini-pro-latest","~moonshotai/kimi-latest","~google/gemini-flash-latest","~anthropic/claude-sonnet-latest","~openai/gpt-latest","~anthropic/claude-opus-latest","alfredpros/codellama-7b-instruct-solidity","anthropic/claude-3.7-sonnet","arcee-ai/spotlight","baidu/ernie-4.5-21b-a3b","baidu/ernie-4.5-21b-a3b-thinking","baidu/ernie-4.5-300b-a47b","baidu/ernie-4.5-vl-28b-a3b","cognitivecomputations/dolphin3.0-mistral-24b","cognitivecomputations/dolphin3.0-r1-mistral-24b","deepseek/deepseek-r1-0528-qwen3-8b:free","deepseek/deepseek-r1-0528:free","deepseek/deepseek-r1:free","deepseek/deepseek-v3-base:free","deepseek/deepseek-v3.2-speciale","deepseek/deepseek-v4-flash:free","featherless/qwerky-72b","google/gemini-2.0-flash-001","google/gemini-2.0-flash-exp:free","google/gemini-2.0-flash-lite-001","google/gemma-2-9b-it:free","google/gemma-3n-e4b-it:free","meta-llama/llama-4-scout:free","microsoft/mai-ds-r1:free","minimax/minimax-m2.5:free","mistralai/devstral-medium","mistralai/devstral-medium-2507","mistralai/devstral-small","mistralai/devstral-small-2505","mistralai/devstral-small-2505:free","mistralai/mistral-7b-instruct-v0.1","mistralai/mistral-7b-instruct:free","mistralai/mistral-large-2411","mistralai/mistral-nemo:free","mistralai/mistral-small-3.2-24b-instruct:free","mistralai/pixtral-large-2411","moonshotai/kimi-dev-72b:free","moonshotai/kimi-k2:free","nex-agi/deepseek-v3.1-nex-n1","nousresearch/deephermes-3-llama-3-8b-preview","nousresearch/hermes-2-pro-llama-3-8b","openai/gpt-4-0314","openai/gpt-4-1106-preview","openai/gpt-4o-audio-preview","openai/gpt-5.2-chat-latest","openrouter/cypher-alpha:free","openrouter/horizon-alpha","openrouter/horizon-beta","openrouter/sonoma-dusk-alpha","openrouter/sonoma-sky-alpha","qwen/qwen2.5-vl-32b-instruct:free","qwen/qwen2.5-vl-72b-instruct:free","qwen/qwen3-8b:free","qwen/qwen3-14b:free","qwen/qwen3-30b-a3b:free","qwen/qwen3-32b:free","qwen/qwen3-235b-a22b:free","qwen/qwen3-235b-a22b-07-25:free","qwen/qwq-32b:free","sao10k/l3-euryale-70b","sarvamai/sarvam-m:free","thudm/glm-z1-32b:free","tngtech/deepseek-r1t2-chimera:free","x-ai/grok-3-mini","x-ai/grok-3-mini-beta","x-ai/grok-4","x-ai/grok-4-fast","x-ai/grok-4-fast:free","x-ai/grok-code-fast-1","xiaomi/mimo-v2-omni","xiaomi/mimo-v2-pro"],"extra":null,"id":"openrouter","models":{"ai21/jamba-large-1.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":2.0,"output":8.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","expiration_date":null,"family":"jamba","hugging_face_id":"ai21labs/AI21-Jamba-Large-1.7","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/ai21/jamba-large-1.7/endpoints"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"ai21/jamba-large-1.7","knowledge":"2024-08-31","last_updated":"2025-08-08","lifecycle":null,"limits":{"context":256000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AI21: Jamba Large 1.7","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-08","retired":false,"tags":null},"aion-labs/aion-2.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":0.8,"output":1.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/aion-labs/aion-2.0-20260223/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"aion-labs/aion-2.0","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-2.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"aion-labs/aion-3.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.75,"input":3.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/aion-labs/aion-3.0-20260707/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"aion-labs/aion-3.0","knowledge":null,"last_updated":"2026-07-07","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-3.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-07","retired":false,"tags":null},"aion-labs/aion-3.0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.18,"input":0.7,"output":1.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/aion-labs/aion-3.0-mini-20260707/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"aion-labs/aion-3.0-mini","knowledge":null,"last_updated":"2026-07-07","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-3.0-Mini","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-07","retired":false,"tags":null},"aion-labs/aion-rp-llama-3.1-8b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.8,"output":1.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/aion-labs/aion-rp-llama-3.1-8b/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"aion-labs/aion-rp-llama-3.1-8b","knowledge":"2023-12-31","last_updated":"2025-02-04","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AionLabs: Aion-RP 1.0 (8B)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-02-04","retired":false,"tags":null},"alibaba/happyhorse-1.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/alibaba/happyhorse-1.0-20260624/endpoints"},"supported_voices":null},"family":null,"id":"alibaba/happyhorse-1.0","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Alibaba: HappyHorse 1.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"alibaba/happyhorse-1.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/alibaba/happyhorse-1.1-20260624/endpoints"},"supported_voices":null},"family":null,"id":"alibaba/happyhorse-1.1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Alibaba: HappyHorse 1.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"alibaba/wan-2.6":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/alibaba/wan-2.6-20260327/endpoints"},"supported_voices":null},"family":null,"id":"alibaba/wan-2.6","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Alibaba: Wan 2.6","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-28","retired":false,"tags":null},"alibaba/wan-2.7":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/alibaba/wan-2.7-20260414/endpoints"},"supported_voices":null},"family":null,"id":"alibaba/wan-2.7","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Alibaba: Wan 2.7","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-15","retired":false,"tags":null},"allenai/olmo-3-32b-think":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.15,"output":0.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"allenai","hugging_face_id":"allenai/Olmo-3-32B-Think","knowledge_cutoff":null,"links":{"details":"/api/v1/models/allenai/olmo-3-32b-think-20251121/endpoints"},"llmfit":{"architecture":"olmo3","context_length":524288,"discovered":true,"gguf_sources":[],"hf_downloads":13031,"hf_likes":0,"matched_hugging_face_id":"allenai/Olmo-3-32B-Think","memory":{"min_ram_gb":18.0,"min_vram_gb":16.5,"recommended_ram_gb":30.0},"model_id":"allenai/Olmo-3-32B-Think","parameter_count":"32.2B","parameters_raw":32233522176,"pipeline_tag":"text-generation","provider":"allenai","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"allenai/olmo-3-32b-think","knowledge":null,"last_updated":"2025-11-21","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"AllenAI: Olmo 3 32B Think","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-21","retired":false,"tags":null},"amazon/nova-2-lite-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.3,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":3.1,"coding_index":23,"intelligence_index":18.2},"design_arena":[]},"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"nova","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/amazon/nova-2-lite-v1/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"amazon/nova-2-lite-v1","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":1000000,"output":65535},"modalities":{"input":["text","image","video","pdf","file"],"output":["text"]},"model":null,"name":"Amazon: Nova 2 Lite","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"amazon/nova-lite-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.06,"output":0.24},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"family":"nova-lite","hugging_face_id":"","knowledge_cutoff":"2024-10-31","links":{"details":"/api/v1/models/amazon/nova-lite-v1/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"amazon/nova-lite-v1","knowledge":"2024-10-31","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":300000,"output":5120},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Amazon: Nova Lite 1.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"amazon/nova-micro-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.035,"output":0.14},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"family":"nova-micro","hugging_face_id":"","knowledge_cutoff":"2024-10-31","links":{"details":"/api/v1/models/amazon/nova-micro-v1/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"amazon/nova-micro-v1","knowledge":"2024-10-31","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":128000,"output":5120},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Amazon: Nova Micro 1.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"amazon/nova-premier-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.625,"input":2.5,"output":12.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":858,"rank":117,"win_rate":26.2}]},"description":"Flagship model for demanding analysis, coding, and production agent workflows","expiration_date":null,"family":"nova","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/amazon/nova-premier-v1/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"amazon/nova-premier-v1","knowledge":null,"last_updated":"2025-10-31","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Amazon: Nova Premier 1.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-31","retired":false,"tags":null},"amazon/nova-pro-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.8,"output":3.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":819,"rank":120,"win_rate":21.4}]},"description":"Flagship model for demanding analysis, coding, and production agent workflows","expiration_date":null,"family":"nova-pro","hugging_face_id":"","knowledge_cutoff":"2024-10-31","links":{"details":"/api/v1/models/amazon/nova-pro-v1/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"amazon/nova-pro-v1","knowledge":"2024-10-31","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":300000,"output":5120},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Amazon: Nova Pro 1.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"anthracite-org/magnum-v4-72b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":3.0,"output":5.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"anthracite-org/magnum-v4-72b","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/anthracite-org/magnum-v4-72b/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthracite-org/magnum-v4-72b","knowledge":"2024-06-30","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":16384,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Magnum v4 72B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"anthropic/claude-3-haiku":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"cache_write":0.3,"input":0.25,"output":1.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","expiration_date":null,"family":"claude","hugging_face_id":null,"knowledge_cutoff":"2023-08-31","links":{"details":"/api/v1/models/anthropic/claude-3-haiku/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-3-haiku","knowledge":"2023-08-31","last_updated":"2024-03-13","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude 3 Haiku","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2024-03-13","retired":false,"tags":null},"anthropic/claude-fable-5":{"aliases":["~anthropic/claude-fable-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.0,"cache_write":12.5,"input":10.0,"output":50.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":52.8,"coding_index":76.5,"intelligence_index":59.9},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1300,"rank":1,"win_rate":65},{"arena":"agents","category":"agentichtmlslides","elo":1254,"rank":1,"win_rate":59.4},{"arena":"agents","category":"agenticslides(html)","elo":1252,"rank":1,"win_rate":59.5},{"arena":"agents","category":"androidnative","elo":1316,"rank":1,"win_rate":66.8},{"arena":"agents","category":"fullstack","elo":1297,"rank":2,"win_rate":64},{"arena":"agents","category":"godotgamedev","elo":1344,"rank":1,"win_rate":70.2},{"arena":"agents","category":"htmlslides","elo":1260,"rank":1,"win_rate":59},{"arena":"agents","category":"mobileapps","elo":1256,"rank":5,"win_rate":57.3},{"arena":"agents","category":"python-pptxslides","elo":1304,"rank":3,"win_rate":63.7},{"arena":"agents","category":"webapps","elo":1304,"rank":2,"win_rate":59.7},{"arena":"models","category":"3d","elo":1376,"rank":3,"win_rate":62.7},{"arena":"models","category":"asciiart","elo":1367,"rank":1,"win_rate":70.2},{"arena":"models","category":"codecategories","elo":1345,"rank":3,"win_rate":60.2},{"arena":"models","category":"dataviz","elo":1341,"rank":5,"win_rate":58.8},{"arena":"models","category":"gamedev","elo":1407,"rank":1,"win_rate":65.1},{"arena":"models","category":"svg","elo":1354,"rank":1,"win_rate":66.3},{"arena":"models","category":"uicomponent","elo":1355,"rank":3,"win_rate":59},{"arena":"models","category":"website","elo":1328,"rank":4,"win_rate":60}]},"description":"Claude model for creative writing, analysis, and controlled agent workflows","expiration_date":null,"family":"claude-fable","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-5-fable-20260609/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"anthropic/claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Fable 5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"anthropic/claude-haiku-4.5":{"aliases":["~anthropic/claude-haiku-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"cache_write":1.25,"input":1.0,"output":5.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":16.4,"coding_index":43.9,"intelligence_index":29.6},"design_arena":[{"arena":"models","category":"3d","elo":1127,"rank":76,"win_rate":41.1},{"arena":"models","category":"asciiart","elo":1177,"rank":36,"win_rate":49.3},{"arena":"models","category":"codecategories","elo":1143,"rank":74,"win_rate":44.9},{"arena":"models","category":"dataviz","elo":1151,"rank":71,"win_rate":45.6},{"arena":"models","category":"gamedev","elo":1149,"rank":66,"win_rate":44.6},{"arena":"models","category":"svg","elo":1073,"rank":62,"win_rate":39.1},{"arena":"models","category":"uicomponent","elo":1135,"rank":68,"win_rate":42.7},{"arena":"models","category":"website","elo":1146,"rank":75,"win_rate":45.1}]},"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","expiration_date":null,"family":"claude-haiku","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-haiku-20251001/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":63999,"min":1024,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-haiku-4.5","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Haiku 4.5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"anthropic/claude-opus-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.5,"cache_write":18.75,"input":15.0,"output":75.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1194,"rank":47,"win_rate":57.7},{"arena":"models","category":"codecategories","elo":1189,"rank":59,"win_rate":55.6},{"arena":"models","category":"dataviz","elo":1172,"rank":62,"win_rate":57.9},{"arena":"models","category":"gamedev","elo":1223,"rank":41,"win_rate":59.9},{"arena":"models","category":"svg","elo":1175,"rank":41,"win_rate":57.7},{"arena":"models","category":"uicomponent","elo":1189,"rank":55,"win_rate":59.2},{"arena":"models","category":"website","elo":1188,"rank":60,"win_rate":54.6}]},"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/anthropic/claude-4-opus-20250522/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":31999,"min":1024,"type":"budget_tokens"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-opus-4","knowledge":"2025-01-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-opus-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.5,"cache_write":18.75,"input":15.0,"output":75.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1208,"rank":43,"win_rate":51.8},{"arena":"models","category":"asciiart","elo":1203,"rank":21,"win_rate":51.4},{"arena":"models","category":"codecategories","elo":1200,"rank":50,"win_rate":55.8},{"arena":"models","category":"dataviz","elo":1192,"rank":51,"win_rate":56.4},{"arena":"models","category":"gamedev","elo":1224,"rank":40,"win_rate":58.5},{"arena":"models","category":"svg","elo":1200,"rank":29,"win_rate":60.8},{"arena":"models","category":"uicomponent","elo":1198,"rank":51,"win_rate":57.9},{"arena":"models","category":"website","elo":1200,"rank":55,"win_rate":55.3}]},"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/anthropic/claude-4.1-opus-20250805/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":31999,"min":1024,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.1","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.1","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"anthropic/claude-opus-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"cache_write":6.25,"input":5.0,"output":25.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1269,"rank":27,"win_rate":58.5},{"arena":"models","category":"asciiart","elo":1227,"rank":17,"win_rate":54.7},{"arena":"models","category":"codecategories","elo":1271,"rank":25,"win_rate":59.6},{"arena":"models","category":"dataviz","elo":1269,"rank":21,"win_rate":58.5},{"arena":"models","category":"gamedev","elo":1282,"rank":23,"win_rate":59.4},{"arena":"models","category":"svg","elo":1228,"rank":18,"win_rate":58.7},{"arena":"models","category":"uicomponent","elo":1274,"rank":26,"win_rate":58.5},{"arena":"models","category":"website","elo":1271,"rank":26,"win_rate":59.8},{"arena":"agents","category":"androidnative","elo":1211,"rank":12,"win_rate":65.5},{"arena":"agents","category":"fullstack","elo":1199,"rank":14,"win_rate":59.9},{"arena":"agents","category":"mobileapps","elo":1249,"rank":6,"win_rate":60.5},{"arena":"agents","category":"webapps","elo":1207,"rank":18,"win_rate":54.7}]},"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.5-opus-20251124/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"max":63999,"min":1024,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.5","knowledge":"2025-05","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"anthropic/claude-opus-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"cache_write":6.25,"input":5.0,"output":25.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1237,"rank":7,"win_rate":68.8},{"arena":"agents","category":"fullstack","elo":1263,"rank":7,"win_rate":68.6},{"arena":"agents","category":"mobileapps","elo":1280,"rank":1,"win_rate":64.8},{"arena":"agents","category":"webapps","elo":1252,"rank":12,"win_rate":60.8},{"arena":"models","category":"3d","elo":1329,"rank":8,"win_rate":62.4},{"arena":"models","category":"asciiart","elo":1292,"rank":8,"win_rate":63.3},{"arena":"models","category":"codecategories","elo":1319,"rank":5,"win_rate":61.5},{"arena":"models","category":"dataviz","elo":1311,"rank":9,"win_rate":59},{"arena":"models","category":"gamedev","elo":1331,"rank":8,"win_rate":61.3},{"arena":"models","category":"svg","elo":1276,"rank":5,"win_rate":61.1},{"arena":"models","category":"uicomponent","elo":1323,"rank":8,"win_rate":60.4},{"arena":"models","category":"website","elo":1316,"rank":8,"win_rate":61.5}]},"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","expiration_date":null,"family":"claude-opus","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.6-opus-20260205/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":false,"mandatory":false,"supported_efforts":["max","high","medium","low"],"supports_max_tokens":true},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.6","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-04","retired":false,"tags":null},"anthropic/claude-opus-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"cache_write":6.25,"input":5.0,"output":25.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":44.4,"coding_index":73.6,"intelligence_index":53.5},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1254,"rank":3,"win_rate":61.4},{"arena":"agents","category":"agentichtmlslides","elo":1243,"rank":3,"win_rate":58},{"arena":"agents","category":"agenticslides","elo":1334,"rank":1,"win_rate":64.7},{"arena":"agents","category":"agenticslides(html)","elo":1242,"rank":3,"win_rate":57.8},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1331,"rank":1,"win_rate":65.2},{"arena":"agents","category":"androidnative","elo":1265,"rank":5,"win_rate":56},{"arena":"agents","category":"fullstack","elo":1503,"rank":1,"win_rate":80.1},{"arena":"agents","category":"godotgamedev","elo":1270,"rank":3,"win_rate":60.9},{"arena":"agents","category":"htmlslides","elo":1244,"rank":2,"win_rate":57.6},{"arena":"agents","category":"pptxslides","elo":1333,"rank":1,"win_rate":64.9},{"arena":"agents","category":"python-pptxslides","elo":1336,"rank":2,"win_rate":63.1},{"arena":"agents","category":"webapps","elo":1302,"rank":3,"win_rate":61.5},{"arena":"models","category":"3d","elo":1305,"rank":15,"win_rate":56.6},{"arena":"models","category":"asciiart","elo":1321,"rank":2,"win_rate":66.4},{"arena":"models","category":"codecategories","elo":1318,"rank":6,"win_rate":58.7},{"arena":"models","category":"dataviz","elo":1310,"rank":11,"win_rate":58.2},{"arena":"models","category":"gamedev","elo":1334,"rank":6,"win_rate":59.9},{"arena":"models","category":"svg","elo":1270,"rank":7,"win_rate":59.2},{"arena":"models","category":"uicomponent","elo":1337,"rank":5,"win_rate":60},{"arena":"models","category":"website","elo":1319,"rank":6,"win_rate":59.2}]},"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","expiration_date":null,"family":"claude-opus","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.7-opus-20260416/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":false,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"anthropic/claude-opus-4.7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.7","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic/claude-opus-4.7-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":3.0,"cache_write":37.5,"input":30.0,"output":150.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.7-opus-fast-20260512/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":false,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"anthropic/claude-opus-4.7-fast","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.7 (Fast)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-12","retired":false,"tags":null},"anthropic/claude-opus-4.8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"cache_write":6.25,"input":5.0,"output":25.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":47.2,"coding_index":74.3,"intelligence_index":55.7},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1261,"rank":2,"win_rate":61.6},{"arena":"agents","category":"agentichtmlslides","elo":1227,"rank":4,"win_rate":55.6},{"arena":"agents","category":"agenticslides","elo":1294,"rank":2,"win_rate":64.8},{"arena":"agents","category":"agenticslides(html)","elo":1230,"rank":4,"win_rate":56},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1310,"rank":2,"win_rate":68.9},{"arena":"agents","category":"androidnative","elo":1265,"rank":6,"win_rate":59.6},{"arena":"agents","category":"fullstack","elo":1286,"rank":4,"win_rate":62.4},{"arena":"agents","category":"godotgamedev","elo":1254,"rank":5,"win_rate":58.9},{"arena":"agents","category":"htmlslides","elo":1238,"rank":3,"win_rate":57},{"arena":"agents","category":"mobileapps","elo":1257,"rank":4,"win_rate":57.7},{"arena":"agents","category":"pptxslides","elo":1306,"rank":2,"win_rate":67.9},{"arena":"agents","category":"python-pptxslides","elo":1298,"rank":4,"win_rate":65.9},{"arena":"agents","category":"webapps","elo":1271,"rank":6,"win_rate":53.7},{"arena":"models","category":"3d","elo":1276,"rank":25,"win_rate":53.4},{"arena":"models","category":"asciiart","elo":1306,"rank":5,"win_rate":63.1},{"arena":"models","category":"codecategories","elo":1270,"rank":26,"win_rate":53.7},{"arena":"models","category":"dataviz","elo":1262,"rank":24,"win_rate":54.3},{"arena":"models","category":"gamedev","elo":1298,"rank":17,"win_rate":54.9},{"arena":"models","category":"svg","elo":1225,"rank":20,"win_rate":53.3},{"arena":"models","category":"uicomponent","elo":1280,"rank":24,"win_rate":54.5},{"arena":"models","category":"website","elo":1269,"rank":27,"win_rate":54.1}]},"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.8-opus-20260528/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":false,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.8","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-27","retired":false,"tags":null},"anthropic/claude-opus-4.8-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.0,"cache_write":12.5,"input":10.0,"output":50.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.8-opus-fast-20260528/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":false,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"anthropic/claude-opus-4.8-fast","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.8 (Fast)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-27","retired":false,"tags":null},"anthropic/claude-opus-5":{"aliases":["~anthropic/claude-opus-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"cache_write":6.25,"input":5.0,"output":25.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":55.3,"coding_index":78,"intelligence_index":60.7},"design_arena":[{"arena":"agents","category":"webapps","elo":1288,"rank":5,"win_rate":56},{"arena":"models","category":"3d","elo":1393,"rank":2,"win_rate":64.8},{"arena":"models","category":"codecategories","elo":1361,"rank":2,"win_rate":60.9},{"arena":"models","category":"dataviz","elo":1391,"rank":1,"win_rate":64.7},{"arena":"models","category":"uicomponent","elo":1385,"rank":2,"win_rate":62.1},{"arena":"models","category":"website","elo":1343,"rank":2,"win_rate":59.3}]},"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5-20260723/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-opus-5-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.0,"cache_write":12.5,"input":10.0,"output":50.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","expiration_date":null,"family":"claude-opus","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5-fast-20260723/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"anthropic/claude-opus-5-fast","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Claude Opus 5 (Fast)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-sonnet-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"cache_write":3.75,"input":3.0,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":16.6,"coding_index":37.6,"intelligence_index":28.9},"design_arena":[{"arena":"models","category":"3d","elo":1195,"rank":46,"win_rate":57.8},{"arena":"models","category":"codecategories","elo":1170,"rank":65,"win_rate":53.4},{"arena":"models","category":"dataviz","elo":1178,"rank":59,"win_rate":55.8},{"arena":"models","category":"gamedev","elo":1191,"rank":52,"win_rate":54.8},{"arena":"models","category":"svg","elo":1126,"rank":50,"win_rate":51.1},{"arena":"models","category":"uicomponent","elo":1165,"rank":62,"win_rate":58},{"arena":"models","category":"website","elo":1169,"rank":67,"win_rate":52.4}]},"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","expiration_date":null,"family":"claude-sonnet","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/anthropic/claude-4-sonnet-20250522/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":63999,"min":1024,"type":"budget_tokens"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4","knowledge":"2025-01-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 4","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-sonnet-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"cache_write":3.75,"input":3.0,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":24.6,"coding_index":52.1,"intelligence_index":36.4},"design_arena":[{"arena":"models","category":"3d","elo":1213,"rank":42,"win_rate":51.2},{"arena":"models","category":"asciiart","elo":1242,"rank":14,"win_rate":56.2},{"arena":"models","category":"codecategories","elo":1212,"rank":43,"win_rate":51.7},{"arena":"models","category":"dataviz","elo":1193,"rank":50,"win_rate":47.4},{"arena":"models","category":"gamedev","elo":1219,"rank":42,"win_rate":51.4},{"arena":"models","category":"svg","elo":1162,"rank":42,"win_rate":52.3},{"arena":"models","category":"uicomponent","elo":1209,"rank":43,"win_rate":49.8},{"arena":"models","category":"website","elo":1213,"rank":46,"win_rate":52.1},{"arena":"agents","category":"fullstack","elo":1096,"rank":22,"win_rate":43.5},{"arena":"agents","category":"mobileapps","elo":1196,"rank":18,"win_rate":52.3},{"arena":"agents","category":"webapps","elo":1112,"rank":27,"win_rate":43.1}]},"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","expiration_date":null,"family":"claude-sonnet","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/anthropic/claude-4.5-sonnet-20250929/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":63999,"min":1024,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4.5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 4.5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"anthropic/claude-sonnet-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"cache_write":3.75,"input":3.0,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":40.8,"coding_index":63,"intelligence_index":47.2},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1190,"rank":9,"win_rate":52.3},{"arena":"agents","category":"androidnative","elo":1233,"rank":8,"win_rate":62.2},{"arena":"agents","category":"fullstack","elo":1253,"rank":8,"win_rate":64.1},{"arena":"agents","category":"godotgamedev","elo":1226,"rank":7,"win_rate":60.6},{"arena":"agents","category":"mobileapps","elo":1272,"rank":2,"win_rate":63.4},{"arena":"agents","category":"webapps","elo":1239,"rank":15,"win_rate":56.8},{"arena":"models","category":"3d","elo":1290,"rank":21,"win_rate":57.6},{"arena":"models","category":"asciiart","elo":1266,"rank":10,"win_rate":59.6},{"arena":"models","category":"codecategories","elo":1306,"rank":10,"win_rate":59.5},{"arena":"models","category":"dataviz","elo":1308,"rank":12,"win_rate":58.3},{"arena":"models","category":"gamedev","elo":1311,"rank":13,"win_rate":59},{"arena":"models","category":"svg","elo":1244,"rank":14,"win_rate":58.9},{"arena":"models","category":"uicomponent","elo":1308,"rank":14,"win_rate":58.5},{"arena":"models","category":"website","elo":1309,"rank":9,"win_rate":60.3}]},"description":"Claude workhorse for coding agents, careful analysis, and production cost control","expiration_date":null,"family":"claude-sonnet","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-4.6-sonnet-20260217/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":false,"supported_efforts":["max","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4.6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 4.6","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"anthropic/claude-sonnet-5":{"aliases":["~anthropic/claude-sonnet-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"cache_write":2.5,"input":2.0,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":46.7,"coding_index":71.5,"intelligence_index":53.4},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1239,"rank":4,"win_rate":56},{"arena":"agents","category":"androidnative","elo":1270,"rank":2,"win_rate":59.5},{"arena":"agents","category":"fullstack","elo":1272,"rank":6,"win_rate":59.8},{"arena":"agents","category":"godotgamedev","elo":1270,"rank":4,"win_rate":60.4},{"arena":"agents","category":"htmlslides","elo":1232,"rank":4,"win_rate":54.1},{"arena":"agents","category":"mobileapps","elo":1232,"rank":8,"win_rate":54.3},{"arena":"agents","category":"python-pptxslides","elo":1248,"rank":6,"win_rate":55.1},{"arena":"agents","category":"webapps","elo":1300,"rank":4,"win_rate":58.4},{"arena":"models","category":"3d","elo":1310,"rank":12,"win_rate":56.4},{"arena":"models","category":"asciiart","elo":1243,"rank":13,"win_rate":52.7},{"arena":"models","category":"codecategories","elo":1300,"rank":15,"win_rate":54.9},{"arena":"models","category":"dataviz","elo":1263,"rank":23,"win_rate":52.5},{"arena":"models","category":"gamedev","elo":1350,"rank":2,"win_rate":55.5},{"arena":"models","category":"svg","elo":1239,"rank":16,"win_rate":53.8},{"arena":"models","category":"uicomponent","elo":1311,"rank":10,"win_rate":54.9},{"arena":"models","category":"website","elo":1296,"rank":14,"win_rate":55.2}]},"description":"Everyday Claude agent model for coding, planning, browsing, and general work","expiration_date":null,"family":"claude-sonnet","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5-20260630/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"anthropic/claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"arcee-ai/trinity-large-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.06,"input":0.22,"output":0.85},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":3.7,"coding_index":25.8,"intelligence_index":18.2},"design_arena":[{"arena":"models","category":"3d","elo":1137,"rank":70,"win_rate":41.3},{"arena":"models","category":"asciiart","elo":1078,"rank":53,"win_rate":37.1},{"arena":"models","category":"codecategories","elo":1146,"rank":73,"win_rate":40.1},{"arena":"models","category":"dataviz","elo":1125,"rank":78,"win_rate":39.3},{"arena":"models","category":"gamedev","elo":1131,"rank":76,"win_rate":38.4},{"arena":"models","category":"svg","elo":1063,"rank":65,"win_rate":35.2},{"arena":"models","category":"uicomponent","elo":1080,"rank":82,"win_rate":32.6},{"arena":"models","category":"website","elo":1160,"rank":69,"win_rate":41.3}]},"description":"Flagship model for demanding analysis, coding, and production agent workflows","expiration_date":null,"family":"trinity","hugging_face_id":"arcee-ai/Trinity-Large-Thinking","knowledge_cutoff":null,"links":{"details":"/api/v1/models/arcee-ai/trinity-large-thinking/endpoints"},"llmfit":{"architecture":"afmoe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":10583,"hf_likes":0,"matched_hugging_face_id":"arcee-ai/Trinity-Large-Thinking","memory":{"min_ram_gb":222.8,"min_vram_gb":204.2,"recommended_ram_gb":371.3},"model_id":"arcee-ai/Trinity-Large-Thinking","moe":{"active_experts":4,"active_parameters":25849006824,"is_moe":true,"num_experts":256},"parameter_count":"398.6B","parameters_raw":398635286016,"pipeline_tag":"text-generation","provider":"arcee-ai","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"arcee-ai/trinity-large-thinking","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Arcee AI: Trinity Large Thinking","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"arcee-ai/virtuoso-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.75,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","expiration_date":null,"hugging_face_id":"","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/arcee-ai/virtuoso-large/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"arcee-ai/virtuoso-large","knowledge":"2025-03-31","last_updated":"2025-05-05","lifecycle":null,"limits":{"context":131072,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Arcee AI: Virtuoso Large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-05-05","retired":false,"tags":null},"baai/bge-base-en-v1.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":768,"max_dimensions":768,"min_dimensions":768},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"BAAI/bge-base-en-v1.5","knowledge_cutoff":null,"links":{"details":"/api/v1/models/baai/bge-base-en-v1.5-20251117/endpoints"},"llmfit":{"architecture":"bert","context_length":512,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/bge-base-en-v1.5-GGUF"}],"hf_downloads":9630426,"hf_likes":0,"matched_hugging_face_id":"BAAI/bge-base-en-v1.5","memory":{"min_ram_gb":1.0,"min_vram_gb":0.5,"recommended_ram_gb":2.0},"model_id":"BAAI/bge-base-en-v1.5","parameter_count":"109M","parameters_raw":109482752,"pipeline_tag":"feature-extraction","provider":"BAAI","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"supported_voices":null},"family":null,"id":"baai/bge-base-en-v1.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"BAAI: bge-base-en-v1.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"baai/bge-large-en-v1.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.01,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"BAAI/bge-large-en-v1.5","knowledge_cutoff":null,"links":{"details":"/api/v1/models/baai/bge-large-en-v1.5-20251117/endpoints"},"llmfit":{"architecture":"bert","context_length":512,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/bge-large-en-v1.5-GGUF"}],"hf_downloads":13358048,"hf_likes":707,"matched_hugging_face_id":"BAAI/bge-large-en-v1.5","memory":{"min_ram_gb":1.0,"min_vram_gb":0.5,"recommended_ram_gb":2.0},"model_id":"BAAI/bge-large-en-v1.5","parameter_count":"335M","parameters_raw":335142400,"pipeline_tag":"feature-extraction","provider":"BAAI","quantization":"Q4_K_M","release_date":"2023-09-12","source":"llmfit","use_case":"Text embeddings for RAG"},"supported_voices":null},"family":null,"id":"baai/bge-large-en-v1.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"BAAI: bge-large-en-v1.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"baai/bge-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.01,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"BAAI/bge-m3","knowledge_cutoff":null,"links":{"details":"/api/v1/models/baai/bge-m3-20251117/endpoints"},"supported_voices":null},"family":null,"id":"baai/bge-m3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8194,"output":8194},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"BAAI: bge-m3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"baidu/ernie-4.5-vl-424b-a47b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.42,"output":1.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"ernie","hugging_face_id":"baidu/ERNIE-4.5-VL-424B-A47B-PT","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/baidu/ernie-4.5-vl-424b-a47b/endpoints"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"baidu/ernie-4.5-vl-424b-a47b","knowledge":"2025-03-31","last_updated":"2025-06-30","lifecycle":null,"limits":{"context":123000,"output":16000},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Baidu: ERNIE 4.5 VL 424B A47B ","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-06-30","retired":false,"tags":null},"black-forest-labs/flux-3-video":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/black-forest-labs/flux-3-video-20260804/endpoints"},"supported_voices":null},"family":null,"id":"black-forest-labs/flux-3-video","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image","video"],"output":["video"]},"model":null,"name":"Black Forest Labs: FLUX.3 Video","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-08-04","retired":false,"tags":null},"black-forest-labs/flux.2-flex":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1219,"rank":5,"win_rate":54.9},{"arena":"models","category":"image","elo":1225,"rank":5,"win_rate":56},{"arena":"models","category":"logo","elo":1225,"rank":5,"win_rate":54.4}]},"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/black-forest-labs/flux.2-flex/endpoints"},"supported_voices":null},"family":null,"id":"black-forest-labs/flux.2-flex","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":67344},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Black Forest Labs: FLUX.2 Flex","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-25","retired":false,"tags":null},"black-forest-labs/flux.2-klein-4b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1033,"rank":10,"win_rate":35.8},{"arena":"models","category":"image","elo":1086,"rank":10,"win_rate":39},{"arena":"models","category":"logo","elo":1073,"rank":10,"win_rate":38},{"arena":"models","category":"imageediting","elo":1070,"rank":6,"win_rate":39.2}]},"expiration_date":null,"hugging_face_id":"black-forest-labs/FLUX.2-klein-4B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/black-forest-labs/flux.2-klein-4b/endpoints"},"supported_voices":null},"family":null,"id":"black-forest-labs/flux.2-klein-4b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":40960},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Black Forest Labs: FLUX.2 Klein 4B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-14","retired":false,"tags":null},"black-forest-labs/flux.2-max":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/black-forest-labs/flux.2-max/endpoints"},"supported_voices":null},"family":null,"id":"black-forest-labs/flux.2-max","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":46864},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Black Forest Labs: FLUX.2 Max","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"black-forest-labs/flux.2-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1203,"rank":6,"win_rate":47.7},{"arena":"models","category":"image","elo":1219,"rank":6,"win_rate":49.5},{"arena":"models","category":"logo","elo":1210,"rank":8,"win_rate":49.5},{"arena":"models","category":"imageediting","elo":1150,"rank":4,"win_rate":47.6}]},"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/black-forest-labs/flux.2-pro/endpoints"},"supported_voices":null},"family":null,"id":"black-forest-labs/flux.2-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":46864},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Black Forest Labs: FLUX.2 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-25","retired":false,"tags":null},"bytedance-seed/seed-1.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.25,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"seed","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-1.6-20250625/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"bytedance-seed/seed-1.6","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed 1.6","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"bytedance-seed/seed-1.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"seed","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-1.6-flash-20250625/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"bytedance-seed/seed-1.6-flash","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed 1.6 Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"bytedance-seed/seed-2.0-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.25,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"seed","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-2.0-lite-20260309/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":false,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"bytedance-seed/seed-2.0-lite","knowledge":null,"last_updated":"2026-03-10","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed-2.0-Lite","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"bytedance-seed/seed-2.0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"seed","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance-seed/seed-2.0-mini-20260224/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":false,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"bytedance-seed/seed-2.0-mini","knowledge":null,"last_updated":"2026-02-26","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"ByteDance Seed: Seed-2.0-Mini","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"bytedance-seed/seedream-4.5":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance-seed/seedream-4.5-20251203/endpoints"},"supported_voices":null},"family":null,"id":"bytedance-seed/seedream-4.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"ByteDance Seed: Seedream 4.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"bytedance/seedance-1-5-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance/seedance-1-5-pro-20260320/endpoints"},"supported_voices":null},"family":null,"id":"bytedance/seedance-1-5-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"ByteDance: Seedance 1.5 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-23","retired":false,"tags":null},"bytedance/seedance-2.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance/seedance-2.0-20260414/endpoints"},"supported_voices":null},"family":null,"id":"bytedance/seedance-2.0","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image","audio","video"],"output":["video"]},"model":null,"name":"ByteDance: Seedance 2.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-15","retired":false,"tags":null},"bytedance/seedance-2.0-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/bytedance/seedance-2.0-fast-20260414/endpoints"},"supported_voices":null},"family":null,"id":"bytedance/seedance-2.0-fast","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image","audio","video"],"output":["video"]},"model":null,"name":"ByteDance: Seedance 2.0 Fast","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-15","retired":false,"tags":null},"bytedance/ui-tars-1.5-7b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"cache_read":0.1,"input":0.1,"output":0.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","expiration_date":null,"hugging_face_id":"ByteDance-Seed/UI-TARS-1.5-7B","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/bytedance/ui-tars-1.5-7b/endpoints"},"llmfit":{"architecture":"qwen2_5_vl","context_length":128000,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/UI-TARS-1.5-7B-GGUF"}],"hf_downloads":850796,"hf_likes":0,"matched_hugging_face_id":"ByteDance-Seed/UI-TARS-1.5-7B","memory":{"min_ram_gb":4.6,"min_vram_gb":4.2,"recommended_ram_gb":7.7},"model_id":"ByteDance-Seed/UI-TARS-1.5-7B","parameter_count":"8.3B","parameters_raw":8292166656,"pipeline_tag":"image-text-to-text","provider":"bytedance-seed","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"bytedance/ui-tars-1.5-7b","knowledge":"2025-01-31","last_updated":"2025-07-22","lifecycle":null,"limits":{"context":128000,"output":2048},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"ByteDance: UI-TARS 7B ","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"canopylabs/orpheus-3b-0.1-ft":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":7.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/canopylabs/orpheus-3b-0.1-ft/endpoints"},"supported_voices":["tara","leah","jess","leo","dan","mia","zac"]},"family":null,"id":"canopylabs/orpheus-3b-0.1-ft","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Canopy Labs: Orpheus 3B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"cognitivecomputations/dolphin-mistral-24b-venice-edition":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.2,"output":0.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","expiration_date":null,"family":"mistral","hugging_face_id":"cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","knowledge_cutoff":"2024-04-30","links":{"details":"/api/v1/models/venice/uncensored/endpoints"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","knowledge":"2024-04-30","last_updated":"2025-07-09","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Venice: Uncensored","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"cohere/command-a":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":2.5,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":9.2,"coding_index":27.8,"intelligence_index":22.5},"design_arena":[]},"description":"Cohere command model for multilingual enterprise agents, tools, and chat","expiration_date":null,"family":"command-a","hugging_face_id":"CohereForAI/c4ai-command-a-03-2025","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/cohere/command-a-03-2025/endpoints"},"llmfit":{"architecture":"cohere2","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/c4ai-command-a-03-2025-GGUF"},{"provider":"mradermacher","repo":"mradermacher/c4ai-command-a-03-2025-GGUF"}],"hf_downloads":1814,"hf_likes":394,"matched_hugging_face_id":"CohereForAI/c4ai-command-a-03-2025","memory":{"min_ram_gb":62.1,"min_vram_gb":56.9,"recommended_ram_gb":103.4},"model_id":"CohereForAI/c4ai-command-a-03-2025","parameter_count":"111.1B","parameters_raw":111057580032,"pipeline_tag":"text-generation","provider":"Cohere","quantization":"Q4_K_M","release_date":"2025-03-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"cohere/command-a","knowledge":"2024-08-31","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere: Command A","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"cohere/command-r-08-2024":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","expiration_date":null,"family":"command-r","hugging_face_id":null,"knowledge_cutoff":"2024-03-31","links":{"details":"/api/v1/models/cohere/command-r-08-2024/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"cohere/command-r-08-2024","knowledge":"2024-06-01","last_updated":"2024-08-30","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere: Command R (08-2024)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-08-30","retired":false,"tags":null},"cohere/command-r-plus-08-2024":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":2.5,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Cohere's RAG workhorse for long-context enterprise search and tool use","expiration_date":null,"family":"command-r","hugging_face_id":null,"knowledge_cutoff":"2024-03-31","links":{"details":"/api/v1/models/cohere/command-r-plus-08-2024/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"cohere/command-r-plus-08-2024","knowledge":"2024-06-01","last_updated":"2024-08-30","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere: Command R+ (08-2024)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-08-30","retired":false,"tags":null},"cohere/command-r7b-12-2024":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0375,"output":0.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","expiration_date":null,"family":"command-r","hugging_face_id":"","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/cohere/command-r7b-12-2024/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"cohere/command-r7b-12-2024","knowledge":"2024-06-01","last_updated":"2024-12-02","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere: Command R7B (12-2024)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-14","retired":false,"tags":null},"cohere/north-mini-code:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":3.1,"coding_index":36.5,"intelligence_index":19.8},"design_arena":[]},"description":"Cohere coding model for practical software engineering and agentic edits","expiration_date":null,"family":"north","hugging_face_id":"CohereLabs/North-Mini-Code-1.0","knowledge_cutoff":null,"links":{"details":"/api/v1/models/cohere/north-mini-code-20260617/endpoints"},"llmfit":{"architecture":"cohere2_moe","context_length":500000,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/North-Mini-Code-1.0-GGUF"},{"provider":"bartowski","repo":"bartowski/North-Mini-Code-1.0-GGUF"},{"provider":"mradermacher","repo":"mradermacher/North-Mini-Code-1.0-GGUF"}],"hf_downloads":14751,"hf_likes":0,"matched_hugging_face_id":"CohereLabs/North-Mini-Code-1.0","memory":{"min_ram_gb":17.0,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"CohereLabs/North-Mini-Code-1.0","moe":{"active_experts":8,"active_parameters":3334220729,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30484303872,"pipeline_tag":"text-generation","provider":"coherelabs","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"cohere/north-mini-code:free","knowledge":null,"last_updated":"2026-06-17","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere: North Mini Code (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-17","retired":false,"tags":null},"cohere/rerank-4-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/cohere/rerank-4-fast/endpoints"},"supported_voices":null},"family":null,"id":"cohere/rerank-4-fast","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text"],"output":["rerank"]},"model":null,"name":"Cohere: Rerank 4 Fast","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-06","retired":false,"tags":null},"cohere/rerank-4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/cohere/rerank-4-pro/endpoints"},"supported_voices":null},"family":null,"id":"cohere/rerank-4-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text"],"output":["rerank"]},"model":null,"name":"Cohere: Rerank 4 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-06","retired":false,"tags":null},"cohere/rerank-v3.5":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/cohere/rerank-v3.5/endpoints"},"supported_voices":null},"family":null,"id":"cohere/rerank-v3.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text"],"output":["rerank"]},"model":null,"name":"Cohere: Rerank v3.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-05","retired":false,"tags":null},"deepcogito/cogito-v2.1-671b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":1.25,"output":1.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"cogito","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/deepcogito/cogito-v2.1-671b-20251118/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepcogito/cogito-v2.1-671b","knowledge":null,"last_updated":"2025-11-13","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Deep Cogito: Cogito v2.1 671B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"deepgram/aura-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":30.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/deepgram/aura-2-20260716/endpoints"},"supported_voices":["aura-2-thalia-en","aura-2-agathe-fr","aura-2-agustina-es","aura-2-alvaro-es","aura-2-ama-ja","aura-2-amalthea-en","aura-2-andromeda-en","aura-2-antonia-es","aura-2-apollo-en","aura-2-aquila-es","aura-2-arcas-en","aura-2-aries-en","aura-2-asteria-en","aura-2-athena-en","aura-2-atlas-en","aura-2-aurelia-de","aura-2-aurora-en","aura-2-beatrix-nl","aura-2-callista-en","aura-2-carina-es","aura-2-celeste-es","aura-2-cesare-it","aura-2-cinzia-it","aura-2-cora-en","aura-2-cordelia-en","aura-2-cornelia-nl","aura-2-daphne-nl","aura-2-delia-en","aura-2-demetra-it","aura-2-diana-es","aura-2-dionisio-it","aura-2-draco-en","aura-2-ebisu-ja","aura-2-elara-de","aura-2-electra-en","aura-2-elio-it","aura-2-estrella-es","aura-2-fabian-de","aura-2-flavio-it","aura-2-fujin-ja","aura-2-gloria-es","aura-2-harmonia-en","aura-2-hector-fr","aura-2-helena-en","aura-2-hera-en","aura-2-hermes-en","aura-2-hestia-nl","aura-2-hyperion-en","aura-2-iris-en","aura-2-izanami-ja","aura-2-janus-en","aura-2-javier-es","aura-2-julius-de","aura-2-juno-en","aura-2-jupiter-en","aura-2-kara-de","aura-2-lara-de","aura-2-lars-nl","aura-2-leda-nl","aura-2-livia-it","aura-2-luciano-es","aura-2-luna-en","aura-2-maia-it","aura-2-mars-en","aura-2-melia-it","aura-2-minerva-en","aura-2-neptune-en","aura-2-nestor-es","aura-2-odysseus-en","aura-2-olivia-es","aura-2-ophelia-en","aura-2-orion-en","aura-2-orpheus-en","aura-2-pandora-en","aura-2-phoebe-en","aura-2-pluto-en","aura-2-rhea-nl","aura-2-roman-nl","aura-2-sander-nl","aura-2-saturn-en","aura-2-selena-es","aura-2-selene-en","aura-2-silvia-es","aura-2-sirio-es","aura-2-theia-en","aura-2-uzume-ja","aura-2-valerio-es","aura-2-vesta-en","aura-2-viktoria-de","aura-2-zeus-en"]},"family":null,"id":"deepgram/aura-2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Deepgram: Aura-2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"deepgram/nova-3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":4.3e3,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/deepgram/nova-3-20260714/endpoints"},"supported_voices":null},"family":null,"id":"deepgram/nova-3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"Deepgram: Nova-3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"deepseek/deepseek-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.2574,"output":1.0287},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1142,"rank":65,"win_rate":50.6},{"arena":"models","category":"codecategories","elo":1137,"rank":79,"win_rate":48.5},{"arena":"models","category":"dataviz","elo":1123,"rank":81,"win_rate":51.2},{"arena":"models","category":"gamedev","elo":1106,"rank":80,"win_rate":43.9},{"arena":"models","category":"svg","elo":1024,"rank":73,"win_rate":38.8},{"arena":"models","category":"uicomponent","elo":1129,"rank":71,"win_rate":52.8},{"arena":"models","category":"website","elo":1143,"rank":77,"win_rate":48.5}]},"description":"DeepSeek chat model for instruction following, coding, and analysis","expiration_date":null,"family":"deepseek","hugging_face_id":"deepseek-ai/DeepSeek-V3","knowledge_cutoff":"2024-07-31","links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3/endpoints"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3-GGUF"}],"hf_downloads":1177282,"hf_likes":4110,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2024-12-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-chat","knowledge":"2025-09","last_updated":"2026-02-28","lifecycle":null,"limits":{"context":163840,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepseek/deepseek-chat-v3-0324":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.135,"input":0.27,"output":1.12},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":1.5,"coding_index":21.2,"intelligence_index":15.4},"design_arena":[]},"description":"DeepSeek chat model for instruction following, coding, and analysis","expiration_date":null,"family":"deepseek","hugging_face_id":"deepseek-ai/DeepSeek-V3-0324","knowledge_cutoff":"2024-07-31","links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3-0324/endpoints"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":899240,"hf_likes":3151,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3-0324","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3-0324","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-03-24","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-chat-v3-0324","knowledge":"2024-07-31","last_updated":"2025-03-24","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3 0324","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-24","retired":false,"tags":null},"deepseek/deepseek-chat-v3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.13,"input":0.25,"output":0.95},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1133,"rank":72,"win_rate":48},{"arena":"models","category":"codecategories","elo":1141,"rank":77,"win_rate":47.9},{"arena":"models","category":"dataviz","elo":1126,"rank":76,"win_rate":46.8},{"arena":"models","category":"gamedev","elo":1137,"rank":71,"win_rate":47.1},{"arena":"models","category":"svg","elo":1014,"rank":75,"win_rate":38.2},{"arena":"models","category":"uicomponent","elo":1120,"rank":74,"win_rate":47.6},{"arena":"models","category":"website","elo":1146,"rank":76,"win_rate":48}]},"description":"DeepSeek chat model for instruction following, coding, and analysis","expiration_date":null,"family":"deepseek","hugging_face_id":"deepseek-ai/DeepSeek-V3.1","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/deepseek/deepseek-chat-v3.1/endpoints"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":273040,"hf_likes":825,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-08-21","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-chat-v3.1","knowledge":"2025-03-31","last_updated":"2025-08-21","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-21","retired":false,"tags":null},"deepseek/deepseek-r1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.7,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":3.1,"coding_index":24.6,"intelligence_index":18.5},"design_arena":[]},"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","expiration_date":null,"family":"deepseek-thinking","hugging_face_id":"deepseek-ai/DeepSeek-R1","knowledge_cutoff":"2024-07-31","links":{"details":"/api/v1/models/deepseek/deepseek-r1/endpoints"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-R1-GGUF"}],"hf_downloads":9604023,"hf_likes":13537,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-01-20","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-r1","knowledge":"2024-07","last_updated":"2025-05-29","lifecycle":null,"limits":{"context":163840,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: R1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek/deepseek-r1-0528":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.35,"input":0.5,"output":2.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1167,"rank":58,"win_rate":53.4},{"arena":"models","category":"codecategories","elo":1167,"rank":66,"win_rate":52.6},{"arena":"models","category":"dataviz","elo":1205,"rank":44,"win_rate":60.7},{"arena":"models","category":"gamedev","elo":1150,"rank":65,"win_rate":49.5},{"arena":"models","category":"svg","elo":1086,"rank":56,"win_rate":48.7},{"arena":"models","category":"uicomponent","elo":1138,"rank":66,"win_rate":54.9},{"arena":"models","category":"website","elo":1172,"rank":65,"win_rate":52.7}]},"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","expiration_date":null,"family":"deepseek","hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/deepseek/deepseek-r1-0528/endpoints"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":206900,"hf_likes":2457,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-R1-0528","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-05-28","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-0528","knowledge":"2025-03-31","last_updated":"2025-05-28","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: R1 0528","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"deepseek/deepseek-r1-distill-llama-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.8,"output":0.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","expiration_date":null,"family":"deepseek-thinking","hugging_face_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","knowledge_cutoff":"2024-07-31","links":{"details":"/api/v1/models/deepseek/deepseek-r1-distill-llama-70b/endpoints"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF"},{"provider":"bartowski","repo":"bartowski/DeepSeek-R1-Distill-Llama-70B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/DeepSeek-R1-Distill-Llama-70B-GGUF"}],"hf_downloads":543482,"hf_likes":791,"matched_hugging_face_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-01-20","source":"llmfit","use_case":"Advanced reasoning, chain-of-thought"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-r1-distill-llama-70b","knowledge":"2024-07-31","last_updated":"2025-01-23","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: R1 Distill Llama 70B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-01-23","retired":false,"tags":null},"deepseek/deepseek-v3.1-terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.135,"input":0.27,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":18.1,"coding_index":43.5,"intelligence_index":30.4},"design_arena":[{"arena":"models","category":"3d","elo":1196,"rank":45,"win_rate":56},{"arena":"models","category":"codecategories","elo":1204,"rank":48,"win_rate":56},{"arena":"models","category":"dataviz","elo":1189,"rank":54,"win_rate":52.8},{"arena":"models","category":"gamedev","elo":1183,"rank":58,"win_rate":52.5},{"arena":"models","category":"svg","elo":1112,"rank":54,"win_rate":50.1},{"arena":"models","category":"uicomponent","elo":1218,"rank":40,"win_rate":59.5},{"arena":"models","category":"website","elo":1210,"rank":50,"win_rate":56.4}]},"description":"DeepSeek chat model for instruction following, coding, and analysis","expiration_date":null,"family":"deepseek","hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/deepseek/deepseek-v3.1-terminus/endpoints"},"llmfit":{"architecture":"deepseek_v3","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":16978,"hf_likes":0,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.1-Terminus","memory":{"min_ram_gb":382.5,"min_vram_gb":350.6,"recommended_ram_gb":637.5},"model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","moe":{"active_experts":8,"active_parameters":54548594820,"is_moe":true,"num_experts":256},"parameter_count":"684.5B","parameters_raw":684531386000,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1-terminus","knowledge":"2025-03-31","last_updated":"2025-09-22","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.1 Terminus","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-22","retired":false,"tags":null},"deepseek/deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1345,"input":0.269,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":18.3,"coding_index":44.2,"intelligence_index":32},"design_arena":[{"arena":"models","category":"3d","elo":1188,"rank":50,"win_rate":49.5},{"arena":"models","category":"asciiart","elo":1120,"rank":50,"win_rate":40.5},{"arena":"models","category":"codecategories","elo":1193,"rank":58,"win_rate":49.3},{"arena":"models","category":"dataviz","elo":1185,"rank":57,"win_rate":48.1},{"arena":"models","category":"gamedev","elo":1184,"rank":57,"win_rate":46.6},{"arena":"models","category":"svg","elo":1080,"rank":59,"win_rate":40.8},{"arena":"models","category":"uicomponent","elo":1184,"rank":56,"win_rate":46.8},{"arena":"models","category":"website","elo":1198,"rank":56,"win_rate":50.2}]},"description":"DeepSeek chat model for instruction following, coding, and analysis","expiration_date":null,"family":"deepseek","hugging_face_id":"deepseek-ai/DeepSeek-V3.2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v3.2-20251201/endpoints"},"llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/DeepSeek-V3.2-GGUF"}],"hf_downloads":1238427,"hf_likes":1462,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2","moe":{"active_experts":8,"active_parameters":37000000000,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-12-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":false,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-v3.2-exp":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.27,"output":0.41},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1204,"rank":44,"win_rate":56.4},{"arena":"models","category":"codecategories","elo":1199,"rank":52,"win_rate":54.2},{"arena":"models","category":"dataviz","elo":1179,"rank":58,"win_rate":50.6},{"arena":"models","category":"gamedev","elo":1197,"rank":49,"win_rate":53},{"arena":"models","category":"svg","elo":1079,"rank":60,"win_rate":42},{"arena":"models","category":"uicomponent","elo":1202,"rank":47,"win_rate":53.3},{"arena":"models","category":"website","elo":1202,"rank":54,"win_rate":54.2}]},"description":"DeepSeek chat model for instruction following, coding, and analysis","expiration_date":null,"family":"deepseek","hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","knowledge_cutoff":"2025-07-31","links":{"details":"/api/v1/models/deepseek/deepseek-v3.2-exp/endpoints"},"llmfit":{"architecture":"deepseek_v32","context_length":6553600,"discovered":true,"gguf_sources":[],"hf_downloads":252109,"hf_likes":993,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Exp","memory":{"min_ram_gb":383.0,"min_vram_gb":351.1,"recommended_ram_gb":638.3},"model_id":"deepseek-ai/DeepSeek-V3.2-Exp","moe":{"active_experts":8,"active_parameters":54617567164,"is_moe":true,"num_experts":256},"parameter_count":"685.4B","parameters_raw":685396921376,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2-exp","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V3.2 Exp","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"deepseek/deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1244,"rank":35,"win_rate":49.3},{"arena":"models","category":"asciiart","elo":1147,"rank":45,"win_rate":42.8},{"arena":"models","category":"codecategories","elo":1234,"rank":37,"win_rate":48.9},{"arena":"models","category":"dataviz","elo":1152,"rank":69,"win_rate":40.5},{"arena":"models","category":"gamedev","elo":1249,"rank":32,"win_rate":50.2},{"arena":"models","category":"svg","elo":1201,"rank":28,"win_rate":48.4},{"arena":"models","category":"uicomponent","elo":1199,"rank":49,"win_rate":44.7},{"arena":"models","category":"website","elo":1231,"rank":38,"win_rate":49.1}]},"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","expiration_date":null,"family":"deepseek-flash","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","interleaved":{"field":"reasoning_content"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260423/endpoints"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":2746291,"hf_likes":1982,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","memory":{"min_ram_gb":162.6,"min_vram_gb":149.0,"recommended_ram_gb":271.0},"model_id":"deepseek-ai/DeepSeek-V4-Flash","moe":{"active_experts":6,"active_parameters":13000000000,"is_moe":true,"num_experts":256},"parameter_count":"290.9B","parameters_raw":290944616402,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","mandatory":false,"supported_efforts":["xhigh","high"]},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V4 Flash 0423","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/deepseek-v4-flash-0731":{"aliases":["~deepseek/deepseek-v4-flash-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.018,"input":0.09,"output":0.18},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":45.7,"coding_index":69.1,"intelligence_index":49.9},"design_arena":[]},"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","expiration_date":null,"family":"deepseek-flash","hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","knowledge_cutoff":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-20260731/endpoints"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":236076,"hf_likes":1963,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash-0731","memory":{"min_ram_gb":170.0,"min_vram_gb":155.8,"recommended_ram_gb":283.3},"model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","moe":{"active_experts":6,"active_parameters":21981788050,"is_moe":true,"num_experts":256},"parameter_count":"304.2B","parameters_raw":304180418494,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-07-31","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["max","high","low"]},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"supported_voices":[],"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V4 Flash 0731","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek/deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.003625,"input":0.435,"output":0.87},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":36.4,"coding_index":59.4,"intelligence_index":44.3},"design_arena":[{"arena":"agents","category":"fullstack","elo":948,"rank":33,"win_rate":22.1},{"arena":"agents","category":"godotgamedev","elo":1059,"rank":27,"win_rate":34},{"arena":"agents","category":"webapps","elo":1000,"rank":32,"win_rate":26.4},{"arena":"models","category":"3d","elo":1315,"rank":10,"win_rate":58.7},{"arena":"models","category":"asciiart","elo":1188,"rank":28,"win_rate":46.7},{"arena":"models","category":"codecategories","elo":1272,"rank":24,"win_rate":53.8},{"arena":"models","category":"dataviz","elo":1223,"rank":40,"win_rate":49.3},{"arena":"models","category":"gamedev","elo":1286,"rank":22,"win_rate":55.5},{"arena":"models","category":"svg","elo":1183,"rank":38,"win_rate":46.5},{"arena":"models","category":"uicomponent","elo":1258,"rank":31,"win_rate":51.6},{"arena":"models","category":"website","elo":1259,"rank":30,"win_rate":52.3}]},"description":"Open MoE flagship with million-token context for coding and long agent runs","expiration_date":null,"family":"deepseek-thinking","hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","interleaved":{"field":"reasoning_content"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-20260423/endpoints"},"llmfit":{"architecture":"deepseek_v4","context_length":16777216,"discovered":false,"gguf_sources":[],"hf_downloads":1596582,"hf_likes":5373,"matched_hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","memory":{"min_ram_gb":893.4,"min_vram_gb":819.0,"recommended_ram_gb":1489.0},"model_id":"deepseek-ai/DeepSeek-V4-Pro","moe":{"active_experts":6,"active_parameters":49000000000,"is_moe":true,"num_experts":384},"parameter_count":"1598.8B","parameters_raw":1598839674782,"pipeline_tag":"text-generation","provider":"DeepSeek","quantization":"Q4_K_M","release_date":"2026-04-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","mandatory":false,"supported_efforts":["xhigh","high"]},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek: DeepSeek V4 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"fish-audio/s1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":15.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/fish-audio/s1-20260729/endpoints"},"supported_voices":null},"family":null,"id":"fish-audio/s1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Fish Audio: S1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"fish-audio/s2-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":15.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/fish-audio/s2-pro-20260729/endpoints"},"supported_voices":null},"family":null,"id":"fish-audio/s2-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Fish Audio: S2 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"fish-audio/s2.1-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":15.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/fish-audio/s2.1-pro-20260729/endpoints"},"supported_voices":null},"family":null,"id":"fish-audio/s2.1-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Fish Audio: S2.1 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"fish-audio/s2.1-pro-free:free":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/fish-audio/s2.1-pro-free-20260729/endpoints"},"supported_voices":null},"family":null,"id":"fish-audio/s2.1-pro-free:free","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Fish Audio: S2.1 Pro Free (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"fish-audio/transcribe-1":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":100.0,"output":0.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/fish-audio/transcribe-1-20260729/endpoints"},"supported_voices":null},"family":null,"id":"fish-audio/transcribe-1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"Fish Audio: Transcribe 1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"google/chirp-3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.6e4,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/chirp-3/endpoints"},"supported_voices":null},"family":null,"id":"google/chirp-3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"Google: Chirp 3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-05","retired":false,"tags":null},"google/gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":1.0,"cache_read":0.03,"cache_write":0.083333,"image":0.3,"input":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1127,"rank":77,"win_rate":47.4},{"arena":"models","category":"codecategories","elo":1133,"rank":80,"win_rate":46.9},{"arena":"models","category":"dataviz","elo":1153,"rank":68,"win_rate":48.4},{"arena":"models","category":"gamedev","elo":1118,"rank":79,"win_rate":44.3},{"arena":"models","category":"uicomponent","elo":1128,"rank":72,"win_rate":48.9},{"arena":"models","category":"website","elo":1138,"rank":79,"win_rate":47.1},{"arena":"models","category":"svg","elo":1067,"rank":63,"win_rate":43.1}]},"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","expiration_date":null,"family":"gemini-flash","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/google/gemini-2.5-flash/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","audio","video","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 2.5 Flash","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"audio":1.0,"cache_read":0.03,"cache_write":0.083333,"image":0.3,"input":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1197,"rank":8,"win_rate":56.9},{"arena":"models","category":"image","elo":1210,"rank":8,"win_rate":55.6},{"arena":"models","category":"logo","elo":1185,"rank":9,"win_rate":51.4}]},"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","expiration_date":null,"family":"gemini-flash","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/google/gemini-2.5-flash-image/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Google: Nano Banana (Gemini 2.5 Flash Image)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-07","retired":false,"tags":null},"google/gemini-2.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":0.3,"cache_read":0.01,"cache_write":0.083333,"image":0.1,"input":0.1,"output":0.4,"reasoning":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","expiration_date":null,"family":"gemini-flash-lite","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/google/gemini-2.5-flash-lite/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":24576,"min":512,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-2.5-flash-lite","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","audio","video","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 2.5 Flash Lite","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"google/gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":1.25,"cache_read":0.125,"cache_write":0.375,"image":1.25,"input":1.25,"output":10.0,"reasoning":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":7.1,"coding_index":33.3,"intelligence_index":25.8},"design_arena":[{"arena":"models","category":"3d","elo":1138,"rank":68,"win_rate":52.1},{"arena":"models","category":"codecategories","elo":1182,"rank":60,"win_rate":58.3},{"arena":"models","category":"dataviz","elo":1273,"rank":19,"win_rate":71.8},{"arena":"models","category":"gamedev","elo":1162,"rank":62,"win_rate":54.9},{"arena":"models","category":"uicomponent","elo":1176,"rank":59,"win_rate":60.1},{"arena":"models","category":"website","elo":1191,"rank":59,"win_rate":58.9}]},"description":"Google's proven reasoning model for coding, math, and multimodal analysis","expiration_date":null,"family":"gemini-pro","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/google/gemini-2.5-pro/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 2.5 Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":1.25,"cache_read":0.125,"cache_write":0.375,"image":1.25,"input":1.25,"output":10.0,"reasoning":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","expiration_date":null,"family":"gemini","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/google/gemini-2.5-pro-preview-06-05/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-2.5-pro-preview","knowledge":"2025-01-31","last_updated":"2025-06-05","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["pdf","image","text","audio","file"],"output":["text"]},"model":null,"name":"Google: Gemini 2.5 Pro Preview 06-05","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-06-05","retired":false,"tags":null},"google/gemini-2.5-pro-preview-05-06":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":1.25,"cache_read":0.125,"cache_write":0.375,"image":1.25,"input":1.25,"output":10.0,"reasoning":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","expiration_date":null,"family":"gemini-pro","hugging_face_id":"","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/google/gemini-2.5-pro-preview-03-25/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-2.5-pro-preview-05-06","knowledge":"2025-01-31","last_updated":"2025-05-07","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","pdf","audio","video","file"],"output":["text"]},"model":null,"name":"Google: Gemini 2.5 Pro Preview 05-06","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"google/gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":1.0,"cache_read":0.05,"cache_write":0.083333,"image":0.5,"input":0.5,"output":3.0,"reasoning":3.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticslides","elo":1073,"rank":9,"win_rate":39.3},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1075,"rank":9,"win_rate":39.3},{"arena":"agents","category":"androidnative","elo":1086,"rank":26,"win_rate":48.1},{"arena":"agents","category":"fullstack","elo":1105,"rank":21,"win_rate":47.1},{"arena":"agents","category":"godotgamedev","elo":1161,"rank":14,"win_rate":50.6},{"arena":"agents","category":"mobileapps","elo":1151,"rank":25,"win_rate":46.6},{"arena":"agents","category":"python-pptxslides","elo":1019,"rank":19,"win_rate":38.3},{"arena":"agents","category":"webapps","elo":1160,"rank":25,"win_rate":48.4},{"arena":"models","category":"3d","elo":1239,"rank":36,"win_rate":62.7},{"arena":"models","category":"codecategories","elo":1218,"rank":40,"win_rate":57.6},{"arena":"models","category":"gamedev","elo":1219,"rank":43,"win_rate":58.3},{"arena":"models","category":"website","elo":1219,"rank":41,"win_rate":57}]},"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","expiration_date":null,"family":"gemini-flash","hugging_face_id":"","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3-flash-preview-20251217/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":false,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3 Flash Preview","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"google/gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":2.0,"cache_read":0.2,"cache_write":0.375,"image":2.0,"input":2.0,"output":12.0,"reasoning":12.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","expiration_date":null,"family":"gemini-pro","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3-pro-image-20260528/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-18","retired":false,"tags":null},"google/gemini-3-pro-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"audio":2.0,"cache_read":0.2,"cache_write":0.375,"image":2.0,"input":2.0,"output":12.0,"reasoning":12.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1281,"rank":3,"win_rate":65.8},{"arena":"models","category":"image","elo":1267,"rank":3,"win_rate":62.1},{"arena":"models","category":"logo","elo":1256,"rank":3,"win_rate":61},{"arena":"models","category":"imageediting","elo":1269,"rank":2,"win_rate":65.4}]},"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","expiration_date":null,"family":"gemini-pro","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3-pro-image-preview-20251120/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3-pro-image-preview","knowledge":"2025-01","last_updated":"2025-11-20","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-20","retired":false,"tags":null},"google/gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.5,"output":3.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","expiration_date":null,"family":"gemini-flash","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-image-20260528/endpoints"},"open_weights":false,"reasoning":{"default_effort":"minimal","default_enabled":true,"mandatory":false,"supported_efforts":["high","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-18","retired":false,"tags":null},"google/gemini-3.1-flash-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.5,"output":3.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1291,"rank":2,"win_rate":66.3},{"arena":"models","category":"image","elo":1300,"rank":2,"win_rate":65.1},{"arena":"models","category":"logo","elo":1278,"rank":2,"win_rate":62.9}]},"description":"Image model for prompt-driven generation, editing, and visual design workflows","expiration_date":null,"family":"gemini-flash","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-image-preview-20260226/endpoints"},"open_weights":false,"reasoning":{"default_effort":"minimal","default_enabled":true,"mandatory":false,"supported_efforts":["high","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image-preview","knowledge":"2025-01","last_updated":"2026-02-26","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["image","text"],"output":["text","image"]},"model":null,"name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"google/gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":0.5,"cache_read":0.025,"cache_write":0.083333,"image":0.25,"input":0.25,"output":1.5,"reasoning":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","expiration_date":null,"family":"gemini-flash-lite","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-20260507/endpoints"},"open_weights":false,"reasoning":{"default_effort":"minimal","default_enabled":true,"mandatory":false,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3.1 Flash Lite","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"google/gemini-3.1-flash-lite-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.25,"output":1.5},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","expiration_date":null,"family":"gemini-flash-lite","hugging_face_id":null,"knowledge_cutoff":"2025-01-01","links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-image-20260630/endpoints"},"open_weights":false,"reasoning":{"default_effort":"minimal","default_enabled":true,"mandatory":false,"supported_efforts":["high","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-image","knowledge":"2025-01","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"google/gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":0.5,"cache_read":0.025,"cache_write":0.083333,"image":0.25,"input":0.25,"output":1.5,"reasoning":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":6.2,"coding_index":34.7,"intelligence_index":25},"design_arena":[{"arena":"models","category":"3d","elo":1103,"rank":82,"win_rate":38.8},{"arena":"models","category":"asciiart","elo":1204,"rank":20,"win_rate":50.6},{"arena":"models","category":"codecategories","elo":1101,"rank":86,"win_rate":36.4},{"arena":"models","category":"dataviz","elo":1072,"rank":89,"win_rate":33.3},{"arena":"models","category":"gamedev","elo":1082,"rank":86,"win_rate":33.7},{"arena":"models","category":"svg","elo":1099,"rank":55,"win_rate":42.5},{"arena":"models","category":"uicomponent","elo":1107,"rank":78,"win_rate":37.7},{"arena":"models","category":"website","elo":1105,"rank":87,"win_rate":36.6}]},"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","expiration_date":null,"family":"gemini-flash-lite","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-lite-preview-20260303/endpoints"},"open_weights":false,"reasoning":{"default_effort":"minimal","default_enabled":true,"mandatory":false,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-preview","knowledge":"2025-01","last_updated":"2026-03-03","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3.1 Flash Lite Preview","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"google/gemini-3.1-flash-tts-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.0,"output":20.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.1-flash-tts-preview/endpoints"},"supported_voices":["Zephyr","Puck","Charon","Kore","Fenrir","Leda","Orus","Aoede","Callirrhoe","Autonoe","Enceladus","Iapetus","Umbriel","Algieba","Despina","Erinome","Algenib","Rasalgethi","Laomedeia","Achernar","Alnilam","Schedar","Gacrux","Pulcherrima","Achird","Zubenelgenubi","Vindemiatrix","Sadachbia","Sadaltager","Sulafat"]},"family":null,"id":"google/gemini-3.1-flash-tts-preview","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Google: Gemini 3.1 Flash TTS Preview","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemini-3.1-pro-preview":{"aliases":["~google/gemini-pro-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":2.0,"cache_read":0.2,"cache_write":0.375,"image":2.0,"input":2.0,"output":12.0,"reasoning":12.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":21.4,"coding_index":68.8,"intelligence_index":46.5},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1124,"rank":17,"win_rate":44.1},{"arena":"agents","category":"agentichtmlslides","elo":1226,"rank":5,"win_rate":55.8},{"arena":"agents","category":"agenticslides","elo":1112,"rank":8,"win_rate":33.8},{"arena":"agents","category":"agenticslides(html)","elo":1219,"rank":5,"win_rate":54.4},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1107,"rank":8,"win_rate":33.9},{"arena":"agents","category":"androidnative","elo":1084,"rank":27,"win_rate":41.6},{"arena":"agents","category":"fullstack","elo":1110,"rank":20,"win_rate":43.1},{"arena":"agents","category":"godotgamedev","elo":1236,"rank":6,"win_rate":60},{"arena":"agents","category":"htmlslides","elo":1203,"rank":11,"win_rate":51.9},{"arena":"agents","category":"mobileapps","elo":1151,"rank":24,"win_rate":45},{"arena":"agents","category":"pptxslides","elo":1110,"rank":8,"win_rate":34.1},{"arena":"agents","category":"python-pptxslides","elo":1109,"rank":17,"win_rate":31.9},{"arena":"agents","category":"webapps","elo":1173,"rank":22,"win_rate":46.6},{"arena":"models","category":"3d","elo":1289,"rank":22,"win_rate":59.5},{"arena":"models","category":"asciiart","elo":1308,"rank":4,"win_rate":63.7},{"arena":"models","category":"codecategories","elo":1270,"rank":27,"win_rate":64.2},{"arena":"models","category":"dataviz","elo":1252,"rank":32,"win_rate":60.5},{"arena":"models","category":"gamedev","elo":1252,"rank":31,"win_rate":54.3},{"arena":"models","category":"svg","elo":1334,"rank":2,"win_rate":68.8},{"arena":"models","category":"uicomponent","elo":1302,"rank":15,"win_rate":68.1},{"arena":"models","category":"website","elo":1274,"rank":23,"win_rate":64.3}]},"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","expiration_date":null,"family":"gemini-pro","hugging_face_id":"","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.1-pro-preview-20260219/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3.1 Pro Preview","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.1-pro-preview-customtools":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":2.0,"cache_read":0.2,"cache_write":0.375,"image":2.0,"input":2.0,"output":12.0,"reasoning":12.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","expiration_date":null,"family":"gemini-pro","hugging_face_id":null,"interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.1-pro-preview-customtools-20260219/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview-customtools","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3.1 Pro Preview Custom Tools","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"google/gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":3.0,"cache_read":0.15,"cache_write":0.083333,"image":1.5,"input":1.5,"output":9.0,"reasoning":9.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":37.4,"coding_index":70.1,"intelligence_index":50.2},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1187,"rank":10,"win_rate":54},{"arena":"agents","category":"agentichtmlslides","elo":1162,"rank":7,"win_rate":45.8},{"arena":"agents","category":"agenticslides","elo":1244,"rank":4,"win_rate":57.5},{"arena":"agents","category":"agenticslides(html)","elo":1162,"rank":7,"win_rate":45.7},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1242,"rank":3,"win_rate":57.8},{"arena":"agents","category":"androidnative","elo":1223,"rank":9,"win_rate":56},{"arena":"agents","category":"fullstack","elo":1235,"rank":10,"win_rate":56.7},{"arena":"agents","category":"godotgamedev","elo":1135,"rank":21,"win_rate":42.9},{"arena":"agents","category":"htmlslides","elo":1172,"rank":16,"win_rate":46.5},{"arena":"agents","category":"mobileapps","elo":1218,"rank":12,"win_rate":53.4},{"arena":"agents","category":"pptxslides","elo":1244,"rank":3,"win_rate":57.7},{"arena":"agents","category":"python-pptxslides","elo":1247,"rank":7,"win_rate":57.4},{"arena":"agents","category":"webapps","elo":1247,"rank":14,"win_rate":53.1},{"arena":"models","category":"3d","elo":1295,"rank":19,"win_rate":57.7},{"arena":"models","category":"asciiart","elo":1294,"rank":7,"win_rate":59.6},{"arena":"models","category":"codecategories","elo":1290,"rank":17,"win_rate":56.3},{"arena":"models","category":"dataviz","elo":1261,"rank":27,"win_rate":54.8},{"arena":"models","category":"gamedev","elo":1323,"rank":10,"win_rate":56.9},{"arena":"models","category":"svg","elo":1296,"rank":3,"win_rate":61},{"arena":"models","category":"uicomponent","elo":1310,"rank":11,"win_rate":56.9},{"arena":"models","category":"website","elo":1283,"rank":21,"win_rate":55.5}]},"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","expiration_date":null,"family":"gemini-flash","hugging_face_id":null,"knowledge_cutoff":"2025-01-01","links":{"details":"/api/v1/models/google/gemini-3.5-flash-20260519/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":true,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3.5 Flash","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":0.3,"cache_read":0.03,"cache_write":0.083333,"image":0.3,"input":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":26.8,"coding_index":49.3,"intelligence_index":36.5},"design_arena":[]},"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","expiration_date":null,"family":"gemini-flash-lite","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.5-flash-lite-20260721/endpoints"},"open_weights":false,"reasoning":{"default_effort":"minimal","default_enabled":true,"mandatory":true,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3.5 Flash Lite","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemini-3.6-flash":{"aliases":["~google/gemini-flash-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":1.5,"cache_read":0.15,"cache_write":0.083333,"image":1.5,"input":1.5,"output":7.5,"reasoning":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":38.7,"coding_index":69.2,"intelligence_index":50.1},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1206,"rank":6,"win_rate":54},{"arena":"agents","category":"androidnative","elo":1103,"rank":24,"win_rate":33.5},{"arena":"agents","category":"htmlslides","elo":1196,"rank":13,"win_rate":51.8},{"arena":"agents","category":"python-pptxslides","elo":1157,"rank":14,"win_rate":47.4},{"arena":"models","category":"3d","elo":1333,"rank":6,"win_rate":54},{"arena":"models","category":"codecategories","elo":1317,"rank":7,"win_rate":55.5},{"arena":"models","category":"dataviz","elo":1344,"rank":4,"win_rate":57.8},{"arena":"models","category":"gamedev","elo":1298,"rank":18,"win_rate":52.3},{"arena":"models","category":"uicomponent","elo":1342,"rank":4,"win_rate":56},{"arena":"models","category":"website","elo":1323,"rank":5,"win_rate":57.9}]},"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","expiration_date":null,"family":"gemini-flash","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-3.6-flash-20260721/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":true,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf","file"],"output":["text"]},"model":null,"name":"Google: Gemini 3.6 Flash","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.014,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemini-embedding-001":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":3072,"max_dimensions":3072,"min_dimensions":128},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"audio":0.0,"image":0.0,"input":0.15,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-embedding-001/endpoints"},"supported_voices":null},"family":null,"id":"google/gemini-embedding-001","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":20000},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Google: Gemini Embedding 001","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-31","retired":false,"tags":null},"google/gemini-embedding-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":true,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"audio":6.5,"image":0.45,"input":0.2,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-embedding-2/endpoints"},"supported_voices":null},"family":null,"id":"google/gemini-embedding-2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text","image","file","audio","video"],"output":["embeddings"]},"model":null,"name":"Google: Gemini Embedding 2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-20","retired":false,"tags":null},"google/gemini-embedding-2-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":3072,"max_dimensions":3072,"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"audio":6.5,"image":0.45,"input":0.2,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemini-embedding-2-preview/endpoints"},"supported_voices":null},"family":null,"id":"google/gemini-embedding-2-preview","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text","image","file","audio","video"],"output":["embeddings"]},"model":null,"name":"Google: Gemini Embedding 2 Preview","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"google/gemma-2-27b-it":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.65,"output":0.65},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-2-27b-it","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/google/gemma-2-27b-it/endpoints"},"llmfit":{"architecture":"gemma2","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/gemma-2-27b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-2-27b-it-GGUF"}],"hf_downloads":118485,"hf_likes":568,"matched_hugging_face_id":"google/gemma-2-27b-it","memory":{"min_ram_gb":15.2,"min_vram_gb":13.9,"recommended_ram_gb":25.4},"model_id":"google/gemma-2-27b-it","parameter_count":"27.2B","parameters_raw":27227128320,"pipeline_tag":"text-generation","provider":"Google","quantization":"Q4_K_M","release_date":"2024-06-24","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-2-27b-it","knowledge":"2024-06-30","last_updated":"2024-07-13","lifecycle":null,"limits":{"context":8192,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Google: Gemma 2 27B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-07-13","retired":false,"tags":null},"google/gemma-3-12b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.05,"output":0.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":0.3,"coding_index":5.8,"intelligence_index":5.5},"design_arena":[]},"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-3-12b-it","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/google/gemma-3-12b-it/endpoints"},"llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-12b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-12b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-12b-it-GGUF"}],"hf_downloads":1281955,"hf_likes":797,"matched_hugging_face_id":"google/gemma-3-12b-it","memory":{"min_ram_gb":6.8,"min_vram_gb":6.2,"recommended_ram_gb":11.4},"model_id":"google/gemma-3-12b-it","parameter_count":"12.2B","parameters_raw":12187325040,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-3-12b-it","knowledge":"2024-08-31","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google: Gemma 3 12B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"google/gemma-3-27b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.04,"input":0.08,"output":0.45},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":0.3,"coding_index":10.1,"intelligence_index":7.4},"design_arena":[]},"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-3-27b-it","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/google/gemma-3-27b-it/endpoints"},"llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-27b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-27b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-27b-it-GGUF"}],"hf_downloads":847078,"hf_likes":2005,"matched_hugging_face_id":"google/gemma-3-27b-it","memory":{"min_ram_gb":15.3,"min_vram_gb":14.1,"recommended_ram_gb":25.5},"model_id":"google/gemma-3-27b-it","parameter_count":"27.4B","parameters_raw":27432406640,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-03-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-3-27b-it","knowledge":"2024-08-31","last_updated":"2025-03-12","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google: Gemma 3 27B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"google/gemma-3-4b-it":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.05,"output":0.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":2.7,"intelligence_index":null},"design_arena":[]},"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-3-4b-it","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/google/gemma-3-4b-it/endpoints"},"llmfit":{"architecture":"gemma3","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3-4b-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3-4b-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3-4b-it-GGUF"}],"hf_downloads":1869741,"hf_likes":1441,"matched_hugging_face_id":"google/gemma-3-4b-it","memory":{"min_ram_gb":2.4,"min_vram_gb":2.2,"recommended_ram_gb":4.0},"model_id":"google/gemma-3-4b-it","parameter_count":"4.3B","parameters_raw":4300079472,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-02-20","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-3-4b-it","knowledge":"2024-08-31","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google: Gemma 3 4B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"google/gemma-3n-e4b-it":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.06,"output":0.12},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":3.2,"intelligence_index":null},"design_arena":[]},"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-3n-E4B-it","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/google/gemma-3n-e4b-it/endpoints"},"llmfit":{"architecture":"gemma3n","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-3n-E4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-3n-E4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-3n-E4B-it-GGUF"}],"hf_downloads":36851,"hf_likes":919,"matched_hugging_face_id":"google/gemma-3n-E4B-it","memory":{"min_ram_gb":4.4,"min_vram_gb":4.0,"recommended_ram_gb":7.3},"model_id":"google/gemma-3n-E4B-it","parameter_count":"7.8B","parameters_raw":7849978192,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2025-06-03","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-3n-e4b-it","knowledge":"2024-08-31","last_updated":"2025-05-20","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Google: Gemma 3n 4B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"google/gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.07,"output":0.34},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":11,"coding_index":39.3,"intelligence_index":25.7},"design_arena":[]},"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-4-26B-A4B-it","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints"},"llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":11882790,"hf_likes":1348,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":false,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Google: Gemma 4 26B A4B ","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-03","retired":false,"tags":null},"google/gemma-4-26b-a4b-it:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":11,"coding_index":39.3,"intelligence_index":25.7},"design_arena":[]},"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-4-26B-A4B-it","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it-20260403/endpoints"},"llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":11882790,"hf_likes":1348,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":false,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-4-26b-a4b-it:free","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Google: Gemma 4 26B A4B  (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-03","retired":false,"tags":null},"google/gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.1,"output":0.34},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":14.4,"coding_index":43.4,"intelligence_index":29.4},"design_arena":[]},"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-4-31B-it","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemma-4-31b-it-20260402/endpoints"},"llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":false,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Google: Gemma 4 31B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31b-it:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":14.4,"coding_index":43.4,"intelligence_index":29.4},"design_arena":[]},"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","expiration_date":null,"family":"gemma","hugging_face_id":"google/gemma-4-31B-it","knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/gemma-4-31b-it-20260402/endpoints"},"llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-31B-it-GGUF"}],"hf_downloads":11886065,"hf_likes":3433,"matched_hugging_face_id":"google/gemma-4-31B-it","memory":{"min_ram_gb":18.3,"min_vram_gb":16.7,"recommended_ram_gb":30.4},"model_id":"google/gemma-4-31B-it","parameter_count":"32.7B","parameters_raw":32682372656,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":false,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"google/gemma-4-31b-it:free","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Google: Gemma 4 31B (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/lyria-3-clip-preview":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","expiration_date":null,"family":"lyria","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/lyria-3-clip-preview-20260330/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"google/lyria-3-clip-preview","knowledge":null,"last_updated":"2026-03-25","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text","audio"]},"model":null,"name":"Google: Lyria 3 Clip Preview","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-30","retired":false,"tags":null},"google/lyria-3-pro-preview":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","expiration_date":null,"family":"lyria","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/lyria-3-pro-preview-20260330/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"google/lyria-3-pro-preview","knowledge":null,"last_updated":"2026-03-25","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text","audio"]},"model":null,"name":"Google: Lyria 3 Pro Preview","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-30","retired":false,"tags":null},"google/veo-3.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/veo-3.1-20260320/endpoints"},"supported_voices":null},"family":null,"id":"google/veo-3.1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Google: Veo 3.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-23","retired":false,"tags":null},"google/veo-3.1-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/veo-3.1-fast-20260320/endpoints"},"supported_voices":null},"family":null,"id":"google/veo-3.1-fast","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Google: Veo 3.1 Fast","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/veo-3.1-lite":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/google/veo-3.1-lite-20260331/endpoints"},"supported_voices":null},"family":null,"id":"google/veo-3.1-lite","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Google: Veo 3.1 Lite","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"gryphe/mythomax-l2-13b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.08,"output":0.11},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"Gryphe/MythoMax-L2-13b","knowledge_cutoff":"2023-06-30","links":{"details":"/api/v1/models/gryphe/mythomax-l2-13b/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"gryphe/mythomax-l2-13b","knowledge":"2023-06-30","last_updated":"2023-07-02","lifecycle":null,"limits":{"context":8192,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MythoMax 13B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-07-02","retired":false,"tags":null},"hexgrad/kokoro-82m":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.62,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/hexgrad/kokoro-82m/endpoints"},"supported_voices":["af_alloy","af_aoede","af_bella","af_heart","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa","bf_alice","bf_emma","bf_isabella","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","ef_dora","em_alex","em_santa","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo","pf_dora","pm_alex","pm_santa","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang"]},"family":null,"id":"hexgrad/kokoro-82m","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"hexgrad: Kokoro 82M","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"ibm-granite/granite-4.0-h-micro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.017,"output":0.112},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"family":"granite","hugging_face_id":"ibm-granite/granite-4.0-h-micro","knowledge_cutoff":null,"links":{"details":"/api/v1/models/ibm-granite/granite-4.0-h-micro/endpoints"},"llmfit":{"architecture":"granitemoehybrid","context_length":131072,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/granite-4.0-h-micro-GGUF"},{"provider":"mradermacher","repo":"mradermacher/granite-4.0-h-micro-GGUF"}],"hf_downloads":24846,"hf_likes":148,"matched_hugging_face_id":"ibm-granite/granite-4.0-h-micro","memory":{"min_ram_gb":1.8,"min_vram_gb":1.6,"recommended_ram_gb":3.0},"model_id":"ibm-granite/granite-4.0-h-micro","parameter_count":"3.2B","parameters_raw":3191396096,"pipeline_tag":"text-generation","provider":"ibm-granite","quantization":"Q4_K_M","release_date":"2025-09-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"ibm-granite/granite-4.0-h-micro","knowledge":null,"last_updated":"2025-10-20","lifecycle":null,"limits":{"context":131000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"IBM: Granite 4.0 Micro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-20","retired":false,"tags":null},"ibm-granite/granite-4.1-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"input":0.05,"output":0.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":9.5,"intelligence_index":null},"design_arena":[]},"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"family":"granite","hugging_face_id":"ibm-granite/granite-4.1-8b","knowledge_cutoff":null,"links":{"details":"/api/v1/models/ibm-granite/granite-4.1-8b-20260429/endpoints"},"llmfit":{"architecture":"granite","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/granite-4.1-8b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/granite-4.1-8b-GGUF"}],"hf_downloads":4085575,"hf_likes":243,"matched_hugging_face_id":"ibm-granite/granite-4.1-8b","memory":{"min_ram_gb":4.9,"min_vram_gb":4.5,"recommended_ram_gb":8.2},"model_id":"ibm-granite/granite-4.1-8b","parameter_count":"8.8B","parameters_raw":8791592960,"pipeline_tag":"text-generation","provider":"ibm-granite","quantization":"Q4_K_M","release_date":"2026-04-06","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"ibm-granite/granite-4.1-8b","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"IBM: Granite 4.1 8B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"inception/mercury-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.025,"input":0.25,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":9.6,"coding_index":31.1,"intelligence_index":21.4},"design_arena":[{"arena":"models","category":"3d","elo":1037,"rank":93,"win_rate":23.5},{"arena":"models","category":"asciiart","elo":1043,"rank":55,"win_rate":27.6},{"arena":"models","category":"codecategories","elo":1021,"rank":103,"win_rate":20.6},{"arena":"models","category":"dataviz","elo":1007,"rank":97,"win_rate":21.1},{"arena":"models","category":"gamedev","elo":1028,"rank":95,"win_rate":20.7},{"arena":"models","category":"svg","elo":1017,"rank":74,"win_rate":24.3},{"arena":"models","category":"uicomponent","elo":988,"rank":96,"win_rate":17.7},{"arena":"models","category":"website","elo":1016,"rank":105,"win_rate":19.9}]},"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"mercury","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/inception/mercury-2-20260304/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"inception/mercury-2","knowledge":null,"last_updated":"2026-03-04","lifecycle":null,"limits":{"context":128000,"output":50000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Inception: Mercury 2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-04","retired":false,"tags":null},"inclusionai/ling-2.6-1t":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.015,"input":0.075,"output":0.625},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","expiration_date":null,"family":"ling","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/inclusionai/ling-2.6-1t-20260423/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"inclusionai/ling-2.6-1t","knowledge":null,"last_updated":"2026-04-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI: Ling-2.6-1T","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"inclusionai/ling-2.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.002,"input":0.01,"output":0.03},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":2.3,"coding_index":25.3,"intelligence_index":14.1},"design_arena":[]},"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"family":"ling","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/inclusionai/ling-2.6-flash-20260421/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"inclusionai/ling-2.6-flash","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI: Ling-2.6-flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"inclusionai/ling-3.0-flash:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"family":"ling","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/inclusionai/ling-3.0-flash-20260723/endpoints"},"open_weights":false,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"inclusionai/ling-3.0-flash:free","knowledge":null,"last_updated":"2026-07-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ling-3.0-flash (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"inclusionai/ring-2.6-1t":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.015,"input":0.075,"output":0.625},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":18.9,"coding_index":42.8,"intelligence_index":30.6},"design_arena":[]},"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"ring","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/inclusionai/ring-2.6-1t-20260508/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","mandatory":true,"supported_efforts":["xhigh","high"]},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"inclusionai/ring-2.6-1t","knowledge":null,"last_updated":"2026-05-08","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"inclusionAI: Ring-2.6-1T","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-08","retired":false,"tags":null},"intfloat/e5-base-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":768,"max_dimensions":768,"min_dimensions":768},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"intfloat/e5-base-v2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/intfloat/e5-base-v2-20251117/endpoints"},"supported_voices":null},"family":null,"id":"intfloat/e5-base-v2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Intfloat: E5-Base-v2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"intfloat/e5-large-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.01,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"intfloat/e5-large-v2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/intfloat/e5-large-v2-20251117/endpoints"},"supported_voices":null},"family":null,"id":"intfloat/e5-large-v2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Intfloat: E5-Large-v2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"intfloat/multilingual-e5-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.01,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"intfloat/multilingual-e5-large","knowledge_cutoff":null,"links":{"details":"/api/v1/models/intfloat/multilingual-e5-large-20251117/endpoints"},"llmfit":{"architecture":"xlm-roberta","context_length":514,"discovered":true,"gguf_sources":[],"hf_downloads":7665419,"hf_likes":0,"matched_hugging_face_id":"intfloat/multilingual-e5-large","memory":{"min_ram_gb":1.0,"min_vram_gb":0.5,"recommended_ram_gb":2.0},"model_id":"intfloat/multilingual-e5-large","parameter_count":"560M","parameters_raw":559890946,"pipeline_tag":"feature-extraction","provider":"intfloat","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose"},"supported_voices":null},"family":null,"id":"intfloat/multilingual-e5-large","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Intfloat: Multilingual-E5-Large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"krea/krea-2-large":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/krea/krea-2-large-20260720/endpoints"},"supported_voices":null},"family":null,"id":"krea/krea-2-large","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Krea: Krea 2 Large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"krea/krea-2-medium":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/krea/krea-2-medium-20260720/endpoints"},"supported_voices":null},"family":null,"id":"krea/krea-2-medium","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Krea: Krea 2 Medium","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"krea/krea-2-medium-turbo":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/krea/krea-2-medium-turbo-20260720/endpoints"},"supported_voices":null},"family":null,"id":"krea/krea-2-medium-turbo","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Krea: Krea 2 Medium Turbo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"kwaipilot/kat-coder-air-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","expiration_date":null,"family":"kat-coder","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/kwaipilot/kat-coder-air-v2.5-20260710/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"kwaipilot/kat-coder-air-v2.5","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":256000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kwaipilot: KAT-Coder-Air V2.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-10","retired":false,"tags":null},"kwaipilot/kat-coder-pro-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":15.5,"coding_index":59.5,"intelligence_index":33.7},"design_arena":[]},"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","expiration_date":null,"family":"kat-coder","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/kwaipilot/kat-coder-pro-v2-20260327/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro-v2","knowledge":null,"last_updated":"2026-03-27","lifecycle":null,"limits":{"context":262144,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kwaipilot: KAT-Coder-Pro V2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-27","retired":false,"tags":null},"kwaipilot/kat-coder-pro-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.15,"input":0.74,"output":2.96},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","expiration_date":null,"family":"kat-coder","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/kwaipilot/kat-coder-pro-v2.5-20260710/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro-v2.5","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":256000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kwaipilot: KAT-Coder-Pro V2.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-10","retired":false,"tags":null},"kwaivgi/kling-v3.0-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/kwaivgi/kling-v3.0-pro-20260429/endpoints"},"supported_voices":null},"family":null,"id":"kwaivgi/kling-v3.0-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Kling: Video v3.0 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"kwaivgi/kling-v3.0-std":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/kwaivgi/kling-v3.0-std-20260429/endpoints"},"supported_voices":null},"family":null,"id":"kwaivgi/kling-v3.0-std","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Kling: Video v3.0 Standard","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"kwaivgi/kling-video-o1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/kwaivgi/kling-video-o1-20260420/endpoints"},"supported_voices":null},"family":null,"id":"kwaivgi/kling-video-o1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Kling: Video O1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"mancer/weaver":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.5,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","expiration_date":null,"family":"alpha","hugging_face_id":null,"knowledge_cutoff":"2023-06-30","links":{"details":"/api/v1/models/mancer/weaver/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mancer/weaver","knowledge":"2023-06-30","last_updated":"2023-08-02","lifecycle":null,"limits":{"context":8000,"output":2000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mancer: Weaver (alpha)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-08-02","retired":false,"tags":null},"meituan/longcat-2.0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.006,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"longcat","hugging_face_id":"meituan-longcat/LongCat-2.0","knowledge_cutoff":null,"links":{"details":"/api/v1/models/meituan/longcat-2.0-20260720/endpoints"},"llmfit":{"architecture":"unknown","context_length":31457280,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"meituan-longcat/LongCat-2.0","memory":{"min_ram_gb":992.2,"min_vram_gb":909.5,"recommended_ram_gb":1653.6},"model_id":"meituan-longcat/LongCat-2.0","parameter_count":"1775.6B","parameters_raw":1775560491136,"pipeline_tag":"text-generation","provider":"meituan-longcat","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false,"supports_max_tokens":true},"reasoning_options":[{"type":"budget_tokens"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"meituan/longcat-2.0","knowledge":null,"last_updated":"2026-07-20","lifecycle":null,"limits":{"context":1048756,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meituan: LongCat 2.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"meta-llama/llama-3.1-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.4,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Meta-Llama-3.1-70B-Instruct","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/meta-llama/llama-3.1-70b-instruct/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-3.1-70b-instruct","knowledge":"2023-12-31","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.1 70B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/llama-3.1-8b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.025,"input":0.05,"output":0.08},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":0.5,"coding_index":5.4,"intelligence_index":7.6},"design_arena":[]},"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Meta-Llama-3.1-8B-Instruct","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-3.1-8b-instruct","knowledge":"2023-12-31","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.1 8B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta-llama/llama-3.2-1b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.027,"output":0.201},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Llama-3.2-1B-Instruct","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/meta-llama/llama-3.2-1b-instruct/endpoints"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.2-1B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.2-1B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.2-1B-Instruct-GGUF"}],"hf_downloads":10100649,"hf_likes":1550,"matched_hugging_face_id":"meta-llama/Llama-3.2-1B-Instruct","memory":{"min_ram_gb":1.0,"min_vram_gb":0.6,"recommended_ram_gb":2.0},"model_id":"meta-llama/Llama-3.2-1B-Instruct","parameter_count":"1.2B","parameters_raw":1235814400,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-09-18","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-3.2-1b-instruct","knowledge":"2023-12-31","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":60000,"output":60000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.2 1B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"meta-llama/llama-3.2-3b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.05,"output":0.33},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Llama-3.2-3B-Instruct","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/meta-llama/llama-3.2-3b-instruct/endpoints"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.2-3B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.2-3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.2-3B-Instruct-GGUF"}],"hf_downloads":1461226,"hf_likes":2387,"matched_hugging_face_id":"meta-llama/Llama-3.2-3B-Instruct","memory":{"min_ram_gb":1.8,"min_vram_gb":1.6,"recommended_ram_gb":3.0},"model_id":"meta-llama/Llama-3.2-3B-Instruct","parameter_count":"3.2B","parameters_raw":3212749824,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-09-18","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-3.2-3b-instruct","knowledge":"2023-12-31","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.2 3B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"meta-llama/llama-3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.32},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":0.3,"coding_index":11.9,"intelligence_index":9.4},"design_arena":[]},"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/meta-llama/llama-3.3-70b-instruct/endpoints"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-3.3-70B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Llama-3.3-70B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-3.3-70B-Instruct-GGUF"}],"hf_downloads":478538,"hf_likes":2936,"matched_hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"meta-llama/Llama-3.3-70B-Instruct","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"Meta","quantization":"Q4_K_M","release_date":"2024-11-26","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta: Llama 3.3 70B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/llama-4-maverick":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.2,"output":0.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1.3,"coding_index":16.3,"intelligence_index":14.3},"design_arena":[{"arena":"models","category":"3d","elo":955,"rank":100,"win_rate":40.2},{"arena":"models","category":"codecategories","elo":908,"rank":112,"win_rate":35.8},{"arena":"models","category":"dataviz","elo":909,"rank":109,"win_rate":38.4},{"arena":"models","category":"gamedev","elo":890,"rank":109,"win_rate":33.7},{"arena":"models","category":"uicomponent","elo":935,"rank":103,"win_rate":40.8},{"arena":"models","category":"website","elo":894,"rank":115,"win_rate":34.4}]},"description":"Open multimodal Llama model for strong reasoning and fast responses","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/meta-llama/llama-4-maverick-17b-128e-instruct/endpoints"},"llmfit":{"architecture":"llama4","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Llama-4-Maverick-17B-128E-Instruct-GGUF"}],"hf_downloads":43543,"hf_likes":505,"matched_hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","memory":{"min_ram_gb":224.4,"min_vram_gb":205.7,"recommended_ram_gb":374.0},"model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","moe":{"active_experts":1,"active_parameters":17000000000,"is_moe":true,"num_experts":16},"parameter_count":"401.6B","parameters_raw":401583781376,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","release_date":"2025-04-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-4-maverick","knowledge":"2024-08-31","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Meta: Llama 4 Maverick","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/llama-4-scout":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1.1,"coding_index":8.2,"intelligence_index":10},"design_arena":[{"arena":"models","category":"codecategories","elo":818,"rank":115,"win_rate":26.6},{"arena":"models","category":"dataviz","elo":922,"rank":107,"win_rate":39.3},{"arena":"models","category":"gamedev","elo":825,"rank":111,"win_rate":27.4},{"arena":"models","category":"uicomponent","elo":804,"rank":108,"win_rate":25.5},{"arena":"models","category":"website","elo":773,"rank":121,"win_rate":22.7}]},"description":"Open multimodal Llama model for long-context analysis and efficient agents","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/meta-llama/llama-4-scout-17b-16e-instruct/endpoints"},"llmfit":{"architecture":"llama4","context_length":4096,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF"}],"hf_downloads":483763,"hf_likes":1331,"matched_hugging_face_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","memory":{"min_ram_gb":60.7,"min_vram_gb":55.6,"recommended_ram_gb":101.2},"model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","moe":{"active_experts":1,"active_parameters":17000000000,"is_moe":true,"num_experts":16},"parameter_count":"108.6B","parameters_raw":108641793536,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","release_date":"2025-04-02","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-4-scout","knowledge":"2024-08-31","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1310720,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Meta: Llama 4 Scout","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta-llama/llama-guard-4-12b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.18,"output":0.18},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","expiration_date":null,"family":"llama","hugging_face_id":"meta-llama/Llama-Guard-4-12B","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/meta-llama/llama-guard-4-12b/endpoints"},"llmfit":{"architecture":"llama4","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":225346,"hf_likes":0,"matched_hugging_face_id":"meta-llama/Llama-Guard-4-12B","memory":{"min_ram_gb":6.7,"min_vram_gb":6.1,"recommended_ram_gb":11.2},"model_id":"meta-llama/Llama-Guard-4-12B","moe":{"active_experts":1,"active_parameters":1312620007,"is_moe":true,"num_experts":16},"parameter_count":"12.0B","parameters_raw":12001097216,"pipeline_tag":"image-text-to-text","provider":"Meta","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"meta-llama/llama-guard-4-12b","knowledge":"2024-08-31","last_updated":"2025-04-30","lifecycle":null,"limits":{"context":1048576,"output":16384},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Meta: Llama Guard 4 12B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-30","retired":false,"tags":null},"meta/muse-spark-1.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":37.5,"coding_index":71.3,"intelligence_index":50.6},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1192,"rank":8,"win_rate":48.2},{"arena":"agents","category":"godotgamedev","elo":1141,"rank":20,"win_rate":39.4},{"arena":"agents","category":"htmlslides","elo":1217,"rank":8,"win_rate":51.6},{"arena":"agents","category":"python-pptxslides","elo":1173,"rank":12,"win_rate":44.1},{"arena":"agents","category":"webapps","elo":1254,"rank":11,"win_rate":51.1},{"arena":"models","category":"3d","elo":1304,"rank":17,"win_rate":52.8},{"arena":"models","category":"asciiart","elo":1320,"rank":3,"win_rate":60.5},{"arena":"models","category":"codecategories","elo":1308,"rank":9,"win_rate":54.9},{"arena":"models","category":"dataviz","elo":1318,"rank":7,"win_rate":55.1},{"arena":"models","category":"gamedev","elo":1343,"rank":5,"win_rate":56.6},{"arena":"models","category":"svg","elo":1263,"rank":10,"win_rate":49.9},{"arena":"models","category":"uicomponent","elo":1334,"rank":7,"win_rate":55.3},{"arena":"models","category":"website","elo":1295,"rank":16,"win_rate":54}]},"description":"Open Llama multimodal model for image understanding and text reasoning","expiration_date":null,"family":"muse","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.1-20260709/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"meta/muse-spark-1.1","knowledge":null,"last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image","video","pdf","audio","file"],"output":["text"]},"model":null,"name":"Meta: Muse Spark 1.1","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.0025,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"microsoft/mai-image-2.5":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":5.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1237,"rank":4,"win_rate":52},{"arena":"models","category":"image","elo":1238,"rank":4,"win_rate":53.4},{"arena":"models","category":"imageediting","elo":1256,"rank":3,"win_rate":61},{"arena":"models","category":"logo","elo":1256,"rank":4,"win_rate":52.4}]},"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/microsoft/mai-image-2.5/endpoints"},"supported_voices":null},"family":null,"id":"microsoft/mai-image-2.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096,"output":1024},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Microsoft: MAI-Image-2.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"microsoft/mai-image-2.5-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":5.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/microsoft/mai-image-2.5-pro-20260723/endpoints"},"supported_voices":null},"family":null,"id":"microsoft/mai-image-2.5-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096,"output":1024},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Microsoft: MAI-Image-2.5 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"microsoft/mai-transcribe-1.5":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":3.6e5,"output":0.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/microsoft/mai-transcribe-1.5/endpoints"},"supported_voices":null},"family":null,"id":"microsoft/mai-transcribe-1.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"Microsoft: MAI-Transcribe 1.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"microsoft/mai-voice-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":22.0,"output":0.0},"deprecated":false,"extra":{"benchmarks":{"design_arena":[{"arena":"models","category":"audiorealism","elo":1227,"rank":1,"win_rate":69.3},{"arena":"models","category":"text-to-speech","elo":1197,"rank":1,"win_rate":53}]},"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/microsoft/mai-voice-2/endpoints"},"supported_voices":["en-US-Harper:MAI-Voice-2","es-MX-Valeria:MAI-Voice-2","fr-FR-Soleil:MAI-Voice-2","de-DE-Klaus:MAI-Voice-2"]},"family":null,"id":"microsoft/mai-voice-2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Microsoft: MAI-Voice-2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"microsoft/mai-voice-2-flash":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":15.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/microsoft/mai-voice-2-flash-20260723/endpoints"},"supported_voices":["en-US-Harper:MAI-Voice-2","es-MX-Valeria:MAI-Voice-2","fr-FR-Soleil:MAI-Voice-2","de-DE-Klaus:MAI-Voice-2"]},"family":null,"id":"microsoft/mai-voice-2-flash","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Microsoft: MAI-Voice-2-Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"microsoft/phi-4":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.07,"output":0.14},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"family":"phi","hugging_face_id":"microsoft/phi-4","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/microsoft/phi-4/endpoints"},"llmfit":{"architecture":"phi3","context_length":16384,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/phi-4-GGUF"},{"provider":"bartowski","repo":"bartowski/phi-4-GGUF"},{"provider":"mradermacher","repo":"mradermacher/phi-4-GGUF"}],"hf_downloads":664421,"hf_likes":2285,"matched_hugging_face_id":"microsoft/phi-4","memory":{"min_ram_gb":8.2,"min_vram_gb":7.5,"recommended_ram_gb":13.7},"model_id":"microsoft/phi-4","parameter_count":"14.7B","parameters_raw":14659507200,"pipeline_tag":"text-generation","provider":"Microsoft","quantization":"Q4_K_M","release_date":"2024-12-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"microsoft/phi-4","knowledge":"2024-06-30","last_updated":"2025-01-10","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Microsoft: Phi 4","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-01-10","retired":false,"tags":null},"microsoft/wizardlm-2-8x22b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.62,"output":0.62},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"microsoft/WizardLM-2-8x22B","knowledge_cutoff":"2024-04-30","links":{"details":"/api/v1/models/microsoft/wizardlm-2-8x22b/endpoints"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"microsoft/wizardlm-2-8x22b","knowledge":"2024-04-30","last_updated":"2024-04-16","lifecycle":null,"limits":{"context":65535,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"WizardLM-2 8x22B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-04-16","retired":false,"tags":null},"minimax/hailuo-2.3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/hailuo-2.3-20260420/endpoints"},"supported_voices":null},"family":null,"id":"minimax/hailuo-2.3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"MiniMax: Hailuo 2.3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"minimax/hailuo-3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/hailuo-03-20260730/endpoints"},"supported_voices":null},"family":null,"id":"minimax/hailuo-3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image","audio","video"],"output":["video"]},"model":null,"name":"MiniMax: H3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"minimax/minimax-01":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.2,"output":1.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","expiration_date":null,"family":"minimax","hugging_face_id":"MiniMaxAI/MiniMax-Text-01","knowledge_cutoff":"2024-03-31","links":{"details":"/api/v1/models/minimax/minimax-01/endpoints"},"llmfit":{"architecture":"minimax_text_01","context_length":10240000,"discovered":true,"gguf_sources":[],"hf_downloads":13887,"hf_likes":0,"matched_hugging_face_id":"MiniMaxAI/MiniMax-Text-01","memory":{"min_ram_gb":254.9,"min_vram_gb":233.6,"recommended_ram_gb":424.8},"model_id":"MiniMaxAI/MiniMax-Text-01","moe":{"active_experts":2,"active_parameters":49884806046,"is_moe":true,"num_experts":32},"parameter_count":"456.1B","parameters_raw":456089655296,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-01","knowledge":"2024-03-31","last_updated":"2025-01-15","lifecycle":null,"limits":{"context":1000192,"output":1000192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax-01","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"minimax/minimax-m1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.55,"output":2.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","expiration_date":null,"family":"minimax","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/minimax/minimax-m1/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-m1","knowledge":"2024-06-30","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1000000,"output":40000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"minimax/minimax-m2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.255,"output":1.02},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1153,"rank":63,"win_rate":48.3},{"arena":"models","category":"codecategories","elo":1164,"rank":68,"win_rate":48.1},{"arena":"models","category":"dataviz","elo":1167,"rank":63,"win_rate":50},{"arena":"models","category":"gamedev","elo":1170,"rank":61,"win_rate":48.1},{"arena":"models","category":"svg","elo":1147,"rank":45,"win_rate":55.3},{"arena":"models","category":"uicomponent","elo":1172,"rank":61,"win_rate":49.2},{"arena":"models","category":"website","elo":1166,"rank":68,"win_rate":48}]},"description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","expiration_date":null,"family":"minimax","hugging_face_id":"MiniMaxAI/MiniMax-M2","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/minimax-m2/endpoints"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2-GGUF"}],"hf_downloads":108116,"hf_likes":1500,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2","moe":{"active_experts":8,"active_parameters":18223715635,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228689764864,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2025-10-22","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-m2","knowledge":null,"last_updated":"2025-10-27","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-23","retired":false,"tags":null},"minimax/minimax-m2-her":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","expiration_date":null,"family":"minimax","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/minimax-m2-her-20260123/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-m2-her","knowledge":null,"last_updated":"2026-01-23","lifecycle":null,"limits":{"context":65536,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M2-her","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-23","retired":false,"tags":null},"minimax/minimax-m2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1220,"rank":40,"win_rate":57.5},{"arena":"models","category":"codecategories","elo":1219,"rank":39,"win_rate":55.3},{"arena":"models","category":"dataviz","elo":1233,"rank":36,"win_rate":57},{"arena":"models","category":"gamedev","elo":1187,"rank":56,"win_rate":50.4},{"arena":"models","category":"svg","elo":1179,"rank":39,"win_rate":55.4},{"arena":"models","category":"uicomponent","elo":1258,"rank":32,"win_rate":60.9},{"arena":"models","category":"website","elo":1225,"rank":40,"win_rate":55.4}]},"description":"Earlier MiniMax agent model for practical coding and productivity tasks","expiration_date":null,"family":"minimax","hugging_face_id":"MiniMaxAI/MiniMax-M2.1","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.1/endpoints"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.1-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.1-GGUF"}],"hf_downloads":12798,"hf_likes":0,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.1","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.1","moe":{"active_experts":8,"active_parameters":18223715635,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228689764864,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-m2.1","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M2.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"minimax/minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"input":0.15,"output":0.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1225,"rank":39,"win_rate":57.6},{"arena":"models","category":"codecategories","elo":1236,"rank":36,"win_rate":56.8},{"arena":"models","category":"dataviz","elo":1199,"rank":48,"win_rate":51.2},{"arena":"models","category":"gamedev","elo":1229,"rank":38,"win_rate":55.5},{"arena":"models","category":"svg","elo":1198,"rank":30,"win_rate":54.5},{"arena":"models","category":"uicomponent","elo":1208,"rank":44,"win_rate":53.4},{"arena":"models","category":"website","elo":1245,"rank":35,"win_rate":57.5}]},"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","expiration_date":null,"family":"minimax","hugging_face_id":"MiniMaxAI/MiniMax-M2.5","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.5-20260211/endpoints"},"llmfit":{"architecture":"minimax_m2","context_length":196608,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.5-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.5-GGUF"}],"hf_downloads":772099,"hf_likes":1502,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.5","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.5","moe":{"active_experts":8,"active_parameters":18224821702,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-02-12","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":196608},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M2.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/minimax-m2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.054,"input":0.27,"output":1.08},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":25.6,"coding_index":52.6,"intelligence_index":38.1},"design_arena":[{"arena":"models","category":"3d","elo":1247,"rank":32,"win_rate":50.6},{"arena":"models","category":"asciiart","elo":1176,"rank":37,"win_rate":47.8},{"arena":"models","category":"codecategories","elo":1263,"rank":30,"win_rate":52.8},{"arena":"models","category":"dataviz","elo":1259,"rank":28,"win_rate":53.1},{"arena":"models","category":"gamedev","elo":1258,"rank":29,"win_rate":52.8},{"arena":"models","category":"svg","elo":1185,"rank":37,"win_rate":50.1},{"arena":"models","category":"uicomponent","elo":1247,"rank":34,"win_rate":50},{"arena":"models","category":"website","elo":1269,"rank":28,"win_rate":53.6}]},"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","expiration_date":null,"family":"minimax","hugging_face_id":"MiniMaxAI/MiniMax-M2.7","knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/minimax-m2.7-20260318/endpoints"},"llmfit":{"architecture":"minimax_m2","context_length":204800,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/MiniMax-M2.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/MiniMax-M2.7-GGUF"}],"hf_downloads":917214,"hf_likes":1236,"matched_hugging_face_id":"MiniMaxAI/MiniMax-M2.7","memory":{"min_ram_gb":127.8,"min_vram_gb":117.1,"recommended_ram_gb":213.0},"model_id":"MiniMaxAI/MiniMax-M2.7","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"228.7B","parameters_raw":228703644928,"pipeline_tag":"text-generation","provider":"minimaxai","quantization":"Q4_K_M","release_date":"2026-04-09","source":"llmfit","use_case":"Lightweight, edge deployment"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-m2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M2.7","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/minimax-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":35.4,"coding_index":58.6,"intelligence_index":44.4},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1196,"rank":7,"win_rate":52.3},{"arena":"agents","category":"androidnative","elo":1203,"rank":13,"win_rate":51.5},{"arena":"agents","category":"fullstack","elo":1223,"rank":11,"win_rate":52.7},{"arena":"agents","category":"htmlslides","elo":1207,"rank":9,"win_rate":51.8},{"arena":"agents","category":"mobileapps","elo":1245,"rank":7,"win_rate":56.5},{"arena":"agents","category":"webapps","elo":1251,"rank":13,"win_rate":52.9},{"arena":"models","category":"3d","elo":1277,"rank":24,"win_rate":54.1},{"arena":"models","category":"asciiart","elo":1194,"rank":23,"win_rate":47.1},{"arena":"models","category":"codecategories","elo":1284,"rank":22,"win_rate":54.3},{"arena":"models","category":"dataviz","elo":1264,"rank":22,"win_rate":53.4},{"arena":"models","category":"gamedev","elo":1271,"rank":25,"win_rate":50.4},{"arena":"models","category":"svg","elo":1219,"rank":23,"win_rate":50},{"arena":"models","category":"uicomponent","elo":1283,"rank":22,"win_rate":53.8},{"arena":"models","category":"website","elo":1285,"rank":20,"win_rate":54.6}]},"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","expiration_date":null,"family":"minimax","hugging_face_id":"MiniMaxAI/Minimax-M3","knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/minimax-m3-20260531/endpoints"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"minimax/minimax-m3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1048576,"output":512000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax: MiniMax M3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-31","retired":false,"tags":null},"minimax/speech-2.8-hd":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":100.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/speech-2.8-hd-20260716/endpoints"},"supported_voices":null},"family":null,"id":"minimax/speech-2.8-hd","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"MiniMax: Speech 2.8 HD","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"minimax/speech-2.8-turbo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":60.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/minimax/speech-2.8-turbo-20260716/endpoints"},"supported_voices":null},"family":null,"id":"minimax/speech-2.8-turbo","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"MiniMax: Speech 2.8 Turbo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"mistralai/codestral-2508":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.3,"output":0.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1036,"rank":99,"win_rate":38.6},{"arena":"models","category":"dataviz","elo":1047,"rank":92,"win_rate":42},{"arena":"models","category":"gamedev","elo":1020,"rank":98,"win_rate":36.3},{"arena":"models","category":"uicomponent","elo":1052,"rank":86,"win_rate":46.7},{"arena":"models","category":"website","elo":1036,"rank":102,"win_rate":37.8},{"arena":"models","category":"3d","elo":1076,"rank":86,"win_rate":45.5}]},"description":"Mistral coding model for code completion, generation, and developer workflows","expiration_date":null,"family":"codestral","hugging_face_id":"","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/mistralai/codestral-2508/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/codestral-2508","knowledge":"2025-03-31","last_updated":"2025-08-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Codestral 2508","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-01","retired":false,"tags":null},"mistralai/codestral-embed-2505":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.15,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/codestral-embed-2505/endpoints"},"supported_voices":null},"family":null,"id":"mistralai/codestral-embed-2505","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Mistral: Codestral Embed 2505","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"mistralai/ministral-14b-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.02,"input":0.2,"output":0.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":2.2,"coding_index":14.4,"intelligence_index":11.1},"design_arena":[{"arena":"models","category":"3d","elo":1045,"rank":91,"win_rate":39.6},{"arena":"models","category":"codecategories","elo":1094,"rank":88,"win_rate":44},{"arena":"models","category":"gamedev","elo":1091,"rank":84,"win_rate":43.6},{"arena":"models","category":"website","elo":1104,"rank":88,"win_rate":44.8}]},"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","expiration_date":null,"family":"ministral","hugging_face_id":"mistralai/Ministral-3-14B-Instruct-2512","knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/ministral-14b-2512/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/ministral-14b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Ministral 3 14B 2512","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/ministral-3b-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.01,"input":0.1,"output":0.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1.6,"coding_index":4.8,"intelligence_index":6.8},"design_arena":[{"arena":"models","category":"3d","elo":1018,"rank":97,"win_rate":35.9},{"arena":"models","category":"codecategories","elo":1039,"rank":98,"win_rate":37.3},{"arena":"models","category":"gamedev","elo":1001,"rank":102,"win_rate":33},{"arena":"models","category":"website","elo":1051,"rank":100,"win_rate":38.2}]},"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","expiration_date":null,"family":"ministral","hugging_face_id":"mistralai/Ministral-3-3B-Instruct-2512","knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/ministral-3b-2512/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/ministral-3b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Ministral 3 3B 2512","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/ministral-8b-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.015,"input":0.15,"output":0.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1.2,"coding_index":9.7,"intelligence_index":9},"design_arena":[{"arena":"models","category":"3d","elo":1087,"rank":84,"win_rate":46.2},{"arena":"models","category":"codecategories","elo":1082,"rank":89,"win_rate":42.9},{"arena":"models","category":"gamedev","elo":1043,"rank":93,"win_rate":38.7},{"arena":"models","category":"website","elo":1088,"rank":91,"win_rate":42.9}]},"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","expiration_date":null,"family":"ministral","hugging_face_id":"mistralai/Ministral-3-8B-Instruct-2512","knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/ministral-8b-2512/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/ministral-8b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Ministral 3 8B 2512","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistralai/mistral-embed-2312":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.1,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/mistral-embed-2312/endpoints"},"supported_voices":null},"family":null,"id":"mistralai/mistral-embed-2312","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Mistral: Mistral Embed 2312","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-31","retired":false,"tags":null},"mistralai/mistral-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":2.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","expiration_date":null,"family":"mistral-large","hugging_face_id":null,"knowledge_cutoff":"2024-11-30","links":{"details":"/api/v1/models/mistralai/mistral-large/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-large","knowledge":"2024-11-30","last_updated":"2024-02-26","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","pdf","file"],"output":["text"]},"model":null,"name":"Mistral Large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-02-26","retired":false,"tags":null},"mistralai/mistral-large-2407":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":2.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","expiration_date":null,"family":"mistral-large","hugging_face_id":"","knowledge_cutoff":"2024-03-31","links":{"details":"/api/v1/models/mistralai/mistral-large-2407/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-large-2407","knowledge":"2024-03-31","last_updated":"2024-11-19","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","pdf","file"],"output":["text"]},"model":null,"name":"Mistral Large 2407","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-11-19","retired":false,"tags":null},"mistralai/mistral-large-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"input":0.5,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":5.5,"coding_index":20.1,"intelligence_index":15.9},"design_arena":[{"arena":"models","category":"3d","elo":1155,"rank":62,"win_rate":46.9},{"arena":"models","category":"asciiart","elo":1106,"rank":52,"win_rate":40.3},{"arena":"models","category":"codecategories","elo":1171,"rank":64,"win_rate":47.6},{"arena":"models","category":"dataviz","elo":1163,"rank":64,"win_rate":45.7},{"arena":"models","category":"gamedev","elo":1133,"rank":73,"win_rate":41.5},{"arena":"models","category":"svg","elo":1040,"rank":69,"win_rate":38},{"arena":"models","category":"uicomponent","elo":1137,"rank":67,"win_rate":43},{"arena":"models","category":"website","elo":1185,"rank":62,"win_rate":49.5}]},"description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","expiration_date":null,"family":"mistral-large","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/mistral-large-2512/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-large-2512","knowledge":"2024-11","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Mistral Large 3 2512","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"mistralai/mistral-medium-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.04,"input":0.4,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1139,"rank":67,"win_rate":54.7},{"arena":"models","category":"codecategories","elo":1098,"rank":87,"win_rate":48.1},{"arena":"models","category":"dataviz","elo":1059,"rank":91,"win_rate":45.7},{"arena":"models","category":"gamedev","elo":1071,"rank":87,"win_rate":45.3},{"arena":"models","category":"uicomponent","elo":1061,"rank":84,"win_rate":49.9},{"arena":"models","category":"website","elo":1102,"rank":89,"win_rate":47.7}]},"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","expiration_date":null,"family":"mistral-medium","hugging_face_id":"","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/mistralai/mistral-medium-3/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-medium-3","knowledge":"2025-03-31","last_updated":"2025-05-07","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Mistral Medium 3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"mistralai/mistral-medium-3-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":1.5,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":19,"coding_index":46.9,"intelligence_index":29.9},"design_arena":[]},"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","expiration_date":null,"family":"mistral-medium","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3.5-20260430/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","mandatory":false,"supported_efforts":["high","none"]},"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-medium-3-5","knowledge":null,"last_updated":"2026-04-30","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Mistral Medium 3.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"mistralai/mistral-medium-3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.04,"input":0.4,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":6.2,"coding_index":20.5,"intelligence_index":14.7},"design_arena":[{"arena":"models","category":"3d","elo":1137,"rank":69,"win_rate":44.7},{"arena":"models","category":"asciiart","elo":1035,"rank":56,"win_rate":30.8},{"arena":"models","category":"codecategories","elo":1149,"rank":72,"win_rate":45.1},{"arena":"models","category":"dataviz","elo":1173,"rank":61,"win_rate":47.3},{"arena":"models","category":"gamedev","elo":1126,"rank":77,"win_rate":40.7},{"arena":"models","category":"svg","elo":1040,"rank":70,"win_rate":38.2},{"arena":"models","category":"uicomponent","elo":1133,"rank":69,"win_rate":43.4},{"arena":"models","category":"website","elo":1156,"rank":72,"win_rate":46}]},"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","expiration_date":null,"family":"mistral-medium","hugging_face_id":"","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/mistralai/mistral-medium-3.1/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-medium-3.1","knowledge":"2025-06-30","last_updated":"2025-08-13","lifecycle":null,"limits":{"context":131072,"output":262144},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Mistral Medium 3.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-13","retired":false,"tags":null},"mistralai/mistral-nemo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.019,"output":0.03},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","expiration_date":null,"family":"mistral-nemo","hugging_face_id":"mistralai/Mistral-Nemo-Instruct-2407","knowledge_cutoff":"2024-04-30","links":{"details":"/api/v1/models/mistralai/mistral-nemo/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-nemo","knowledge":"2024-07","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral: Mistral Nemo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-07-19","retired":false,"tags":null},"mistralai/mistral-saba":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.02,"input":0.2,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","expiration_date":null,"family":"mistral","hugging_face_id":"","knowledge_cutoff":"2024-09-30","links":{"details":"/api/v1/models/mistralai/mistral-saba-2502/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-saba","knowledge":"2024-09-30","last_updated":"2025-02-17","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Saba","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-02-17","retired":false,"tags":null},"mistralai/mistral-small-24b-instruct-2501":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.05,"output":0.08},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","expiration_date":null,"family":"mistral-small","hugging_face_id":"mistralai/Mistral-Small-24B-Instruct-2501","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/mistralai/mistral-small-24b-instruct-2501/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-small-24b-instruct-2501","knowledge":"2023-10-31","last_updated":"2025-01-30","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral: Mistral Small 3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-01-30","retired":false,"tags":null},"mistralai/mistral-small-2603":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":4.7,"coding_index":26.6,"intelligence_index":19.6},"design_arena":[]},"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","expiration_date":null,"family":"mistral-small","hugging_face_id":"mistralai/Mistral-Small-4-119B-2603","knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-2603/endpoints"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":false,"mandatory":false,"supported_efforts":["high","none"]},"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-small-2603","knowledge":"2025-06","last_updated":"2026-03-16","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Mistral Small 4","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"mistralai/mistral-small-3.1-24b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.351,"output":0.555},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","expiration_date":null,"family":"mistral-small","hugging_face_id":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/mistralai/mistral-small-3.1-24b-instruct-2503/endpoints"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-small-3.1-24b-instruct","knowledge":"2023-10-31","last_updated":"2025-03-17","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral: Mistral Small 3.1 24B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-17","retired":false,"tags":null},"mistralai/mistral-small-3.2-24b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.09375,"output":0.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":936,"rank":110,"win_rate":39.8},{"arena":"models","category":"dataviz","elo":955,"rank":102,"win_rate":43.3},{"arena":"models","category":"gamedev","elo":941,"rank":107,"win_rate":39.4},{"arena":"models","category":"uicomponent","elo":943,"rank":102,"win_rate":40.5},{"arena":"models","category":"website","elo":919,"rank":113,"win_rate":38.3}]},"description":"Efficient Mistral model for fast chat, extraction, and production assistants","expiration_date":null,"family":"mistral-small","hugging_face_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/mistralai/mistral-small-3.2-24b-instruct-2506/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mistral-small-3.2-24b-instruct","knowledge":"2023-10-31","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Mistral: Mistral Small 3.2 24B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"mistralai/mixtral-8x22b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":2.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","expiration_date":null,"family":"mistral","hugging_face_id":"mistralai/Mixtral-8x22B-Instruct-v0.1","knowledge_cutoff":"2024-01-31","links":{"details":"/api/v1/models/mistralai/mixtral-8x22b-instruct/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/mixtral-8x22b-instruct","knowledge":"2024-01-31","last_updated":"2024-04-17","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Mixtral 8x22B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-04-17","retired":false,"tags":null},"mistralai/voxtral-mini-transcribe":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":3.0e3,"output":0.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/voxtral-mini-transcribe-2602/endpoints"},"supported_voices":null},"family":null,"id":"mistralai/voxtral-mini-transcribe","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"Mistral: Voxtral Mini Transcribe","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-15","retired":false,"tags":null},"mistralai/voxtral-mini-tts-2603":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":16.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/voxtral-mini-tts-2603/endpoints"},"supported_voices":["en_paul_sad","en_paul_neutral","en_paul_happy","en_paul_frustrated","en_paul_excited","en_paul_confident","en_paul_cheerful","en_paul_angry","gb_oliver_neutral","gb_oliver_sad","gb_oliver_excited","gb_oliver_curious","gb_oliver_confident","gb_oliver_cheerful","gb_oliver_angry","gb_jane_sarcasm","gb_jane_confused","gb_jane_shameful","gb_jane_sad","gb_jane_neutral","gb_jane_jealousy","gb_jane_frustrated","gb_jane_curious","gb_jane_confident","fr_marie_sad","fr_marie_neutral","fr_marie_happy","fr_marie_excited","fr_marie_curious","fr_marie_angry"]},"family":null,"id":"mistralai/voxtral-mini-tts-2603","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Mistral: Voxtral Mini TTS","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-19","retired":false,"tags":null},"mistralai/voxtral-small-24b-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":100.0,"cache_read":0.01,"input":0.1,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","expiration_date":null,"family":"mistral","hugging_face_id":"mistralai/Voxtral-Small-24B-2507","knowledge_cutoff":null,"links":{"details":"/api/v1/models/mistralai/voxtral-small-24b-2507/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"mistralai/voxtral-small-24b-2507","knowledge":null,"last_updated":"2025-10-30","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text","audio","pdf","file"],"output":["text"]},"model":null,"name":"Mistral: Voxtral Small 24B 2507","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"moonshotai/kimi-k2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.57,"output":2.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1062,"rank":93,"win_rate":51.7},{"arena":"models","category":"dataviz","elo":1046,"rank":93,"win_rate":49.4},{"arena":"models","category":"gamedev","elo":1026,"rank":96,"win_rate":46.4},{"arena":"models","category":"uicomponent","elo":1066,"rank":83,"win_rate":55.1},{"arena":"models","category":"website","elo":1074,"rank":94,"win_rate":53.1}]},"description":"Kimi model for long-context chat, coding, and agentic reasoning","expiration_date":null,"family":"kimi-k2","hugging_face_id":"moonshotai/Kimi-K2-Instruct","knowledge_cutoff":"2024-12-31","links":{"details":"/api/v1/models/moonshotai/kimi-k2/endpoints"},"llmfit":{"architecture":"kimi_k2","context_length":4194304,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2-Instruct-GGUF"}],"hf_downloads":177689,"hf_likes":2371,"matched_hugging_face_id":"moonshotai/Kimi-K2-Instruct","memory":{"min_ram_gb":573.6,"min_vram_gb":525.8,"recommended_ram_gb":956.0},"model_id":"moonshotai/Kimi-K2-Instruct","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1026.5B","parameters_raw":1026470731056,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-07-11","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"moonshotai/kimi-k2","knowledge":"2024-12-31","last_updated":"2025-07-11","lifecycle":null,"limits":{"context":131072,"output":100352},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2 0711","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-11","retired":false,"tags":null},"moonshotai/kimi-k2-0905":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.6,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1127,"rank":81,"win_rate":48.5},{"arena":"models","category":"website","elo":1130,"rank":83,"win_rate":48.3}]},"description":"Kimi model for long-context chat, coding, and agentic reasoning","expiration_date":null,"family":"kimi-k2","hugging_face_id":"moonshotai/Kimi-K2-Instruct-0905","knowledge_cutoff":"2024-12-31","links":{"details":"/api/v1/models/moonshotai/kimi-k2-0905/endpoints"},"llmfit":{"architecture":"kimi_k2","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":66851,"hf_likes":787,"matched_hugging_face_id":"moonshotai/Kimi-K2-Instruct-0905","memory":{"min_ram_gb":573.6,"min_vram_gb":525.8,"recommended_ram_gb":956.0},"model_id":"moonshotai/Kimi-K2-Instruct-0905","moe":{"active_experts":8,"active_parameters":71639103404,"is_moe":true,"num_experts":384},"parameter_count":"1026.5B","parameters_raw":1026470735448,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-09-03","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-0905","knowledge":"2024-12-31","last_updated":"2025-09-04","lifecycle":null,"limits":{"context":262144,"output":100352},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2 0905","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"moonshotai/kimi-k2-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.15,"input":0.6,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":1.8,"coding_index":21,"intelligence_index":17.3},"design_arena":[{"arena":"models","category":"website","elo":1136,"rank":80,"win_rate":48.8}]},"description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","expiration_date":null,"family":"kimi-thinking","hugging_face_id":"moonshotai/Kimi-K2-Thinking","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2-thinking-20251106/endpoints"},"llmfit":{"architecture":"kimi_k2","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":62805,"hf_likes":1714,"matched_hugging_face_id":"moonshotai/Kimi-K2-Thinking","memory":{"min_ram_gb":591.3,"min_vram_gb":542.0,"recommended_ram_gb":985.4},"model_id":"moonshotai/Kimi-K2-Thinking","moe":{"active_experts":8,"active_parameters":73847838596,"is_moe":true,"num_experts":384},"parameter_count":"1058.1B","parameters_raw":1058118284416,"pipeline_tag":"text-generation","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2025-11-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-thinking","knowledge":"2024-08","last_updated":"2025-11-06","lifecycle":null,"limits":{"context":262144,"output":100352},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2 Thinking","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"moonshotai/kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.095,"input":0.57,"output":2.85},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":21.7,"coding_index":46.8,"intelligence_index":35.4},"design_arena":[{"arena":"agents","category":"androidnative","elo":1155,"rank":20,"win_rate":58},{"arena":"agents","category":"fullstack","elo":1157,"rank":18,"win_rate":54.2},{"arena":"agents","category":"godotgamedev","elo":1219,"rank":9,"win_rate":59.8},{"arena":"agents","category":"mobileapps","elo":1206,"rank":15,"win_rate":54.2},{"arena":"agents","category":"webapps","elo":1183,"rank":20,"win_rate":51.3},{"arena":"models","category":"3d","elo":1261,"rank":29,"win_rate":53.1},{"arena":"models","category":"asciiart","elo":1205,"rank":19,"win_rate":46.5},{"arena":"models","category":"codecategories","elo":1266,"rank":29,"win_rate":54.1},{"arena":"models","category":"dataviz","elo":1247,"rank":33,"win_rate":51.3},{"arena":"models","category":"gamedev","elo":1259,"rank":28,"win_rate":53.4},{"arena":"models","category":"svg","elo":1195,"rank":33,"win_rate":48.4},{"arena":"models","category":"uicomponent","elo":1272,"rank":27,"win_rate":53.6},{"arena":"models","category":"website","elo":1273,"rank":24,"win_rate":55.3}]},"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","expiration_date":null,"family":"kimi-k2","hugging_face_id":"moonshotai/Kimi-K2.5","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2.5-0127/endpoints"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Kimi-K2.5-GGUF"}],"hf_downloads":967470,"hf_likes":2860,"matched_hugging_face_id":"moonshotai/Kimi-K2.5","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.5","moe":{"active_experts":8,"active_parameters":32000000000,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","release_date":"2026-01-01","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"moonshotai/kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0992,"input":0.589,"output":2.48},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":30.3,"coding_index":61.8,"intelligence_index":44.2},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1150,"rank":15,"win_rate":47.9},{"arena":"agents","category":"agentichtmlslides","elo":1248,"rank":2,"win_rate":59},{"arena":"agents","category":"agenticslides","elo":1187,"rank":5,"win_rate":45.8},{"arena":"agents","category":"agenticslides(html)","elo":1252,"rank":2,"win_rate":59.2},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1186,"rank":5,"win_rate":45.5},{"arena":"agents","category":"androidnative","elo":1198,"rank":15,"win_rate":51.9},{"arena":"agents","category":"fullstack","elo":1199,"rank":15,"win_rate":55},{"arena":"agents","category":"godotgamedev","elo":1161,"rank":15,"win_rate":47.1},{"arena":"agents","category":"htmlslides","elo":1226,"rank":6,"win_rate":54.6},{"arena":"agents","category":"mobileapps","elo":1223,"rank":9,"win_rate":55},{"arena":"agents","category":"pptxslides","elo":1181,"rank":5,"win_rate":44.3},{"arena":"agents","category":"python-pptxslides","elo":1180,"rank":11,"win_rate":42.1},{"arena":"agents","category":"webapps","elo":1268,"rank":8,"win_rate":59.3},{"arena":"models","category":"3d","elo":1330,"rank":7,"win_rate":60.3},{"arena":"models","category":"asciiart","elo":1189,"rank":26,"win_rate":46.6},{"arena":"models","category":"codecategories","elo":1306,"rank":11,"win_rate":56.8},{"arena":"models","category":"dataviz","elo":1286,"rank":16,"win_rate":56.2},{"arena":"models","category":"gamedev","elo":1301,"rank":16,"win_rate":56.1},{"arena":"models","category":"svg","elo":1226,"rank":19,"win_rate":51.6},{"arena":"models","category":"uicomponent","elo":1300,"rank":17,"win_rate":56},{"arena":"models","category":"website","elo":1299,"rank":11,"win_rate":55.6}]},"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","expiration_date":null,"family":"kimi-k2","hugging_face_id":"moonshotai/Kimi-K2.6","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2.6-20260420/endpoints"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2.6","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"moonshotai/kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.15,"input":0.73,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":29.6,"coding_index":60.8,"intelligence_index":41.9},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1138,"rank":16,"win_rate":42.9},{"arena":"agents","category":"androidnative","elo":1170,"rank":19,"win_rate":47.3},{"arena":"agents","category":"fullstack","elo":1220,"rank":12,"win_rate":54.7},{"arena":"agents","category":"godotgamedev","elo":1184,"rank":12,"win_rate":49.3},{"arena":"agents","category":"htmlslides","elo":1226,"rank":7,"win_rate":53.9},{"arena":"agents","category":"mobileapps","elo":1204,"rank":16,"win_rate":50.7},{"arena":"agents","category":"python-pptxslides","elo":1154,"rank":15,"win_rate":42.9},{"arena":"agents","category":"webapps","elo":1227,"rank":16,"win_rate":49.3},{"arena":"models","category":"3d","elo":1300,"rank":18,"win_rate":52.3},{"arena":"models","category":"asciiart","elo":1253,"rank":11,"win_rate":53},{"arena":"models","category":"codecategories","elo":1289,"rank":20,"win_rate":53.1},{"arena":"models","category":"dataviz","elo":1254,"rank":31,"win_rate":51.3},{"arena":"models","category":"gamedev","elo":1267,"rank":27,"win_rate":50.6},{"arena":"models","category":"svg","elo":1220,"rank":22,"win_rate":48.8},{"arena":"models","category":"uicomponent","elo":1295,"rank":18,"win_rate":53.7},{"arena":"models","category":"website","elo":1298,"rank":12,"win_rate":55}]},"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","expiration_date":null,"family":"kimi-k2","hugging_face_id":"moonshotai/Kimi-K2.7-Code","knowledge_cutoff":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2.7-code-20260612/endpoints"},"llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":695030,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.7-Code","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.7-Code","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K2.7 Code","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/kimi-k3":{"aliases":["~moonshotai/kimi-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"input":3.0,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":50.1,"coding_index":76.2,"intelligence_index":57.1},"design_arena":[{"arena":"agents","category":"godotgamedev","elo":1199,"rank":11,"win_rate":48.5},{"arena":"agents","category":"python-pptxslides","elo":1375,"rank":1,"win_rate":70.7},{"arena":"agents","category":"webapps","elo":1331,"rank":1,"win_rate":63.8},{"arena":"models","category":"3d","elo":1455,"rank":1,"win_rate":69.4},{"arena":"models","category":"codecategories","elo":1416,"rank":1,"win_rate":66.7},{"arena":"models","category":"dataviz","elo":1380,"rank":2,"win_rate":65.4},{"arena":"models","category":"uicomponent","elo":1397,"rank":1,"win_rate":64.8},{"arena":"models","category":"website","elo":1379,"rank":1,"win_rate":63.6}]},"description":"Kimi multimodal agent model for visual understanding, coding, and planning","expiration_date":null,"family":"kimi-k3","hugging_face_id":"moonshotai/Kimi-K3","knowledge_cutoff":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3-20260715/endpoints"},"llmfit":{"architecture":"kimi_k3","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":967622,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K3","memory":{"min_ram_gb":1553.4,"min_vram_gb":1424.0,"recommended_ram_gb":2589.0},"model_id":"moonshotai/Kimi-K3","parameter_count":"2779.9B","parameters_raw":2779931837184,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_effort":"max","default_enabled":true,"mandatory":false,"supported_efforts":["max","high","low"]},"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"moonshotai/kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MoonshotAI: Kimi K3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"morph/morph-v3-fast":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.8,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"family":"morph","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/morph/morph-v3-fast/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"morph/morph-v3-fast","knowledge":null,"last_updated":"2025-07-07","lifecycle":null,"limits":{"context":81920,"output":38000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Morph: Morph V3 Fast","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-07","retired":false,"tags":null},"morph/morph-v3-large":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.9,"output":1.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","expiration_date":null,"family":"morph","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/morph/morph-v3-large/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"morph/morph-v3-large","knowledge":null,"last_updated":"2025-07-07","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Morph: Morph V3 Large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-07","retired":false,"tags":null},"nex-agi/nex-n2-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0025,"input":0.025,"output":0.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"agi","hugging_face_id":"nex-agi/Nex-N2-Mini","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nex-agi/nex-n2-mini/endpoints"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nex-agi/nex-n2-mini","knowledge":null,"last_updated":"2026-06-24","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Nex AGI: Nex-N2-Mini","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"nex-agi/nex-n2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.025,"input":0.25,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":31,"coding_index":59.1,"intelligence_index":41},"design_arena":[{"arena":"models","category":"3d","elo":1306,"rank":14,"win_rate":53.8},{"arena":"models","category":"asciiart","elo":1133,"rank":48,"win_rate":37.3},{"arena":"models","category":"codecategories","elo":1268,"rank":28,"win_rate":50.2},{"arena":"models","category":"dataviz","elo":1270,"rank":20,"win_rate":52},{"arena":"models","category":"gamedev","elo":1271,"rank":26,"win_rate":50.4},{"arena":"models","category":"svg","elo":1247,"rank":13,"win_rate":52.2},{"arena":"models","category":"uicomponent","elo":1262,"rank":30,"win_rate":49.5},{"arena":"models","category":"website","elo":1250,"rank":33,"win_rate":48.1}]},"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"agi","hugging_face_id":"nex-agi/Nex-N2-Pro","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nex-agi/nex-n2-pro/endpoints"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"nex-agi/Nex-N2-Pro","memory":{"min_ram_gb":221.7,"min_vram_gb":203.3,"recommended_ram_gb":369.6},"model_id":"nex-agi/Nex-N2-Pro","moe":{"active_experts":10,"active_parameters":27202661840,"is_moe":true,"num_experts":512},"parameter_count":"396.8B","parameters_raw":396802360816,"pipeline_tag":"text-generation","provider":"nex-agi","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nex-agi/nex-n2-pro","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Nex AGI: Nex-N2-Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-08","retired":false,"tags":null},"nousresearch/hermes-3-llama-3.1-405b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1.0,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"nousresearch","hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-405B","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/nousresearch/hermes-3-llama-3.1-405b/endpoints"},"llmfit":{"architecture":"llama","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-405B","memory":{"min_ram_gb":226.8,"min_vram_gb":207.9,"recommended_ram_gb":378.0},"model_id":"NousResearch/Hermes-3-Llama-3.1-405B","parameter_count":"405.9B","parameters_raw":405853388800,"pipeline_tag":"text-generation","provider":"NousResearch","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nousresearch/hermes-3-llama-3.1-405b","knowledge":"2023-12-31","last_updated":"2024-08-16","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 3 405B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-08-16","retired":false,"tags":null},"nousresearch/hermes-3-llama-3.1-70b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.7,"output":0.7},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"nousresearch","hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-70B","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/nousresearch/hermes-3-llama-3.1-70b/endpoints"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Hermes-3-Llama-3.1-70B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Hermes-3-Llama-3.1-70B-GGUF"}],"hf_downloads":10320,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-3-Llama-3.1-70B","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"NousResearch/Hermes-3-Llama-3.1-70B","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"NousResearch","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nousresearch/hermes-3-llama-3.1-70b","knowledge":"2023-12-31","last_updated":"2024-08-18","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 3 70B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-08-18","retired":false,"tags":null},"nousresearch/hermes-4-405b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":1.0,"output":3.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"hermes","hugging_face_id":"NousResearch/Hermes-4-405B","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/nousresearch/hermes-4-405b/endpoints"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-4-405B","memory":{"min_ram_gb":226.8,"min_vram_gb":207.9,"recommended_ram_gb":378.0},"model_id":"NousResearch/Hermes-4-405B","parameter_count":"405.9B","parameters_raw":405853388800,"pipeline_tag":"text-generation","provider":"NousResearch","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nousresearch/hermes-4-405b","knowledge":"2024-08-31","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 4 405B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"nousresearch/hermes-4-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.13,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"hermes","hugging_face_id":"NousResearch/Hermes-4-70B","knowledge_cutoff":"2024-08-31","links":{"details":"/api/v1/models/nousresearch/hermes-4-70b/endpoints"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":0,"hf_likes":0,"matched_hugging_face_id":"NousResearch/Hermes-4-70B","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"NousResearch/Hermes-4-70B","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"NousResearch","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nousresearch/hermes-4-70b","knowledge":"2024-08-31","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nous: Hermes 4 70B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"nvidia/llama-nemotron-embed-vl-1b-v2:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":4096,"max_dimensions":4096,"min_dimensions":4096},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"nvidia/llama-nemotron-embed-vl-1b-v2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/llama-nemotron-embed-vl-1b-v2-20260224/endpoints"},"supported_voices":null},"family":null,"id":"nvidia/llama-nemotron-embed-vl-1b-v2:free","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":131072},"modalities":{"input":["text","image"],"output":["embeddings"]},"model":null,"name":"NVIDIA: Llama Nemotron Embed VL 1B V2 (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"nvidia/llama-nemotron-rerank-vl-1b-v2:free":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/llama-nemotron-rerank-vl-1b-v2/endpoints"},"supported_voices":null},"family":null,"id":"nvidia/llama-nemotron-rerank-vl-1b-v2:free","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":10240},"modalities":{"input":["text","image"],"output":["rerank"]},"model":null,"name":"NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"nvidia/nemotron-3-embed-1b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":true,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-embed-1b-20260716/endpoints"},"supported_voices":null},"family":null,"id":"nvidia/nemotron-3-embed-1b:free","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"NVIDIA: Nemotron 3 Embed 1B (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nvidia/nemotron-3-nano-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.05,"output":0.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":2,"coding_index":14.4,"intelligence_index":14.2},"design_arena":[]},"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-GGUF"}],"hf_downloads":920209,"hf_likes":805,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","memory":{"min_ram_gb":17.6,"min_vram_gb":16.2,"recommended_ram_gb":29.4},"model_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","moe":{"active_experts":6,"active_parameters":3000000000,"is_moe":true,"num_experts":128},"parameter_count":"31.6B","parameters_raw":31577937344,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2025-12-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3-nano-30b-a3b","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Nano 30B A3B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-14","retired":false,"tags":null},"nvidia/nemotron-3-nano-30b-a3b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":2,"coding_index":14.4,"intelligence_index":14.2},"design_arena":[]},"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-nano-30b-a3b/endpoints"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-GGUF"}],"hf_downloads":920209,"hf_likes":805,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","memory":{"min_ram_gb":17.6,"min_vram_gb":16.2,"recommended_ram_gb":29.4},"model_id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","moe":{"active_experts":6,"active_parameters":3000000000,"is_moe":true,"num_experts":128},"parameter_count":"31.6B","parameters_raw":31577937344,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2025-12-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3-nano-30b-a3b:free","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Nano 30B A3B (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-14","retired":false,"tags":null},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":13.8,"intelligence_index":null},"design_arena":[]},"description":"Open Nemotron omni model combining reasoning with text, vision, and audio","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428/endpoints"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false,"supports_max_tokens":true},"reasoning_options":[{"type":"budget_tokens"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","knowledge":null,"last_updated":"2026-04-28","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Nano Omni (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.085,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":8.7,"coding_index":37.7,"intelligence_index":25.4},"design_arena":[]},"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":210668,"hf_likes":271,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","memory":{"min_ram_gb":69.1,"min_vram_gb":63.3,"recommended_ram_gb":115.1},"model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","moe":{"active_experts":22,"active_parameters":11226390744,"is_moe":true,"num_experts":512},"parameter_count":"123.6B","parameters_raw":123611012096,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-03-10","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["medium","low"],"supports_max_tokens":true},"reasoning_options":[{"type":"effort","values":["low","medium"]},{"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":1000000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Super","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":8.7,"coding_index":37.7,"intelligence_index":25.4},"design_arena":[]},"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-super-120b-a12b-20230311/endpoints"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":210668,"hf_likes":271,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","memory":{"min_ram_gb":69.1,"min_vram_gb":63.3,"recommended_ram_gb":115.1},"model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","moe":{"active_experts":22,"active_parameters":11226390744,"is_moe":true,"num_experts":512},"parameter_count":"123.6B","parameters_raw":123611012096,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-03-10","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["medium","low"],"supports_max_tokens":true},"reasoning_options":[{"type":"effort","values":["low","medium"]},{"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b:free","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Super (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nvidia/nemotron-3-ultra-550b-a55b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":0.6,"output":3.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":27.4,"coding_index":49.3,"intelligence_index":37.8},"design_arena":[{"arena":"models","category":"3d","elo":1189,"rank":49,"win_rate":41.4},{"arena":"models","category":"asciiart","elo":1112,"rank":51,"win_rate":37.1},{"arena":"models","category":"codecategories","elo":1156,"rank":70,"win_rate":36.2},{"arena":"models","category":"dataviz","elo":1152,"rank":70,"win_rate":37.6},{"arena":"models","category":"gamedev","elo":1180,"rank":60,"win_rate":38.6},{"arena":"models","category":"svg","elo":1126,"rank":51,"win_rate":37.5},{"arena":"models","category":"uicomponent","elo":1181,"rank":57,"win_rate":39.6},{"arena":"models","category":"website","elo":1133,"rank":82,"win_rate":33}]},"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":451729,"hf_likes":302,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","memory":{"min_ram_gb":313.2,"min_vram_gb":287.1,"recommended_ram_gb":522.0},"model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","moe":{"active_experts":22,"active_parameters":50907017398,"is_moe":true,"num_experts":512},"parameter_count":"560.5B","parameters_raw":560524578816,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-06-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["high","medium"],"supports_max_tokens":true},"reasoning_options":[{"type":"effort","values":["medium","high"]},{"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":512288,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Ultra","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/nemotron-3-ultra-550b-a55b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":27.4,"coding_index":49.3,"intelligence_index":37.8},"design_arena":[{"arena":"models","category":"3d","elo":1189,"rank":49,"win_rate":41.4},{"arena":"models","category":"asciiart","elo":1112,"rank":51,"win_rate":37.1},{"arena":"models","category":"codecategories","elo":1156,"rank":70,"win_rate":36.2},{"arena":"models","category":"dataviz","elo":1152,"rank":70,"win_rate":37.6},{"arena":"models","category":"gamedev","elo":1180,"rank":60,"win_rate":38.6},{"arena":"models","category":"svg","elo":1126,"rank":51,"win_rate":37.5},{"arena":"models","category":"uicomponent","elo":1181,"rank":57,"win_rate":39.6},{"arena":"models","category":"website","elo":1133,"rank":82,"win_rate":33}]},"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints"},"llmfit":{"architecture":"nemotron_h","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":451729,"hf_likes":302,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","memory":{"min_ram_gb":313.2,"min_vram_gb":287.1,"recommended_ram_gb":522.0},"model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","moe":{"active_experts":22,"active_parameters":50907017398,"is_moe":true,"num_experts":512},"parameter_count":"560.5B","parameters_raw":560524578816,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2026-06-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["high","medium"],"supports_max_tokens":true},"reasoning_options":[{"type":"effort","values":["medium","high"]},{"type":"budget_tokens"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3-ultra-550b-a55b:free","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3 Ultra (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/nemotron-3.5-content-safety:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/Nemotron-3.5-Content-Safety","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-content-safety-20260604/endpoints"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-3.5-content-safety:free","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron 3.5 Content Safety (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/nemotron-nano-12b-v2-vl:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/nemotron-nano-12b-v2-vl/endpoints"},"llmfit":{"architecture":"unknown","context_length":131072,"discovered":true,"gguf_sources":[],"hf_downloads":173376,"hf_likes":0,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","memory":{"min_ram_gb":7.4,"min_vram_gb":6.8,"recommended_ram_gb":12.3},"model_id":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16","parameter_count":"13.2B","parameters_raw":13181860358,"pipeline_tag":"image-text-to-text","provider":"nvidia","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-nano-12b-v2-vl:free","knowledge":null,"last_updated":"2025-10-28","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron Nano 12B 2 VL (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-28","retired":false,"tags":null},"nvidia/nemotron-nano-9b-v2:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Compact Nemotron model for efficient reasoning and deployable AI agents","expiration_date":null,"family":"nemotron","hugging_face_id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/nvidia/nemotron-nano-9b-v2/endpoints"},"llmfit":{"architecture":"nemotron_h","context_length":131072,"discovered":false,"gguf_sources":[],"hf_downloads":304561,"hf_likes":506,"matched_hugging_face_id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","memory":{"min_ram_gb":5.0,"min_vram_gb":4.6,"recommended_ram_gb":8.3},"model_id":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","parameter_count":"8.9B","parameters_raw":8888227328,"pipeline_tag":"text-generation","provider":"nvidia","quantization":"Q4_K_M","release_date":"2025-08-12","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"nvidia/nemotron-nano-9b-v2:free","knowledge":null,"last_updated":"2025-08-18","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA: Nemotron Nano 9B V2 (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-05","retired":false,"tags":null},"nvidia/parakeet-tdt-0.6b-v3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.5e3,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/nvidia/parakeet-tdt-0.6b-v3/endpoints"},"supported_voices":null},"family":null,"id":"nvidia/parakeet-tdt-0.6b-v3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"NVIDIA: Parakeet TDT 0.6B v3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-27","retired":false,"tags":null},"openai/gpt-3.5-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.5,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":10.7,"intelligence_index":null},"design_arena":[]},"description":"Compact GPT model for low-latency assistance and high-volume workloads","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2021-09-30","links":{"details":"/api/v1/models/openai/gpt-3.5-turbo/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo","knowledge":"2021-09-01","last_updated":"2023-11-06","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-3.5 Turbo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-05-28","retired":false,"tags":null},"openai/gpt-3.5-turbo-0613":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":1.0,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2021-09-30","links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-0613/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo-0613","knowledge":"2021-09-30","last_updated":"2024-01-25","lifecycle":null,"limits":{"context":4095,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-3.5 Turbo (older v0613)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"openai/gpt-3.5-turbo-16k":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":3.0,"output":4.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2021-09-30","links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-16k/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo-16k","knowledge":"2021-09-30","last_updated":"2023-08-28","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-3.5 Turbo 16k","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-08-28","retired":false,"tags":null},"openai/gpt-3.5-turbo-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1.5,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2021-09-30","links":{"details":"/api/v1/models/openai/gpt-3.5-turbo-instruct/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo-instruct","knowledge":"2021-09-30","last_updated":"2023-09-28","lifecycle":null,"limits":{"context":4095,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-3.5 Turbo Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-09-28","retired":false,"tags":null},"openai/gpt-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":30.0,"output":60.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":13.1,"intelligence_index":null},"design_arena":[]},"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2021-09-30","links":{"details":"/api/v1/models/openai/gpt-4/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4","knowledge":"2023-11","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":8191,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-05-28","retired":false,"tags":null},"openai/gpt-4-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":10.0,"output":30.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":21.5,"intelligence_index":null},"design_arena":[]},"description":"Compact GPT model for low-latency assistance and high-volume workloads","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/openai/gpt-4-turbo/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4-turbo","knowledge":"2023-12","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4 Turbo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-04-09","retired":false,"tags":null},"openai/gpt-4-turbo-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":10.0,"output":30.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/openai/gpt-4-turbo-preview/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4-turbo-preview","knowledge":"2023-12-31","last_updated":"2024-01-25","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4 Turbo Preview","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"openai/gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"input":2.0,"output":8.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":905,"rank":104,"win_rate":30.9},{"arena":"models","category":"codecategories","elo":1054,"rank":95,"win_rate":50.9},{"arena":"models","category":"dataviz","elo":1131,"rank":74,"win_rate":59.5},{"arena":"models","category":"gamedev","elo":1132,"rank":74,"win_rate":59.1},{"arena":"models","category":"uicomponent","elo":1036,"rank":90,"win_rate":49.7},{"arena":"models","category":"website","elo":1062,"rank":96,"win_rate":52.3}]},"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/gpt-4.1-2025-04-14/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4.1","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.4,"output":1.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1.7,"coding_index":20.2,"intelligence_index":14.8},"design_arena":[{"arena":"models","category":"3d","elo":892,"rank":105,"win_rate":30.5},{"arena":"models","category":"codecategories","elo":1022,"rank":102,"win_rate":47.5},{"arena":"models","category":"dataviz","elo":1060,"rank":90,"win_rate":49.2},{"arena":"models","category":"gamedev","elo":1123,"rank":78,"win_rate":58.5},{"arena":"models","category":"uicomponent","elo":997,"rank":94,"win_rate":45.4},{"arena":"models","category":"website","elo":1021,"rank":103,"win_rate":47.8}]},"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","expiration_date":null,"family":"gpt-mini","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/gpt-4.1-mini-2025-04-14/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4.1 Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.025,"input":0.1,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1.2,"coding_index":11.1,"intelligence_index":9.6},"design_arena":[{"arena":"models","category":"3d","elo":980,"rank":98,"win_rate":46},{"arena":"models","category":"codecategories","elo":991,"rank":106,"win_rate":47.3},{"arena":"models","category":"dataviz","elo":918,"rank":108,"win_rate":41.1},{"arena":"models","category":"gamedev","elo":1023,"rank":97,"win_rate":49.6},{"arena":"models","category":"uicomponent","elo":952,"rank":100,"win_rate":43.9},{"arena":"models","category":"website","elo":996,"rank":107,"win_rate":48.1}]},"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","expiration_date":null,"family":"gpt-nano","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/gpt-4.1-nano-2025-04-14/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4.1 Nano","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.25,"input":2.5,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":924,"rank":101,"win_rate":39.2},{"arena":"models","category":"codecategories","elo":889,"rank":113,"win_rate":34.8},{"arena":"models","category":"dataviz","elo":884,"rank":110,"win_rate":36},{"arena":"models","category":"gamedev","elo":958,"rank":104,"win_rate":42.3},{"arena":"models","category":"uicomponent","elo":921,"rank":104,"win_rate":38.1},{"arena":"models","category":"website","elo":854,"rank":118,"win_rate":31.5}]},"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/gpt-4o/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4o","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-2024-05-13":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":5.0,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":24.2,"intelligence_index":null},"design_arena":[]},"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/gpt-4o-2024-05-13/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-05-13","knowledge":"2023-09","last_updated":"2024-05-13","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4o (2024-05-13)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-2024-08-06":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.25,"input":2.5,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/gpt-4o-2024-08-06/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-08-06","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4o (2024-08-06)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-08-06","retired":false,"tags":null},"openai/gpt-4o-2024-11-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.25,"input":2.5,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/gpt-4o-2024-11-20/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-11-20","knowledge":"2023-09","last_updated":"2024-11-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4o (2024-11-20)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-11-20","retired":false,"tags":null},"openai/gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1,"coding_index":11.4,"intelligence_index":null},"design_arena":[]},"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","expiration_date":null,"family":"gpt-mini","hugging_face_id":null,"knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/gpt-4o-mini/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4o-mini","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai/gpt-4o-mini-2024-07-18":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","expiration_date":null,"family":"o-mini","hugging_face_id":null,"knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/gpt-4o-mini-2024-07-18/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-4o-mini-2024-07-18","knowledge":"2023-10-31","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-4o-mini (2024-07-18)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai/gpt-4o-mini-transcribe":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1.25,"output":5.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-4o-mini-transcribe/endpoints"},"supported_voices":null},"family":null,"id":"openai/gpt-4o-mini-transcribe","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":128000},"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"OpenAI: GPT-4o Mini Transcribe","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-01","retired":false,"tags":null},"openai/gpt-4o-transcribe":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":2.5,"output":10.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-4o-transcribe/endpoints"},"supported_voices":null},"family":null,"id":"openai/gpt-4o-transcribe","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":128000},"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"OpenAI: GPT-4o Transcribe","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"openai/gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.125,"input":1.25,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":25.7,"coding_index":37.8,"intelligence_index":34.7},"design_arena":[{"arena":"models","category":"3d","elo":1111,"rank":80,"win_rate":41.4},{"arena":"models","category":"asciiart","elo":1178,"rank":34,"win_rate":49},{"arena":"models","category":"codecategories","elo":1197,"rank":54,"win_rate":54.7},{"arena":"models","category":"dataviz","elo":1262,"rank":26,"win_rate":62.9},{"arena":"models","category":"gamedev","elo":1239,"rank":36,"win_rate":59.5},{"arena":"models","category":"svg","elo":1236,"rank":17,"win_rate":64.1},{"arena":"models","category":"uicomponent","elo":1218,"rank":41,"win_rate":58.2},{"arena":"models","category":"website","elo":1208,"rank":52,"win_rate":53.8}]},"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":"2024-09-30","links":{"details":"/api/v1/models/openai/gpt-5-2025-08-07/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"cache_read":1.25,"input":10.0,"output":10.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1202,"rank":7,"win_rate":49},{"arena":"models","category":"image","elo":1215,"rank":7,"win_rate":54},{"arena":"models","category":"logo","elo":1218,"rank":7,"win_rate":52.8}]},"description":"Image model for prompt-driven generation, editing, and visual design workflows","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5-image/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-5-image","knowledge":"2024-10-01","last_updated":"2025-10-14","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf","file"],"output":["image","text"]},"model":null,"name":"OpenAI: GPT-5 Image","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-14","retired":false,"tags":null},"openai/gpt-5-image-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"cache_read":0.25,"input":2.5,"output":2.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1196,"rank":9,"win_rate":47.9},{"arena":"models","category":"image","elo":1207,"rank":9,"win_rate":51.1},{"arena":"models","category":"logo","elo":1224,"rank":6,"win_rate":51.5}]},"description":"Image model for prompt-driven generation, editing, and visual design workflows","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5-image-mini/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-5-image-mini","knowledge":null,"last_updated":"2025-10-16","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text","file"],"output":["image","text"]},"model":null,"name":"OpenAI: GPT-5 Image Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-16","retired":false,"tags":null},"openai/gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.025,"input":0.25,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":19.4,"coding_index":15.6,"intelligence_index":25.3},"design_arena":[{"arena":"models","category":"3d","elo":1093,"rank":83,"win_rate":36.9},{"arena":"models","category":"asciiart","elo":1159,"rank":40,"win_rate":44.5},{"arena":"models","category":"codecategories","elo":1143,"rank":75,"win_rate":43.5},{"arena":"models","category":"dataviz","elo":1157,"rank":66,"win_rate":43.6},{"arena":"models","category":"gamedev","elo":1182,"rank":59,"win_rate":46.5},{"arena":"models","category":"svg","elo":1138,"rank":48,"win_rate":45.8},{"arena":"models","category":"uicomponent","elo":1141,"rank":65,"win_rate":42},{"arena":"models","category":"website","elo":1148,"rank":73,"win_rate":44.3}]},"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","expiration_date":null,"family":"gpt-mini","hugging_face_id":"","knowledge_cutoff":"2024-05-31","links":{"details":"/api/v1/models/openai/gpt-5-mini-2025-08-07/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5 Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1020,"rank":96,"win_rate":36.1},{"arena":"models","category":"codecategories","elo":1113,"rank":83,"win_rate":48.1},{"arena":"models","category":"dataviz","elo":1090,"rank":85,"win_rate":47.2},{"arena":"models","category":"gamedev","elo":1098,"rank":82,"win_rate":46.6},{"arena":"models","category":"uicomponent","elo":1102,"rank":79,"win_rate":51.9},{"arena":"models","category":"website","elo":1125,"rank":84,"win_rate":48.9}]},"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","expiration_date":null,"family":"gpt-nano","hugging_face_id":"","knowledge_cutoff":"2024-05-31","links":{"details":"/api/v1/models/openai/gpt-5-nano-2025-08-07/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5 Nano","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":15.0,"output":120.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","expiration_date":null,"family":"gpt-pro","hugging_face_id":"","knowledge_cutoff":"2024-09-30","links":{"details":"/api/v1/models/openai/gpt-5-pro-2025-10-06/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","mandatory":true,"supported_efforts":["high"]},"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5-pro","knowledge":"2024-09-30","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5 Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"openai/gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.125,"input":1.25,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":21,"coding_index":49.4,"intelligence_index":36.9},"design_arena":[{"arena":"models","category":"3d","elo":1117,"rank":79,"win_rate":43.9},{"arena":"models","category":"asciiart","elo":1156,"rank":42,"win_rate":48.6},{"arena":"models","category":"codecategories","elo":1200,"rank":51,"win_rate":53.1},{"arena":"models","category":"dataviz","elo":1231,"rank":37,"win_rate":58},{"arena":"models","category":"gamedev","elo":1232,"rank":37,"win_rate":56},{"arena":"models","category":"svg","elo":1197,"rank":32,"win_rate":57.4},{"arena":"models","category":"uicomponent","elo":1202,"rank":48,"win_rate":53},{"arena":"models","category":"website","elo":1211,"rank":48,"win_rate":54.1}]},"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-20251113/endpoints"},"open_weights":false,"reasoning":{"default_effort":"none","default_enabled":true,"mandatory":false,"supported_efforts":["high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.1","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.13,"input":1.25,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"agents","category":"fullstack","elo":1086,"rank":25,"win_rate":44.5},{"arena":"agents","category":"mobileapps","elo":1191,"rank":20,"win_rate":53.4},{"arena":"agents","category":"webapps","elo":1067,"rank":31,"win_rate":44.1},{"arena":"models","category":"codecategories","elo":1180,"rank":61,"win_rate":55.3},{"arena":"models","category":"dataviz","elo":1205,"rank":45,"win_rate":51.4},{"arena":"models","category":"gamedev","elo":1191,"rank":53,"win_rate":52.3},{"arena":"models","category":"website","elo":1184,"rank":63,"win_rate":56}]},"description":"Codex GPT for repository edits, code review, and practical software agents","expiration_date":null,"family":"gpt-codex","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-codex-20251113/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.1-Codex","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.125,"input":1.25,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","expiration_date":null,"family":"gpt-codex","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-codex-max-20251204/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.1-Codex-Max","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-04","retired":false,"tags":null},"openai/gpt-5.1-codex-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.25,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1044,"rank":92,"win_rate":32.8},{"arena":"models","category":"asciiart","elo":1142,"rank":46,"win_rate":43},{"arena":"models","category":"codecategories","elo":1122,"rank":82,"win_rate":41.5},{"arena":"models","category":"dataviz","elo":1124,"rank":79,"win_rate":40.7},{"arena":"models","category":"gamedev","elo":1145,"rank":69,"win_rate":43.4},{"arena":"models","category":"svg","elo":1025,"rank":72,"win_rate":35.3},{"arena":"models","category":"uicomponent","elo":1116,"rank":75,"win_rate":41},{"arena":"models","category":"website","elo":1134,"rank":81,"win_rate":42.8}]},"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","expiration_date":null,"family":"gpt-codex","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.1-codex-mini-20251113/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":false,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.1-codex-mini","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.1-Codex-Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.175,"input":1.75,"output":14.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"website","elo":1217,"rank":42,"win_rate":54.4},{"arena":"agents","category":"androidnative","elo":1095,"rank":25,"win_rate":49.2},{"arena":"agents","category":"fullstack","elo":1085,"rank":26,"win_rate":44.1},{"arena":"agents","category":"godotgamedev","elo":1142,"rank":18,"win_rate":48.1},{"arena":"agents","category":"mobileapps","elo":1153,"rank":23,"win_rate":46.6},{"arena":"agents","category":"webapps","elo":1134,"rank":26,"win_rate":45.3},{"arena":"models","category":"3d","elo":1135,"rank":71,"win_rate":41.5},{"arena":"models","category":"codecategories","elo":1198,"rank":53,"win_rate":49.8},{"arena":"models","category":"dataviz","elo":1229,"rank":38,"win_rate":56.1},{"arena":"models","category":"gamedev","elo":1248,"rank":34,"win_rate":56},{"arena":"models","category":"uicomponent","elo":1225,"rank":39,"win_rate":51.3},{"arena":"models","category":"asciiart","elo":1190,"rank":25,"win_rate":50.7},{"arena":"models","category":"svg","elo":1186,"rank":36,"win_rate":53.7}]},"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-20251211/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.2","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-10","retired":false,"tags":null},"openai/gpt-5.2-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.175,"input":1.75,"output":14.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","expiration_date":"2026-08-10","family":"gpt-codex","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-chat-20251211/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.2-chat","knowledge":"2025-08-31","last_updated":"2025-12-10","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["pdf","image","text","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.2 Chat","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-10","retired":false,"tags":null},"openai/gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.175,"input":1.75,"output":14.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1176,"rank":18,"win_rate":47.5},{"arena":"agents","category":"fullstack","elo":1034,"rank":31,"win_rate":37},{"arena":"agents","category":"godotgamedev","elo":1142,"rank":19,"win_rate":47.8},{"arena":"agents","category":"mobileapps","elo":1149,"rank":27,"win_rate":46.4},{"arena":"agents","category":"webapps","elo":1099,"rank":29,"win_rate":39.5}]},"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","expiration_date":null,"family":"gpt-codex","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-codex-20260114/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.2-Codex","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-14","retired":false,"tags":null},"openai/gpt-5.2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":21.0,"output":168.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","expiration_date":null,"family":"gpt-pro","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.2-pro-20251211/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["xhigh","high","medium"]},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.2-pro","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.2 Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-10","retired":false,"tags":null},"openai/gpt-5.3-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.175,"input":1.75,"output":14.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","expiration_date":"2026-08-10","family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.3-chat-20260303/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.3-chat","knowledge":null,"last_updated":"2026-03-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.3 Chat","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"openai/gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.175,"input":1.75,"output":14.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1084,"rank":28,"win_rate":35.2},{"arena":"agents","category":"fullstack","elo":1025,"rank":32,"win_rate":36.4},{"arena":"agents","category":"godotgamedev","elo":1124,"rank":24,"win_rate":45.1},{"arena":"agents","category":"mobileapps","elo":1114,"rank":31,"win_rate":41.4},{"arena":"agents","category":"webapps","elo":1082,"rank":30,"win_rate":36.9},{"arena":"models","category":"3d","elo":1063,"rank":87,"win_rate":35.3},{"arena":"models","category":"asciiart","elo":1188,"rank":30,"win_rate":51.2},{"arena":"models","category":"codecategories","elo":1173,"rank":62,"win_rate":47.2},{"arena":"models","category":"dataviz","elo":1190,"rank":53,"win_rate":50.5},{"arena":"models","category":"gamedev","elo":1214,"rank":44,"win_rate":51.3},{"arena":"models","category":"svg","elo":1177,"rank":40,"win_rate":54},{"arena":"models","category":"uicomponent","elo":1173,"rank":60,"win_rate":47.3},{"arena":"models","category":"website","elo":1186,"rank":61,"win_rate":48.6}]},"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","expiration_date":null,"family":"gpt-codex","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.3-codex-20260224/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.3-Codex","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"openai/gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.25,"input":2.5,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":41.1,"coding_index":71.1,"intelligence_index":51.4},"design_arena":[{"arena":"models","category":"3d","elo":1157,"rank":61,"win_rate":42.4},{"arena":"models","category":"asciiart","elo":1237,"rank":16,"win_rate":55.5},{"arena":"models","category":"codecategories","elo":1240,"rank":35,"win_rate":52.5},{"arena":"models","category":"dataviz","elo":1262,"rank":25,"win_rate":56.6},{"arena":"models","category":"gamedev","elo":1291,"rank":20,"win_rate":57.6},{"arena":"models","category":"svg","elo":1242,"rank":15,"win_rate":57.8},{"arena":"models","category":"uicomponent","elo":1275,"rank":25,"win_rate":57.4},{"arena":"models","category":"website","elo":1243,"rank":36,"win_rate":52.5},{"arena":"agents","category":"androidnative","elo":1066,"rank":30,"win_rate":47.4},{"arena":"agents","category":"fullstack","elo":1060,"rank":29,"win_rate":40.8},{"arena":"agents","category":"godotgamedev","elo":1135,"rank":22,"win_rate":46.9},{"arena":"agents","category":"mobileapps","elo":1147,"rank":28,"win_rate":45.9},{"arena":"agents","category":"webapps","elo":1107,"rank":28,"win_rate":40.1}]},"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-20260305/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":false,"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.4","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.4-image-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"cache_read":2.0,"input":8.0,"output":15.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-image-2-20260421/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":false,"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.4-image-2","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":272000,"output":128000},"modalities":{"input":["image","text","pdf","file"],"output":["image","text"]},"model":null,"name":"OpenAI: GPT-5.4 Image 2","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/gpt-5.4-mini":{"aliases":["~openai/gpt-mini-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":30.2,"coding_index":56.1,"intelligence_index":40},"design_arena":[]},"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","expiration_date":null,"family":"gpt-mini","hugging_face_id":"","knowledge_cutoff":"2025-08-31","links":{"details":"/api/v1/models/openai/gpt-5.4-mini-20260317/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":false,"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.4 Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":27.5,"coding_index":56.1,"intelligence_index":38.2},"design_arena":[]},"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","expiration_date":null,"family":"gpt-nano","hugging_face_id":"","knowledge_cutoff":"2025-08-31","links":{"details":"/api/v1/models/openai/gpt-5.4-nano-20260317/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":false,"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.4 Nano","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":30.0,"output":180.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","expiration_date":null,"family":"gpt-pro","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-pro-20260305/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["xhigh","high","medium"]},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.4-pro","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.4 Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"input":5.0,"output":30.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":44.9,"coding_index":74.9,"intelligence_index":54.8},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1186,"rank":12,"win_rate":51.6},{"arena":"agents","category":"agentichtmlslides","elo":1084,"rank":9,"win_rate":34.2},{"arena":"agents","category":"agenticslides","elo":1150,"rank":7,"win_rate":43.5},{"arena":"agents","category":"agenticslides(html)","elo":1077,"rank":9,"win_rate":33.2},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1155,"rank":7,"win_rate":45.2},{"arena":"agents","category":"androidnative","elo":1200,"rank":14,"win_rate":50.9},{"arena":"agents","category":"fullstack","elo":1128,"rank":19,"win_rate":43.2},{"arena":"agents","category":"godotgamedev","elo":1211,"rank":10,"win_rate":52.4},{"arena":"agents","category":"htmlslides","elo":1090,"rank":19,"win_rate":34.8},{"arena":"agents","category":"mobileapps","elo":1210,"rank":13,"win_rate":51.7},{"arena":"agents","category":"pptxslides","elo":1157,"rank":7,"win_rate":45.3},{"arena":"agents","category":"python-pptxslides","elo":1152,"rank":16,"win_rate":43.3},{"arena":"agents","category":"webapps","elo":1165,"rank":24,"win_rate":42.8},{"arena":"models","category":"3d","elo":1249,"rank":31,"win_rate":51.9},{"arena":"models","category":"asciiart","elo":1287,"rank":9,"win_rate":60.6},{"arena":"models","category":"codecategories","elo":1286,"rank":21,"win_rate":55.7},{"arena":"models","category":"dataviz","elo":1281,"rank":17,"win_rate":56.4},{"arena":"models","category":"gamedev","elo":1348,"rank":3,"win_rate":60.8},{"arena":"models","category":"svg","elo":1278,"rank":4,"win_rate":58.1},{"arena":"models","category":"uicomponent","elo":1293,"rank":20,"win_rate":56.5},{"arena":"models","category":"website","elo":1280,"rank":22,"win_rate":55.2}]},"description":"Default frontier GPT for coding, computer use, research, and knowledge work","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":"2025-12-01","links":{"details":"/api/v1/models/openai/gpt-5.5-20260423/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"openai/gpt-5.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":30.0,"output":180.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","expiration_date":null,"family":"gpt-pro","hugging_face_id":"","knowledge_cutoff":"2025-12-01","links":{"details":"/api/v1/models/openai/gpt-5.5-pro-20260423/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["xhigh","high","medium"]},"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.5-pro","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.5 Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"openai/gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":45.6,"coding_index":71.4,"intelligence_index":51.2},"design_arena":[]},"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","expiration_date":null,"family":"gpt-luna","hugging_face_id":null,"knowledge_cutoff":"2026-02-16","links":{"details":"/api/v1/models/openai/gpt-5.6-luna-20260709/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.6 Luna","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-luna-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.01,"cache_write":0.125,"input":0.1,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","expiration_date":null,"family":"gpt-luna","hugging_face_id":null,"knowledge_cutoff":"2026-02-16","links":{"details":"/api/v1/models/openai/gpt-5.6-luna-pro-20260709/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.6-luna-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.6 Luna Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-sol":{"aliases":["~openai/gpt-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"cache_write":6.25,"input":5.0,"output":30.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":54,"coding_index":77.4,"intelligence_index":58.9},"design_arena":[]},"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","expiration_date":null,"family":"gpt-sol","hugging_face_id":null,"knowledge_cutoff":"2026-02-16","links":{"details":"/api/v1/models/openai/gpt-5.6-sol-20260709/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.6 Sol","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-sol-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"cache_write":6.25,"input":5.0,"output":30.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","expiration_date":null,"family":"gpt-sol","hugging_face_id":null,"knowledge_cutoff":"2026-02-16","links":{"details":"/api/v1/models/openai/gpt-5.6-sol-pro-20260709/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.6-sol-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.6 Sol Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"cache_write":1.25,"input":1.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":47.4,"coding_index":76.7,"intelligence_index":55},"design_arena":[]},"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","expiration_date":null,"family":"gpt-terra","hugging_face_id":null,"knowledge_cutoff":"2026-02-16","links":{"details":"/api/v1/models/openai/gpt-5.6-terra-20260709/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.6 Terra","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-terra-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"cache_write":1.25,"input":1.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","expiration_date":null,"family":"gpt-terra","hugging_face_id":null,"knowledge_cutoff":"2026-02-16","links":{"details":"/api/v1/models/openai/gpt-5.6-terra-pro-20260709/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-5.6-terra-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5.6 Terra Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-audio":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":32.0,"input":2.5,"output":10.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","expiration_date":null,"family":"gpt","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-audio/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-audio","knowledge":null,"last_updated":"2026-01-19","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"OpenAI: GPT Audio","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"openai/gpt-audio-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"audio":0.6,"input":0.6,"output":2.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","expiration_date":null,"family":"o-mini","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-audio-mini/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-audio-mini","knowledge":null,"last_updated":"2026-01-19","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"OpenAI: GPT Audio Mini","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"openai/gpt-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"input":5.0,"output":30.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","expiration_date":null,"family":"gpt","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-chat-latest-20260505/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/gpt-chat-latest","knowledge":null,"last_updated":"2026-05-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: GPT Chat Latest","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-05","retired":false,"tags":null},"openai/gpt-image-1":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"cache_read":1.25,"input":10.0,"output":10.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"benchmarks":{"design_arena":[{"arena":"models","category":"imageediting","elo":1122,"rank":5,"win_rate":45.3}]},"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-image-1/endpoints"},"supported_voices":null},"family":null,"id":"openai/gpt-image-1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":400000},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"OpenAI: GPT Image 1","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"openai/gpt-image-1-mini":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"cache_read":0.25,"input":2.5,"output":2.5},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-image-1-mini/endpoints"},"supported_voices":null},"family":null,"id":"openai/gpt-image-1-mini","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":400000},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"OpenAI: GPT Image 1 Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"openai/gpt-image-2":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"cache_read":2.0,"input":8.0,"output":8.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-image-2/endpoints"},"supported_voices":null},"family":null,"id":"openai/gpt-image-2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":400000},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"OpenAI: GPT Image 2","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.037,"output":0.17},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":13.2,"coding_index":30.4,"intelligence_index":23.8},"design_arena":[{"arena":"models","category":"3d","elo":956,"rank":99,"win_rate":29.4},{"arena":"models","category":"codecategories","elo":992,"rank":105,"win_rate":33.4},{"arena":"models","category":"dataviz","elo":1026,"rank":95,"win_rate":45.1},{"arena":"models","category":"gamedev","elo":1046,"rank":92,"win_rate":40.6},{"arena":"models","category":"uicomponent","elo":960,"rank":99,"win_rate":35.5},{"arena":"models","category":"website","elo":991,"rank":108,"win_rate":32.5}]},"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","expiration_date":null,"family":"gpt-oss","hugging_face_id":"openai/gpt-oss-120b","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/gpt-oss-120b/endpoints"},"llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: gpt-oss-120b","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.03,"output":0.13},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":3.1,"coding_index":20.7,"intelligence_index":14.9},"design_arena":[{"arena":"models","category":"dataviz","elo":961,"rank":101,"win_rate":39.7},{"arena":"models","category":"website","elo":876,"rank":116,"win_rate":27.9}]},"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","expiration_date":null,"family":"gpt-oss","hugging_face_id":"openai/gpt-oss-20b","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/gpt-oss-20b/endpoints"},"llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: gpt-oss-20b","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":3.1,"coding_index":20.7,"intelligence_index":14.9},"design_arena":[{"arena":"models","category":"dataviz","elo":961,"rank":101,"win_rate":39.7},{"arena":"models","category":"website","elo":876,"rank":116,"win_rate":27.9}]},"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","expiration_date":null,"family":"gpt-oss","hugging_face_id":"openai/gpt-oss-20b","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/gpt-oss-20b/endpoints"},"llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-oss-20b:free","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: gpt-oss-20b (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-safeguard-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0375,"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","expiration_date":null,"family":"gpt-oss","hugging_face_id":"openai/gpt-oss-safeguard-20b","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/gpt-oss-safeguard-20b/endpoints"},"llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-safeguard-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-safeguard-20b-GGUF"}],"hf_downloads":101805,"hf_likes":243,"matched_hugging_face_id":"openai/gpt-oss-safeguard-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-safeguard-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-09-18","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openai/gpt-oss-safeguard-20b","knowledge":null,"last_updated":"2025-10-29","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: gpt-oss-safeguard-20b","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-29","retired":false,"tags":null},"openai/o1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":7.5,"input":15.0,"output":60.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":null,"coding_index":39.7,"intelligence_index":null},"design_arena":[]},"description":"O-series reasoning model for hard analysis, math, coding, and planning","expiration_date":null,"family":"o","hugging_face_id":"","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/o1-2024-12-17/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o1","knowledge":"2023-09","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: o1","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-17","retired":false,"tags":null},"openai/o1-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":150.0,"output":600.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","expiration_date":null,"family":"o-pro","hugging_face_id":"","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/o1-pro/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o1-pro","knowledge":"2023-09","last_updated":"2025-03-19","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: o1-pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-19","retired":false,"tags":null},"openai/o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"input":2.0,"output":8.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1048,"rank":96,"win_rate":51.9},{"arena":"models","category":"dataviz","elo":1200,"rank":47,"win_rate":48.1},{"arena":"models","category":"gamedev","elo":1087,"rank":85,"win_rate":56.9},{"arena":"models","category":"uicomponent","elo":1052,"rank":87,"win_rate":53.3},{"arena":"models","category":"website","elo":1059,"rank":97,"win_rate":53.8}]},"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","expiration_date":null,"family":"o","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/o3-2025-04-16/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: o3","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","expiration_date":null,"family":"o-mini","hugging_face_id":"","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/o3-mini-2025-01-31/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: o3 Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-01-31","retired":false,"tags":null},"openai/o3-mini-high":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":1.7,"coding_index":16.3,"intelligence_index":15.6},"design_arena":[]},"description":"O-series reasoning model for hard analysis, math, coding, and planning","expiration_date":null,"family":"o","hugging_face_id":"","knowledge_cutoff":"2023-10-31","links":{"details":"/api/v1/models/openai/o3-mini-high-2025-01-31/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","mandatory":true,"supported_efforts":["high"]},"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o3-mini-high","knowledge":"2023-10-31","last_updated":"2025-02-12","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: o3 Mini High","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-02-12","retired":false,"tags":null},"openai/o3-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":20.0,"output":80.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"High-effort o3 tier for difficult technical reasoning and careful answers","expiration_date":null,"family":"o-pro","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/o3-pro-2025-06-10/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o3-pro","knowledge":"2024-05","last_updated":"2025-06-10","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf","image","file"],"output":["text"]},"model":null,"name":"OpenAI: o3 Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-06-10","retired":false,"tags":null},"openai/o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":909,"rank":103,"win_rate":34},{"arena":"models","category":"codecategories","elo":1004,"rank":104,"win_rate":46.4},{"arena":"models","category":"dataviz","elo":1018,"rank":96,"win_rate":50},{"arena":"models","category":"gamedev","elo":1055,"rank":89,"win_rate":50},{"arena":"models","category":"uicomponent","elo":1019,"rank":92,"win_rate":46.9},{"arena":"models","category":"website","elo":1008,"rank":106,"win_rate":47.1}]},"description":"Fast o-series model for compact reasoning, coding, and tool use","expiration_date":null,"family":"o-mini","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/o4-mini-2025-04-16/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o4-mini","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: o4 Mini","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/o4-mini-high":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","expiration_date":null,"family":"o","hugging_face_id":"","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/openai/o4-mini-high-2025-04-16/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","mandatory":true,"supported_efforts":["high"]},"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"openai/o4-mini-high","knowledge":"2024-06-30","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["image","text","pdf","file"],"output":["text"]},"model":null,"name":"OpenAI: o4 Mini High","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/sora-2-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/sora-2-pro-20260320/endpoints"},"supported_voices":null},"family":null,"id":"openai/sora-2-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"OpenAI: Sora 2 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-23","retired":false,"tags":null},"openai/text-embedding-3-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":3072,"max_dimensions":3072,"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.13,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/text-embedding-3-large/endpoints"},"supported_voices":null},"family":null,"id":"openai/text-embedding-3-large","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"OpenAI: Text Embedding 3 Large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"openai/text-embedding-3-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1536,"max_dimensions":1536,"min_dimensions":1},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.02,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/text-embedding-3-small/endpoints"},"supported_voices":null},"family":null,"id":"openai/text-embedding-3-small","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"OpenAI: Text Embedding 3 Small","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"openai/text-embedding-ada-002":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1536,"max_dimensions":1536,"min_dimensions":1536},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.1,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/text-embedding-ada-002/endpoints"},"supported_voices":null},"family":null,"id":"openai/text-embedding-ada-002","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"OpenAI: Text Embedding Ada 002","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"openai/whisper-1":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":6.0e3,"output":0.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/whisper-1/endpoints"},"supported_voices":[]},"family":null,"id":"openai/whisper-1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"OpenAI: Whisper 1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"openai/whisper-large-v3":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1.5e3,"output":0.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":"openai/whisper-large-v3","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/whisper-large-v3/endpoints"},"supported_voices":null},"family":null,"id":"openai/whisper-large-v3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"OpenAI: Whisper Large V3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-01","retired":false,"tags":null},"openai/whisper-large-v3-turbo":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":4.0e4,"output":0.0},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"expiration_date":null,"hugging_face_id":"openai/whisper-large-v3-turbo","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openai/whisper-large-v3-turbo/endpoints"},"supported_voices":null},"family":null,"id":"openai/whisper-large-v3-turbo","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"OpenAI: Whisper Large V3 Turbo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-01","retired":false,"tags":null},"openrouter/auto":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":-1.0e6,"output":-1.0e6},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","expiration_date":null,"family":"auto","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openrouter/auto/endpoints"},"open_weights":false,"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openrouter/auto","knowledge":null,"last_updated":"2023-11-08","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","audio","pdf","video","file"],"output":["text","image"]},"model":null,"name":"Auto Router","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-11-08","retired":false,"tags":null},"openrouter/auto-beta":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":true}},"cost":{"input":-1.0e6,"output":-1.0e6},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openrouter/auto-beta/endpoints"},"supported_voices":null},"family":null,"id":"openrouter/auto-beta","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":2000000},"modalities":{"input":["text","image","file","audio","video"],"output":["text","image"]},"model":null,"name":"Auto Router (Beta)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-17","retired":false,"tags":null},"openrouter/bodybuilder":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":-1.0e6,"output":-1.0e6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Preview model for early access evaluation, prototyping, and compatibility testing","expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openrouter/bodybuilder/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":false},"family":null,"id":"openrouter/bodybuilder","knowledge":null,"last_updated":"2025-12-05","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Body Builder (beta)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-05","retired":false,"tags":null},"openrouter/free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openrouter/free/endpoints"},"open_weights":false,"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"openrouter/free","knowledge":null,"last_updated":"2026-02-01","lifecycle":null,"limits":{"context":200000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Free Models Router","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-01","retired":false,"tags":null},"openrouter/fusion":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":-1.0e6,"output":-1.0e6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/openrouter/fusion/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":false},"family":null,"id":"openrouter/fusion","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenRouter: Fusion","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"openrouter/pareto-code":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":-1.0e6,"output":-1.0e6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/openrouter/pareto-code/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":false},"family":null,"id":"openrouter/pareto-code","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":2000000,"output":200000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Pareto Code Router","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"perceptron/perceptron-mk1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.15,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/perceptron/perceptron-mk1-20260512/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"perceptron/perceptron-mk1","knowledge":null,"last_updated":"2026-05-12","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Perceptron: Perceptron Mk1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-12","retired":false,"tags":null},"perplexity/pplx-embed-v1-0.6b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":768,"max_dimensions":768,"min_dimensions":768},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.004,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/perplexity/pplx-embed-v1-0.6B/endpoints"},"supported_voices":null},"family":null,"id":"perplexity/pplx-embed-v1-0.6b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Perplexity: Embed V1 0.6B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"perplexity/pplx-embed-v1-4b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":4096,"max_dimensions":4096,"min_dimensions":4096},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.03,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/perplexity/pplx-embed-v1-4B/endpoints"},"supported_voices":null},"family":null,"id":"perplexity/pplx-embed-v1-4b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Perplexity: Embed V1 4B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"perplexity/sonar":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1.0,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","expiration_date":null,"family":"sonar","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/perplexity/sonar/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"perplexity/sonar","knowledge":null,"last_updated":"2025-01-27","lifecycle":null,"limits":{"context":127072,"output":127072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null},"perplexity/sonar-deep-research":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":2.0,"output":8.0,"reasoning":3.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","expiration_date":null,"family":"sonar-deep-research","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/perplexity/sonar-deep-research/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"perplexity/sonar-deep-research","knowledge":null,"last_updated":"2025-03-07","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Deep Research","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-07","retired":false,"tags":null},"perplexity/sonar-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":3.0,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Advanced Sonar search model for deeper research and cited synthesis","expiration_date":null,"family":"sonar-pro","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/perplexity/sonar-pro/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"perplexity/sonar-pro","knowledge":null,"last_updated":"2025-03-07","lifecycle":null,"limits":{"context":200000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-07","retired":false,"tags":null},"perplexity/sonar-pro-search":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":3.0,"output":15.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Advanced Sonar search model for deeper research and cited synthesis","expiration_date":null,"family":"sonar-pro","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/perplexity/sonar-pro-search/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"perplexity/sonar-pro-search","knowledge":null,"last_updated":"2025-10-30","lifecycle":null,"limits":{"context":200000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Pro Search","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.018,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-30","retired":false,"tags":null},"perplexity/sonar-reasoning-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":2.0,"output":8.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Web-grounded reasoning model for multi-step research and cited answers","expiration_date":null,"family":"sonar-reasoning","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/perplexity/sonar-reasoning-pro/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"perplexity/sonar-reasoning-pro","knowledge":null,"last_updated":"2025-03-07","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Perplexity: Sonar Reasoning Pro","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-07","retired":false,"tags":null},"poolside/laguna-s-2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.009,"input":0.09,"output":0.18},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","expiration_date":null,"family":"laguna-s","hugging_face_id":"poolside/Laguna-S-2.1","knowledge_cutoff":null,"links":{"details":"/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints"},"llmfit":{"architecture":"laguna","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":81584,"hf_likes":902,"matched_hugging_face_id":"poolside/Laguna-S-2.1","memory":{"min_ram_gb":65.7,"min_vram_gb":60.2,"recommended_ram_gb":109.5},"model_id":"poolside/Laguna-S-2.1","moe":{"active_experts":10,"active_parameters":10240750390,"is_moe":true,"num_experts":256},"parameter_count":"117.6B","parameters_raw":117561977600,"pipeline_tag":"text-generation","provider":"poolside","quantization":"Q4_K_M","release_date":"2026-07-13","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"poolside/laguna-s-2.1","knowledge":null,"last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna S 2.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"poolside/laguna-s-2.1:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","expiration_date":null,"family":"laguna-s","hugging_face_id":"poolside/Laguna-S-2.1","knowledge_cutoff":null,"links":{"details":"/api/v1/models/poolside/laguna-s-2.1-20260720/endpoints"},"llmfit":{"architecture":"laguna","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":81584,"hf_likes":902,"matched_hugging_face_id":"poolside/Laguna-S-2.1","memory":{"min_ram_gb":65.7,"min_vram_gb":60.2,"recommended_ram_gb":109.5},"model_id":"poolside/Laguna-S-2.1","moe":{"active_experts":10,"active_parameters":10240750390,"is_moe":true,"num_experts":256},"parameter_count":"117.6B","parameters_raw":117561977600,"pipeline_tag":"text-generation","provider":"poolside","quantization":"Q4_K_M","release_date":"2026-07-13","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"poolside/laguna-s-2.1:free","knowledge":null,"last_updated":"2026-07-21","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna S 2.1 (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"poolside/laguna-xs-2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.06,"output":0.12},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Agentic coding model from Poolside in the XS size class for local deployment","expiration_date":null,"family":"laguna","hugging_face_id":"poolside/Laguna-XS-2.1","knowledge_cutoff":null,"links":{"details":"/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints"},"llmfit":{"architecture":"laguna","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":33669,"hf_likes":200,"matched_hugging_face_id":"poolside/Laguna-XS-2.1","memory":{"min_ram_gb":18.7,"min_vram_gb":17.1,"recommended_ram_gb":31.1},"model_id":"poolside/Laguna-XS-2.1","moe":{"active_experts":8,"active_parameters":2664958542,"is_moe":true,"num_experts":256},"parameter_count":"33.4B","parameters_raw":33442617088,"pipeline_tag":"text-generation","provider":"poolside","quantization":"Q4_K_M","release_date":"2026-06-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"poolside/laguna-xs-2.1","knowledge":null,"last_updated":"2026-07-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna XS 2.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-02","retired":false,"tags":null},"poolside/laguna-xs-2.1:free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","expiration_date":null,"family":"laguna","hugging_face_id":"poolside/Laguna-XS-2.1","knowledge_cutoff":null,"links":{"details":"/api/v1/models/poolside/laguna-xs-2.1-20260625/endpoints"},"llmfit":{"architecture":"laguna","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":33669,"hf_likes":200,"matched_hugging_face_id":"poolside/Laguna-XS-2.1","memory":{"min_ram_gb":18.7,"min_vram_gb":17.1,"recommended_ram_gb":31.1},"model_id":"poolside/Laguna-XS-2.1","moe":{"active_experts":8,"active_parameters":2664958542,"is_moe":true,"num_experts":256},"parameter_count":"33.4B","parameters_raw":33442617088,"pipeline_tag":"text-generation","provider":"poolside","quantization":"Q4_K_M","release_date":"2026-06-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"poolside/laguna-xs-2.1:free","knowledge":null,"last_updated":"2026-07-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Poolside: Laguna XS 2.1 (free)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-02","retired":false,"tags":null},"qwen/qwen-2.5-72b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.36,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/qwen/qwen-2.5-72b-instruct/endpoints"},"llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-72B-Instruct-GGUF"}],"hf_downloads":445760,"hf_likes":968,"matched_hugging_face_id":"Qwen/Qwen2.5-72B-Instruct","memory":{"min_ram_gb":40.6,"min_vram_gb":37.2,"recommended_ram_gb":67.7},"model_id":"Qwen/Qwen2.5-72B-Instruct","parameter_count":"72.7B","parameters_raw":72706203648,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen-2.5-72b-instruct","knowledge":"2024-06-30","last_updated":"2024-09-19","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 72B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-09-19","retired":false,"tags":null},"qwen/qwen-2.5-7b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen2.5-7B-Instruct","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/qwen/qwen-2.5-7b-instruct/endpoints"},"llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/Qwen2.5-7B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-7B-Instruct-GGUF"}],"hf_downloads":12160501,"hf_likes":1456,"matched_hugging_face_id":"Qwen/Qwen2.5-7B-Instruct","memory":{"min_ram_gb":4.3,"min_vram_gb":3.9,"recommended_ram_gb":7.1},"model_id":"Qwen/Qwen2.5-7B-Instruct","parameter_count":"7.6B","parameters_raw":7615616512,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-09-16","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen-2.5-7b-instruct","knowledge":"2024-06-30","last_updated":"2024-10-16","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen2.5 7B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-10-16","retired":false,"tags":null},"qwen/qwen-2.5-coder-32b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.66,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen2.5-Coder-32B-Instruct","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/qwen/qwen-2.5-coder-32b-instruct/endpoints"},"llmfit":{"architecture":"qwen2","context_length":32768,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen2.5-Coder-32B-Instruct-GGUF"},{"provider":"bartowski","repo":"bartowski/Qwen2.5-Coder-32B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-Coder-32B-Instruct-GGUF"}],"hf_downloads":1205822,"hf_likes":2092,"matched_hugging_face_id":"Qwen/Qwen2.5-Coder-32B-Instruct","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen2.5-Coder-32B-Instruct","parameter_count":"32.8B","parameters_raw":32763876352,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2024-11-06","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen-2.5-coder-32b-instruct","knowledge":"2024-06-30","last_updated":"2024-11-11","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 Coder 32B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-11-11","retired":false,"tags":null},"qwen/qwen-audio-3.0-tts-flash":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":15.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen-audio-3.0-tts-flash-20260723/endpoints"},"supported_voices":["loongjohn","longanhuan_v3.6"]},"family":null,"id":"qwen/qwen-audio-3.0-tts-flash","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Qwen: Qwen-Audio-3.0-TTS Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"qwen/qwen-audio-3.0-tts-plus":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":20.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen-audio-3.0-tts-plus-20260723/endpoints"},"supported_voices":["longanlingxin","longanlufeng"]},"family":null,"id":"qwen/qwen-audio-3.0-tts-plus","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Qwen: Qwen-Audio-3.0-TTS Plus","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"qwen/qwen-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.052,"cache_write":0.325,"input":0.26,"output":0.78},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen-plus-2025-01-25/endpoints"},"open_weights":false,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen-plus","knowledge":"2024-04","last_updated":"2025-09-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen-Plus","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-02-01","retired":false,"tags":null},"qwen/qwen-plus-2025-07-28":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.26,"output":0.78},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen-plus-2025-07-28","knowledge":"2025-03-31","last_updated":"2025-09-08","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen Plus 0728","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-08","retired":false,"tags":null},"qwen/qwen-plus-2025-07-28:thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_write":0.5,"input":0.4,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen-plus-2025-07-28/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen-plus-2025-07-28:thinking","knowledge":"2025-03-31","last_updated":"2025-09-08","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen Plus 0728 (thinking)","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-08","retired":false,"tags":null},"qwen/qwen2.5-vl-72b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.25,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen2.5-VL-72B-Instruct","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/qwen/qwen2.5-vl-72b-instruct/endpoints"},"llmfit":{"architecture":"qwen2_5_vl","context_length":128000,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen2.5-VL-72B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen2.5-VL-72B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen2.5-VL-72B-Instruct-GGUF"}],"hf_downloads":582424,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen2.5-VL-72B-Instruct","memory":{"min_ram_gb":41.0,"min_vram_gb":37.6,"recommended_ram_gb":68.4},"model_id":"Qwen/Qwen2.5-VL-72B-Instruct","parameter_count":"73.4B","parameters_raw":73410777344,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen2.5-vl-72b-instruct","knowledge":"2024-06-30","last_updated":"2025-02-01","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen2.5 VL 72B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-02-01","retired":false,"tags":null},"qwen/qwen3-14b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.2275,"output":0.91},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":1.8,"coding_index":13.8,"intelligence_index":10.4},"design_arena":[]},"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-14B","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-14b-04-28/endpoints"},"llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-14B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-14B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-14B-GGUF"}],"hf_downloads":2837654,"hf_likes":436,"matched_hugging_face_id":"Qwen/Qwen3-14B","memory":{"min_ram_gb":8.3,"min_vram_gb":7.6,"recommended_ram_gb":13.8},"model_id":"Qwen/Qwen3-14B","parameter_count":"14.8B","parameters_raw":14768307200,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-14b","knowledge":"2025-03-31","last_updated":"2025-04-28","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 14B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-235b-a22b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.455,"output":1.82},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":914,"rank":102,"win_rate":24.5},{"arena":"models","category":"codecategories","elo":1031,"rank":100,"win_rate":38.3},{"arena":"models","category":"dataviz","elo":1027,"rank":94,"win_rate":41},{"arena":"models","category":"gamedev","elo":981,"rank":103,"win_rate":33.1},{"arena":"models","category":"uicomponent","elo":995,"rank":95,"win_rate":38.9},{"arena":"models","category":"website","elo":1054,"rank":99,"win_rate":40.5}]},"description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-235B-A22B","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-04-28/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-235B-A22B-GGUF"}],"hf_downloads":702999,"hf_likes":1105,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B","moe":{"active_experts":8,"active_parameters":22000000000,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":38912,"min":1,"type":"budget_tokens"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 235B A22B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-235b-a22b-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1495,"output":0.598},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1050,"rank":90,"win_rate":41.1},{"arena":"models","category":"codecategories","elo":1067,"rank":90,"win_rate":42.7},{"arena":"models","category":"dataviz","elo":1084,"rank":86,"win_rate":47.7},{"arena":"models","category":"gamedev","elo":1005,"rank":101,"win_rate":35.3},{"arena":"models","category":"uicomponent","elo":1002,"rank":93,"win_rate":38.9},{"arena":"models","category":"website","elo":1081,"rank":92,"win_rate":43.7}]},"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-07-25/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF"}],"hf_downloads":59827,"hf_likes":793,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-21","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-2507","knowledge":"2025-06-30","last_updated":"2025-07-21","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-21","retired":false,"tags":null},"qwen/qwen3-235b-a22b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.23,"output":2.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":3.8,"coding_index":22.1,"intelligence_index":19.6},"design_arena":[{"arena":"models","category":"3d","elo":1055,"rank":89,"win_rate":40.7},{"arena":"models","category":"codecategories","elo":1061,"rank":94,"win_rate":40.8},{"arena":"models","category":"dataviz","elo":974,"rank":100,"win_rate":32.3},{"arena":"models","category":"gamedev","elo":1010,"rank":100,"win_rate":34.4},{"arena":"models","category":"uicomponent","elo":978,"rank":98,"win_rate":33.9},{"arena":"models","category":"website","elo":1076,"rank":93,"win_rate":42}]},"description":"Qwen reasoning model for deliberate problem solving, math, and coding","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-235b-a22b-thinking-2507/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-235B-A22B-Thinking-2507-GGUF"}],"hf_downloads":29970,"hf_likes":408,"matched_hugging_face_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","memory":{"min_ram_gb":131.4,"min_vram_gb":120.4,"recommended_ram_gb":218.9},"model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","moe":{"active_experts":8,"active_parameters":25713366280,"is_moe":true,"num_experts":128},"parameter_count":"235.1B","parameters_raw":235093634560,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-25","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-thinking-2507","knowledge":"2025-06-30","last_updated":"2025-07-25","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 235B A22B Thinking 2507","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"qwen/qwen3-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.12,"output":0.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":971,"rank":109,"win_rate":37.5},{"arena":"models","category":"dataviz","elo":994,"rank":98,"win_rate":39},{"arena":"models","category":"gamedev","elo":951,"rank":106,"win_rate":33.9},{"arena":"models","category":"uicomponent","elo":981,"rank":97,"win_rate":42.4},{"arena":"models","category":"website","elo":978,"rank":110,"win_rate":37.7}]},"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-30B-A3B","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-04-28/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-30B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-GGUF"}],"hf_downloads":3084500,"hf_likes":914,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B","moe":{"active_experts":8,"active_parameters":3300000000,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b","knowledge":"2025-03-31","last_updated":"2025-04-28","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 30B A3B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-30b-a3b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.04815,"output":0.19305},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-instruct-2507/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-Instruct-2507-GGUF"}],"hf_downloads":1902844,"hf_likes":822,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-28","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b-instruct-2507","knowledge":"2025-06-30","last_updated":"2025-07-29","lifecycle":null,"limits":{"context":262144,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 30B A3B Instruct 2507","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-29","retired":false,"tags":null},"qwen/qwen3-30b-a3b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.2,"output":2.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":1.8,"coding_index":12.1,"intelligence_index":14.4},"design_arena":[{"arena":"models","category":"dataviz","elo":952,"rank":103,"win_rate":33.3},{"arena":"models","category":"website","elo":954,"rank":112,"win_rate":35.5}]},"description":"Qwen reasoning model for deliberate problem solving, math, and coding","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-30B-A3B-Thinking-2507","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-30B-A3B-Thinking-2507-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-30B-A3B-Thinking-2507-GGUF"}],"hf_downloads":137435,"hf_likes":377,"matched_hugging_face_id":"Qwen/Qwen3-30B-A3B-Thinking-2507","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-30B-A3B-Thinking-2507","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-30b-a3b-thinking-2507","knowledge":"2025-06-30","last_updated":"2025-08-28","lifecycle":null,"limits":{"context":81920,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 30B A3B Thinking 2507","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-28","retired":false,"tags":null},"qwen/qwen3-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.08,"output":0.28},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":1.8,"coding_index":15.3,"intelligence_index":11.5},"design_arena":[]},"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-32B","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-32b-04-28/endpoints"},"llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-32B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-32B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-32B-GGUF"}],"hf_downloads":8526764,"hf_likes":727,"matched_hugging_face_id":"Qwen/Qwen3-32B","memory":{"min_ram_gb":18.3,"min_vram_gb":16.8,"recommended_ram_gb":30.5},"model_id":"Qwen/Qwen3-32B","parameter_count":"32.8B","parameters_raw":32762123264,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-32b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 32B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.117,"output":0.455},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":1.5,"coding_index":9,"intelligence_index":8.3},"design_arena":[]},"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-8B","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-8b-04-28/endpoints"},"llmfit":{"architecture":"qwen3","context_length":40960,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-8B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-8B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-8B-GGUF"}],"hf_downloads":15911466,"hf_likes":1273,"matched_hugging_face_id":"Qwen/Qwen3-8B","memory":{"min_ram_gb":4.6,"min_vram_gb":4.2,"recommended_ram_gb":7.6},"model_id":"Qwen/Qwen3-8B","parameter_count":"8.2B","parameters_raw":8190735360,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-8b","knowledge":"2025-03-31","last_updated":"2025-04-28","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 8B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen/qwen3-asr-flash-2026-02-10":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":35.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-asr-flash-2026-02-10/endpoints"},"supported_voices":null},"family":null,"id":"qwen/qwen3-asr-flash-2026-02-10","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"Qwen: Qwen3 ASR Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-14","retired":false,"tags":null},"qwen/qwen3-coder":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.3,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"codecategories","elo":1172,"rank":63,"win_rate":61.2},{"arena":"models","category":"dataviz","elo":1109,"rank":84,"win_rate":54.9},{"arena":"models","category":"gamedev","elo":1151,"rank":64,"win_rate":58.7},{"arena":"models","category":"uicomponent","elo":1149,"rank":64,"win_rate":61.4},{"arena":"models","category":"website","elo":1182,"rank":64,"win_rate":61.7}]},"description":"Qwen coding model for software agents, repository edits, and code reasoning","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-coder-480b-a35b-07-25/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF"}],"hf_downloads":91304,"hf_likes":1357,"matched_hugging_face_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","memory":{"min_ram_gb":268.3,"min_vram_gb":245.9,"recommended_ram_gb":447.2},"model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","moe":{"active_experts":8,"active_parameters":35000000000,"is_moe":true,"num_experts":160},"parameter_count":"480.2B","parameters_raw":480154875392,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-22","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-coder","knowledge":"2025-06-30","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Coder 480B A35B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"qwen/qwen3-coder-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.07,"output":0.27},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"dataviz","elo":1111,"rank":83,"win_rate":54.7},{"arena":"models","category":"uicomponent","elo":1082,"rank":81,"win_rate":54.1},{"arena":"models","category":"website","elo":1111,"rank":86,"win_rate":57.1}]},"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-coder-30b-a3b-instruct/endpoints"},"llmfit":{"architecture":"qwen3_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Coder-30B-A3B-Instruct-GGUF"}],"hf_downloads":1462772,"hf_likes":1187,"matched_hugging_face_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","memory":{"min_ram_gb":17.1,"min_vram_gb":15.6,"recommended_ram_gb":28.4},"model_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","moe":{"active_experts":8,"active_parameters":3339450907,"is_moe":true,"num_experts":128},"parameter_count":"30.5B","parameters_raw":30532122624,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-07-31","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Coder 30B A3B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"qwen/qwen3-coder-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.039,"cache_write":0.24375,"input":0.195,"output":0.975},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-coder-flash/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-coder-flash","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Coder Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-17","retired":false,"tags":null},"qwen/qwen3-coder-next":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.07,"input":0.12,"output":0.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":8.8,"coding_index":36.2,"intelligence_index":21.1},"design_arena":[]},"description":"Qwen coding model for software agents, repository edits, and code reasoning","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-Coder-Next","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-coder-next-2025-02-03/endpoints"},"llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Coder-Next-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-Coder-Next-GGUF"}],"hf_downloads":552224,"hf_likes":1568,"matched_hugging_face_id":"Qwen/Qwen3-Coder-Next","memory":{"min_ram_gb":44.5,"min_vram_gb":40.8,"recommended_ram_gb":74.2},"model_id":"Qwen/Qwen3-Coder-Next","moe":{"active_experts":10,"active_parameters":3000000000,"is_moe":true,"num_experts":512},"parameter_count":"79.7B","parameters_raw":79674391296,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-01-30","source":"llmfit","use_case":"Code generation and completion"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-coder-next","knowledge":null,"last_updated":"2026-02-04","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Coder Next","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-04","retired":false,"tags":null},"qwen/qwen3-coder-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.13,"cache_write":0.8125,"input":0.65,"output":3.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-coder-plus/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-coder-plus","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Coder Plus","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-embedding-4b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":2560,"max_dimensions":2560,"min_dimensions":2560},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.02,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"Qwen/Qwen3-Embedding-4B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-embedding-4b/endpoints"},"llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[{"provider":"mradermacher","repo":"mradermacher/Qwen3-Embedding-4B-GGUF"}],"hf_downloads":3288621,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-Embedding-4B","memory":{"min_ram_gb":2.2,"min_vram_gb":2.1,"recommended_ram_gb":3.7},"model_id":"Qwen/Qwen3-Embedding-4B","parameter_count":"4.0B","parameters_raw":4021774336,"pipeline_tag":"feature-extraction","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"supported_voices":null},"family":null,"id":"qwen/qwen3-embedding-4b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Qwen: Qwen3 Embedding 4B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-28","retired":false,"tags":null},"qwen/qwen3-embedding-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":4096,"max_dimensions":4096,"min_dimensions":4096},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.01,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"Qwen/Qwen3-Embedding-8B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-embedding-8b/endpoints"},"llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[],"hf_downloads":3352596,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-Embedding-8B","memory":{"min_ram_gb":4.2,"min_vram_gb":3.9,"recommended_ram_gb":7.0},"model_id":"Qwen/Qwen3-Embedding-8B","parameter_count":"7.6B","parameters_raw":7567295488,"pipeline_tag":"feature-extraction","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"supported_voices":null},"family":null,"id":"qwen/qwen3-embedding-8b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768,"output":32000},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Qwen: Qwen3 Embedding 8B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-28","retired":false,"tags":null},"qwen/qwen3-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.156,"cache_write":0.975,"input":0.78,"output":3.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1129,"rank":74,"win_rate":43.5},{"arena":"models","category":"asciiart","elo":1165,"rank":39,"win_rate":47.2},{"arena":"models","category":"codecategories","elo":1138,"rank":78,"win_rate":44},{"arena":"models","category":"dataviz","elo":1126,"rank":77,"win_rate":41.1},{"arena":"models","category":"gamedev","elo":1147,"rank":68,"win_rate":43.9},{"arena":"models","category":"svg","elo":1058,"rank":66,"win_rate":37.3},{"arena":"models","category":"uicomponent","elo":1113,"rank":76,"win_rate":40.2},{"arena":"models","category":"website","elo":1142,"rank":78,"win_rate":44.5}]},"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":"2025-06-30","links":{"details":"/api/v1/models/qwen/qwen3-max/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Max","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-max-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.78,"output":3.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","expiration_date":null,"family":"qwen","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-max-thinking","knowledge":null,"last_updated":"2026-02-09","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Max Thinking","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-09","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.09,"output":1.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","knowledge_cutoff":"2025-09-30","links":{"details":"/api/v1/models/qwen/qwen3-next-80b-a3b-instruct-2509/endpoints"},"llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3-Next-80B-A3B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Instruct-GGUF"}],"hf_downloads":285987,"hf_likes":1042,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","moe":{"active_experts":10,"active_parameters":5575200546,"is_moe":true,"num_experts":512},"parameter_count":"81.3B","parameters_raw":81324862720,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-09-09","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Next 80B A3B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-11","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.15,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":2.1,"coding_index":17.4,"intelligence_index":16.7},"design_arena":[]},"description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","knowledge_cutoff":"2025-09-30","links":{"details":"/api/v1/models/qwen/qwen3-next-80b-a3b-thinking-2509/endpoints"},"llmfit":{"architecture":"qwen3_next","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-Next-80B-A3B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-Next-80B-A3B-Thinking-GGUF"}],"hf_downloads":37095,"hf_likes":492,"matched_hugging_face_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","memory":{"min_ram_gb":45.4,"min_vram_gb":41.7,"recommended_ram_gb":75.7},"model_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","moe":{"active_experts":10,"active_parameters":5575200546,"is_moe":true,"num_experts":512},"parameter_count":"81.3B","parameters_raw":81324862720,"pipeline_tag":"text-generation","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2025-09-09","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-thinking","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 Next 80B A3B Thinking","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-11","retired":false,"tags":null},"qwen/qwen3-vl-235b-a22b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.21,"output":1.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-vl-235b-a22b-instruct/endpoints"},"llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-235B-A22B-Instruct-GGUF"}],"hf_downloads":1789796,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","memory":{"min_ram_gb":131.7,"min_vram_gb":120.7,"recommended_ram_gb":219.5},"model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","moe":{"active_experts":8,"active_parameters":25776408752,"is_moe":true,"num_experts":128},"parameter_count":"235.7B","parameters_raw":235670022896,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-vl-235b-a22b-instruct","knowledge":"2025-03-31","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 235B A22B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-vl-235b-a22b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.98,"output":3.95},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-vl-235b-a22b-thinking/endpoints"},"llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-235B-A22B-Thinking-GGUF"}],"hf_downloads":11877,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","memory":{"min_ram_gb":131.7,"min_vram_gb":120.7,"recommended_ram_gb":219.5},"model_id":"Qwen/Qwen3-VL-235B-A22B-Thinking","moe":{"active_experts":8,"active_parameters":25776408752,"is_moe":true,"num_experts":128},"parameter_count":"235.7B","parameters_raw":235670022896,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-vl-235b-a22b-thinking","knowledge":"2025-03-31","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 235B A22B Thinking","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-vl-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-vl-30b-a3b-instruct/endpoints"},"llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":815503,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","memory":{"min_ram_gb":17.4,"min_vram_gb":15.9,"recommended_ram_gb":28.9},"model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","moe":{"active_experts":8,"active_parameters":3398363717,"is_moe":true,"num_experts":128},"parameter_count":"31.1B","parameters_raw":31070754032,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-vl-30b-a3b-instruct","knowledge":"2025-03-31","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 30B A3B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"qwen/qwen3-vl-30b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.2,"output":2.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/qwen/qwen3-vl-30b-a3b-thinking/endpoints"},"llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":39960,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","memory":{"min_ram_gb":17.4,"min_vram_gb":15.9,"recommended_ram_gb":28.9},"model_id":"Qwen/Qwen3-VL-30B-A3B-Thinking","moe":{"active_experts":8,"active_parameters":3398363717,"is_moe":true,"num_experts":128},"parameter_count":"31.1B","parameters_raw":31070754032,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-vl-30b-a3b-thinking","knowledge":"2025-03-31","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 30B A3B Thinking","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"qwen/qwen3-vl-32b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.104,"output":0.416},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-VL-32B-Instruct","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-32b-instruct/endpoints"},"llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3-VL-32B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3-VL-32B-Instruct-GGUF"}],"hf_downloads":2809038,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-32B-Instruct","memory":{"min_ram_gb":18.6,"min_vram_gb":17.1,"recommended_ram_gb":31.1},"model_id":"Qwen/Qwen3-VL-32B-Instruct","parameter_count":"33.4B","parameters_raw":33357390064,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-vl-32b-instruct","knowledge":null,"last_updated":"2025-10-23","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 32B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-23","retired":false,"tags":null},"qwen/qwen3-vl-8b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.117,"output":0.455},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-VL-8B-Instruct","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-8b-instruct/endpoints"},"llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":4896095,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-8B-Instruct","memory":{"min_ram_gb":4.9,"min_vram_gb":4.5,"recommended_ram_gb":8.2},"model_id":"Qwen/Qwen3-VL-8B-Instruct","parameter_count":"8.8B","parameters_raw":8767123696,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-vl-8b-instruct","knowledge":null,"last_updated":"2025-10-14","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 8B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-14","retired":false,"tags":null},"qwen/qwen3-vl-8b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.18,"output":2.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3-VL-8B-Thinking","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3-vl-8b-thinking/endpoints"},"llmfit":{"architecture":"qwen3_vl","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":134706,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-8B-Thinking","memory":{"min_ram_gb":4.9,"min_vram_gb":4.5,"recommended_ram_gb":8.2},"model_id":"Qwen/Qwen3-VL-8B-Thinking","parameter_count":"8.8B","parameters_raw":8767123696,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3-vl-8b-thinking","knowledge":null,"last_updated":"2025-10-14","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["image","text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3 VL 8B Thinking","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-10-14","retired":false,"tags":null},"qwen/qwen3.5-122b-a10b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.26,"output":2.08},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":20.7,"coding_index":45.7,"intelligence_index":32.3},"design_arena":[]},"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3.5-122B-A10B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-122b-a10b-20260224/endpoints"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-122B-A10B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-122B-A10B-GGUF"}],"hf_downloads":2114418,"hf_likes":603,"matched_hugging_face_id":"Qwen/Qwen3.5-122B-A10B","memory":{"min_ram_gb":69.9,"min_vram_gb":64.1,"recommended_ram_gb":116.5},"model_id":"Qwen/Qwen3.5-122B-A10B","moe":{"active_experts":8,"active_parameters":10000000000,"is_moe":true,"num_experts":256},"parameter_count":"125.1B","parameters_raw":125086497008,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-122b-a10b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5-122B-A10B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"qwen/qwen3.5-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.195,"output":1.56},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3.5-27B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-27b-20260224/endpoints"},"llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-27B-GGUF"}],"hf_downloads":2666483,"hf_likes":1023,"matched_hugging_face_id":"Qwen/Qwen3.5-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.5-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-27b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5-27B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"qwen/qwen3.5-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.14,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":11.8,"coding_index":37,"intelligence_index":24},"design_arena":[]},"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3.5-35B-A3B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-35b-a3b-20260224/endpoints"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.5-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-35B-A3B-GGUF"}],"hf_downloads":2582188,"hf_likes":1480,"matched_hugging_face_id":"Qwen/Qwen3.5-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.5-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-24","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-35b-a3b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5-35B-A3B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"qwen/qwen3.5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.39,"output":2.34},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":19.8,"coding_index":48.2,"intelligence_index":33.7},"design_arena":[{"arena":"models","category":"3d","elo":1216,"rank":41,"win_rate":56.7},{"arena":"models","category":"codecategories","elo":1208,"rank":44,"win_rate":52.6},{"arena":"models","category":"dataviz","elo":1202,"rank":46,"win_rate":53.2},{"arena":"models","category":"gamedev","elo":1192,"rank":51,"win_rate":50.1},{"arena":"models","category":"svg","elo":1188,"rank":35,"win_rate":56.1},{"arena":"models","category":"uicomponent","elo":1199,"rank":50,"win_rate":51.4},{"arena":"models","category":"website","elo":1214,"rank":45,"win_rate":52.6}]},"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3.5-397B-A17B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-397b-a17b-20260216/endpoints"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-397B-A17B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-397B-A17B-GGUF"}],"hf_downloads":416324,"hf_likes":1546,"matched_hugging_face_id":"Qwen/Qwen3.5-397B-A17B","memory":{"min_ram_gb":225.4,"min_vram_gb":206.6,"recommended_ram_gb":375.7},"model_id":"Qwen/Qwen3.5-397B-A17B","moe":{"active_experts":10,"active_parameters":17000000000,"is_moe":true,"num_experts":512},"parameter_count":"403.4B","parameters_raw":403397928944,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-16","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5 397B A17B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"qwen/qwen3.5-9b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":7.4,"coding_index":28.7,"intelligence_index":21.4},"design_arena":[]},"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3.5-9B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-9b-20260310/endpoints"},"llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.5-9B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.5-9B-GGUF"}],"hf_downloads":12236962,"hf_likes":1781,"matched_hugging_face_id":"Qwen/Qwen3.5-9B","memory":{"min_ram_gb":5.4,"min_vram_gb":4.9,"recommended_ram_gb":9.0},"model_id":"Qwen/Qwen3.5-9B","parameter_count":"9.7B","parameters_raw":9653104368,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-02-27","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-9b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5-9B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"qwen/qwen3.5-flash-02-23":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.065,"output":0.26},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-flash-20260224/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-flash-02-23","knowledge":null,"last_updated":"2026-02-25","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5-Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"qwen/qwen3.5-plus-02-15":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.26,"output":1.56},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1175,"rank":56,"win_rate":47.7},{"arena":"models","category":"asciiart","elo":1131,"rank":49,"win_rate":43.2},{"arena":"models","category":"codecategories","elo":1195,"rank":56,"win_rate":48.5},{"arena":"models","category":"dataviz","elo":1163,"rank":65,"win_rate":44.9},{"arena":"models","category":"gamedev","elo":1158,"rank":63,"win_rate":42.7},{"arena":"models","category":"svg","elo":1155,"rank":44,"win_rate":48.9},{"arena":"models","category":"uicomponent","elo":1213,"rank":42,"win_rate":52.2},{"arena":"models","category":"website","elo":1211,"rank":49,"win_rate":50}]},"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-plus-20260216/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-plus-02-15","knowledge":"2025-04","last_updated":"2026-02-16","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5 Plus 2026-02-15","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"qwen/qwen3.5-plus-20260420":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_write":0.375,"input":0.3,"output":1.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen3.5","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.5-plus-20260420/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.5-plus-20260420","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.5 Plus 2026-04-20","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen/qwen3.6-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.289,"output":2.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":27,"coding_index":53.7,"intelligence_index":37.1},"design_arena":[]},"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3.6-27B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-27b-20260422/endpoints"},"llmfit":{"architecture":"qwen3_5","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-27B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-27B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-27B-GGUF"}],"hf_downloads":6895121,"hf_likes":2145,"matched_hugging_face_id":"Qwen/Qwen3.6-27B","memory":{"min_ram_gb":15.5,"min_vram_gb":14.2,"recommended_ram_gb":25.9},"model_id":"Qwen/Qwen3.6-27B","parameter_count":"27.8B","parameters_raw":27781427952,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-21","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.6-27b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.6 27B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen/qwen3.6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.14,"output":1.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":21.4,"coding_index":41.9,"intelligence_index":31.6},"design_arena":[]},"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","expiration_date":null,"family":"qwen","hugging_face_id":"Qwen/Qwen3.6-35B-A3B","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-35b-a3b-20260415/endpoints"},"llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Qwen3.6-35B-A3B-GGUF"},{"provider":"ggml-org","repo":"ggml-org/Qwen3.6-35B-A3B-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Qwen3.6-35B-A3B-GGUF"}],"hf_downloads":5928967,"hf_likes":2614,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B","moe":{"active_experts":8,"active_parameters":3000000000,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35951822704,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","release_date":"2026-04-15","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.6-35b-a3b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.6 35B A3B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen/qwen3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_write":0.234375,"input":0.1875,"output":1.125},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen3.6","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-flash/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.6-flash","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.6 Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen/qwen3.6-max-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_write":1.28375,"input":1.027,"output":6.162},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","expiration_date":null,"family":"qwen","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-max-preview-20260420/endpoints"},"open_weights":false,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":131072,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.6-max-preview","knowledge":"2025-04","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.6 Max Preview","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen/qwen3.6-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_write":0.40625,"input":0.325,"output":1.95},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":27.6,"coding_index":54.5,"intelligence_index":39.6},"design_arena":[{"arena":"models","category":"3d","elo":1256,"rank":30,"win_rate":51.6},{"arena":"models","category":"asciiart","elo":1157,"rank":41,"win_rate":44.5},{"arena":"models","category":"codecategories","elo":1263,"rank":31,"win_rate":52.1},{"arena":"models","category":"dataviz","elo":1256,"rank":30,"win_rate":51.6},{"arena":"models","category":"gamedev","elo":1257,"rank":30,"win_rate":50.9},{"arena":"models","category":"svg","elo":1208,"rank":27,"win_rate":51.6},{"arena":"models","category":"uicomponent","elo":1272,"rank":28,"win_rate":52.6},{"arena":"models","category":"website","elo":1261,"rank":29,"win_rate":52.5}]},"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","expiration_date":null,"family":"qwen","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-plus-04-02/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.6-plus","knowledge":"2025-04","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.6 Plus","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"qwen/qwen3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-flash-20260727/endpoints"},"open_weights":false,"reasoning":{"default_enabled":true,"mandatory":false,"supports_max_tokens":true},"reasoning_options":[{"type":"budget_tokens"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.7-flash","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.7 Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"qwen/qwen3.7-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.295,"cache_write":1.84375,"input":1.475,"output":4.425},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":30.6,"coding_index":66,"intelligence_index":46},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1179,"rank":13,"win_rate":48.4},{"arena":"agents","category":"androidnative","elo":1187,"rank":16,"win_rate":50},{"arena":"agents","category":"fullstack","elo":1240,"rank":9,"win_rate":55.5},{"arena":"agents","category":"godotgamedev","elo":1224,"rank":8,"win_rate":55.3},{"arena":"agents","category":"htmlslides","elo":1191,"rank":14,"win_rate":46.7},{"arena":"agents","category":"mobileapps","elo":1210,"rank":14,"win_rate":50.8},{"arena":"agents","category":"python-pptxslides","elo":1227,"rank":9,"win_rate":52.8},{"arena":"agents","category":"webapps","elo":1256,"rank":10,"win_rate":51.1},{"arena":"models","category":"3d","elo":1322,"rank":9,"win_rate":56.8},{"arena":"models","category":"asciiart","elo":1251,"rank":12,"win_rate":53.6},{"arena":"models","category":"codecategories","elo":1305,"rank":12,"win_rate":56.7},{"arena":"models","category":"dataviz","elo":1317,"rank":8,"win_rate":58.1},{"arena":"models","category":"gamedev","elo":1321,"rank":11,"win_rate":57.6},{"arena":"models","category":"svg","elo":1265,"rank":9,"win_rate":59.5},{"arena":"models","category":"uicomponent","elo":1309,"rank":13,"win_rate":55.5},{"arena":"models","category":"website","elo":1297,"rank":13,"win_rate":56.5}]},"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","expiration_date":null,"family":"qwen","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-max-20260520/endpoints"},"open_weights":false,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":262144,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.7 Max","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"qwen/qwen3.7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.064,"cache_write":0.4,"input":0.32,"output":1.28},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":20.8,"coding_index":55.9,"intelligence_index":39},"design_arena":[{"arena":"models","category":"3d","elo":1294,"rank":20,"win_rate":48.3},{"arena":"models","category":"asciiart","elo":1188,"rank":31,"win_rate":45.5},{"arena":"models","category":"codecategories","elo":1290,"rank":19,"win_rate":50.4},{"arena":"models","category":"dataviz","elo":1291,"rank":14,"win_rate":53.8},{"arena":"models","category":"gamedev","elo":1306,"rank":15,"win_rate":51.6},{"arena":"models","category":"uicomponent","elo":1283,"rank":23,"win_rate":49.2},{"arena":"models","category":"website","elo":1295,"rank":17,"win_rate":52.5}]},"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","expiration_date":null,"family":"qwen","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.7-plus-20260602/endpoints"},"open_weights":false,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[{"type":"toggle"},{"max":262144,"min":1,"type":"budget_tokens"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.7 Plus","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-03","retired":false,"tags":null},"qwen/qwen3.8-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.25,"cache_write":2.5,"input":2.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":49.9,"coding_index":68.9,"intelligence_index":53.4},"design_arena":[]},"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","expiration_date":null,"family":"qwen","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-max-20260803/endpoints"},"open_weights":false,"reasoning":{"default_effort":"xhigh","default_enabled":true,"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"]},"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"qwen/qwen3.8-max","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen: Qwen3.8 Max","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"recraft/recraft-v3":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v3-20260413/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v3","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"recraft/recraft-v4":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4-20260413/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"recraft/recraft-v4-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4-pro-20260413/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"recraft/recraft-v4-pro-vector":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4-pro-vector-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4-pro-vector","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4 Pro Vector","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"recraft/recraft-v4-vector":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4-vector-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4-vector","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4 Vector","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"recraft/recraft-v4.1":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4.1-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4.1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"recraft/recraft-v4.1-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4.1-pro-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4.1-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4.1 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"recraft/recraft-v4.1-pro-vector":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4.1-pro-vector-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4.1-pro-vector","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4.1 Pro Vector","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"recraft/recraft-v4.1-utility":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4.1-utility-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4.1-utility","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4.1 Utility","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"recraft/recraft-v4.1-utility-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4.1-utility-pro-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4.1-utility-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4.1 Utility Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"recraft/recraft-v4.1-vector":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/recraft/recraft-v4.1-vector-20260514/endpoints"},"supported_voices":null},"family":null,"id":"recraft/recraft-v4.1-vector","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Recraft: Recraft V4.1 Vector","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-13","retired":false,"tags":null},"rekaai/reka-edge":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","expiration_date":null,"family":"reka","hugging_face_id":"RekaAI/reka-edge-2603","knowledge_cutoff":null,"links":{"details":"/api/v1/models/rekaai/reka-edge-2603/endpoints"},"open_weights":true,"reasoning":{"mandatory":false},"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"rekaai/reka-edge","knowledge":null,"last_updated":"2026-03-20","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Reka Edge","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-20","retired":false,"tags":null},"rekaai/reka-flash-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.1,"output":0.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","expiration_date":null,"family":"reka","hugging_face_id":"RekaAI/reka-flash-3","knowledge_cutoff":"2025-01-31","links":{"details":"/api/v1/models/rekaai/reka-flash-3/endpoints"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"rekaai/reka-flash-3","knowledge":"2025-01-31","last_updated":"2025-03-12","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Reka Flash 3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"relace/relace-apply-3":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.85,"output":1.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/relace/relace-apply-3/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":false},"family":null,"id":"relace/relace-apply-3","knowledge":null,"last_updated":"2025-09-26","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Relace: Relace Apply 3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-26","retired":false,"tags":null},"relace/relace-search":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":1.0,"output":3.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Tool-capable chat model for instruction following and agentic application workflows","expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/relace/relace-search-20251208/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"relace/relace-search","knowledge":null,"last_updated":"2025-12-08","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Relace: Relace Search","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"runway/aleph-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/runway/aleph-2-20260729/endpoints"},"supported_voices":null},"family":null,"id":"runway/aleph-2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image","video"],"output":["video"]},"model":null,"name":"Runway: Aleph 2.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"runway/gen-4.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/runway/gen-4.5-20260729/endpoints"},"supported_voices":null},"family":null,"id":"runway/gen-4.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Runway: Gen-4.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"sakana/fugu-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.5,"input":5.0,"output":30.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Quality-first multi-agent model for hard research, analysis, and competitions","expiration_date":null,"family":"fugu","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/sakana/fugu-ultra-20260615/endpoints"},"open_weights":false,"reasoning":{"default_effort":"xhigh","default_enabled":true,"mandatory":true,"supported_efforts":["max","xhigh","high"]},"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"structured_output":true,"supported_voices":null,"temperature":false},"family":null,"id":"sakana/fugu-ultra","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sakana: Fugu Ultra","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.01,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-24","retired":false,"tags":null},"sao10k/l3-lunaris-8b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.04,"output":0.05},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"Sao10K/L3-8B-Lunaris-v1","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/sao10k/l3-lunaris-8b/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"sao10k/l3-lunaris-8b","knowledge":"2023-12-31","last_updated":"2024-08-13","lifecycle":null,"limits":{"context":8192,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sao10K: Llama 3 8B Lunaris","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-08-13","retired":false,"tags":null},"sao10k/l3.1-euryale-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.85,"output":0.85},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"Sao10K/L3.1-70B-Euryale-v2.2","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/sao10k/l3.1-euryale-70b/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"sao10k/l3.1-euryale-70b","knowledge":"2023-12-31","last_updated":"2024-08-28","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sao10K: Llama 3.1 Euryale 70B v2.2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-08-28","retired":false,"tags":null},"sao10k/l3.3-euryale-70b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.65,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","expiration_date":null,"family":"llama","hugging_face_id":"Sao10K/L3.3-70B-Euryale-v2.3","knowledge_cutoff":"2023-12-31","links":{"details":"/api/v1/models/sao10k/l3.3-euryale-70b-v2.3/endpoints"},"llmfit":{"architecture":"llama","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/L3.3-70B-Euryale-v2.3-GGUF"},{"provider":"mradermacher","repo":"mradermacher/L3.3-70B-Euryale-v2.3-GGUF"}],"hf_downloads":49996,"hf_likes":0,"matched_hugging_face_id":"Sao10K/L3.3-70B-Euryale-v2.3","memory":{"min_ram_gb":39.4,"min_vram_gb":36.1,"recommended_ram_gb":65.7},"model_id":"Sao10K/L3.3-70B-Euryale-v2.3","parameter_count":"70.6B","parameters_raw":70553706496,"pipeline_tag":"text-generation","provider":"sao10k","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"sao10k/l3.3-euryale-70b","knowledge":"2023-12-31","last_updated":"2024-12-18","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sao10K: Llama 3.3 Euryale 70B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-12-18","retired":false,"tags":null},"sentence-transformers/all-minilm-l12-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":384,"max_dimensions":384,"min_dimensions":384},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"sentence-transformers/all-MiniLM-L12-v2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/sentence-transformers/all-minilm-l12-v2-20251117/endpoints"},"supported_voices":null},"family":null,"id":"sentence-transformers/all-minilm-l12-v2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Sentence Transformers: all-MiniLM-L12-v2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"sentence-transformers/all-minilm-l6-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":384,"max_dimensions":384,"min_dimensions":384},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"sentence-transformers/all-MiniLM-L6-v2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/sentence-transformers/all-minilm-l6-v2-20251117/endpoints"},"supported_voices":null},"family":null,"id":"sentence-transformers/all-minilm-l6-v2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Sentence Transformers: all-MiniLM-L6-v2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-17","retired":false,"tags":null},"sentence-transformers/all-mpnet-base-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":768,"max_dimensions":768,"min_dimensions":768},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"sentence-transformers/all-mpnet-base-v2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/sentence-transformers/all-mpnet-base-v2-20251117/endpoints"},"supported_voices":null},"family":null,"id":"sentence-transformers/all-mpnet-base-v2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Sentence Transformers: all-mpnet-base-v2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-17","retired":false,"tags":null},"sentence-transformers/multi-qa-mpnet-base-dot-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":768,"max_dimensions":768,"min_dimensions":768},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"sentence-transformers/multi-qa-mpnet-base-dot-v1","knowledge_cutoff":null,"links":{"details":"/api/v1/models/sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117/endpoints"},"supported_voices":null},"family":null,"id":"sentence-transformers/multi-qa-mpnet-base-dot-v1","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Sentence Transformers: multi-qa-mpnet-base-dot-v1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"sentence-transformers/paraphrase-minilm-l6-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":384,"max_dimensions":384,"min_dimensions":384},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"sentence-transformers/paraphrase-MiniLM-L6-v2","knowledge_cutoff":null,"links":{"details":"/api/v1/models/sentence-transformers/paraphrase-minilm-l6-v2-20251117/endpoints"},"supported_voices":null},"family":null,"id":"sentence-transformers/paraphrase-minilm-l6-v2","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Sentence Transformers: paraphrase-MiniLM-L6-v2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"sesame/csm-1b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":7.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/sesame/csm-1b/endpoints"},"supported_voices":["conversational_a","conversational_b","read_speech_a","read_speech_b","read_speech_c","read_speech_d","none"]},"family":null,"id":"sesame/csm-1b","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Sesame: CSM 1B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"sourceful/riverflow-v2-fast":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/sourceful/riverflow-v2-fast-20260130/endpoints"},"supported_voices":null},"family":null,"id":"sourceful/riverflow-v2-fast","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Sourceful: Riverflow V2 Fast","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-02","retired":false,"tags":null},"sourceful/riverflow-v2-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/sourceful/riverflow-v2-pro-20260130/endpoints"},"supported_voices":null},"family":null,"id":"sourceful/riverflow-v2-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":8192},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Sourceful: Riverflow V2 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-02","retired":false,"tags":null},"sourceful/riverflow-v2.5-fast":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/sourceful/riverflow-v2.5-fast-20260605/endpoints"},"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"supported_voices":null},"family":null,"id":"sourceful/riverflow-v2.5-fast","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Sourceful: Riverflow V2.5 Fast","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"sourceful/riverflow-v2.5-pro":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"benchmarks":{"design_arena":[{"arena":"models","category":"graphicdesign","elo":1471,"rank":1,"win_rate":79.2},{"arena":"models","category":"image","elo":1407,"rank":1,"win_rate":73.1},{"arena":"models","category":"logo","elo":1308,"rank":1,"win_rate":65.1},{"arena":"models","category":"imageediting","elo":1373,"rank":1,"win_rate":75.2}]},"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/sourceful/riverflow-v2.5-pro-20260605/endpoints"},"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["xhigh","high","medium","low"]},"supported_voices":null},"family":null,"id":"sourceful/riverflow-v2.5-pro","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32768},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Sourceful: Riverflow V2.5 Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"stepfun/step-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","expiration_date":null,"hugging_face_id":"stepfun-ai/Step-3.5-Flash","knowledge_cutoff":null,"links":{"details":"/api/v1/models/stepfun/step-3.5-flash/endpoints"},"llmfit":{"architecture":"step3p5","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/Step-3.5-Flash-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Step-3.5-Flash-GGUF"}],"hf_downloads":94390,"hf_likes":829,"matched_hugging_face_id":"stepfun-ai/Step-3.5-Flash","memory":{"min_ram_gb":111.4,"min_vram_gb":102.1,"recommended_ram_gb":185.7},"model_id":"stepfun-ai/Step-3.5-Flash","parameter_count":"199.4B","parameters_raw":199384301376,"pipeline_tag":"text-generation","provider":"stepfun-ai","quantization":"Q4_K_M","release_date":"2026-02-01","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"stepfun/step-3.5-flash","knowledge":"2025-01","last_updated":"2026-02-13","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"StepFun: Step 3.5 Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"stepfun/step-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.04,"input":0.2,"output":1.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":21.5,"coding_index":39.6,"intelligence_index":30.3},"design_arena":[{"arena":"models","category":"3d","elo":1176,"rank":55,"win_rate":41.7},{"arena":"models","category":"asciiart","elo":1193,"rank":24,"win_rate":46.5},{"arena":"models","category":"codecategories","elo":1203,"rank":49,"win_rate":44.6},{"arena":"models","category":"dataviz","elo":1199,"rank":49,"win_rate":45.5},{"arena":"models","category":"gamedev","elo":1203,"rank":47,"win_rate":41.9},{"arena":"models","category":"svg","elo":1116,"rank":53,"win_rate":38.7},{"arena":"models","category":"uicomponent","elo":1204,"rank":46,"win_rate":43.6},{"arena":"models","category":"website","elo":1212,"rank":47,"win_rate":46}]},"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","expiration_date":null,"hugging_face_id":"stepfun-ai/Step-3.7-Flash","knowledge_cutoff":null,"links":{"details":"/api/v1/models/stepfun/step-3.7-flash-20260528/endpoints"},"llmfit":{"architecture":"step3p7","context_length":524288,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Step-3.7-Flash-GGUF"},{"provider":"bartowski","repo":"bartowski/Step-3.7-Flash-GGUF"}],"hf_downloads":143509,"hf_likes":0,"matched_hugging_face_id":"stepfun-ai/Step-3.7-Flash","memory":{"min_ram_gb":112.5,"min_vram_gb":103.1,"recommended_ram_gb":187.5},"model_id":"stepfun-ai/Step-3.7-Flash","parameter_count":"201.4B","parameters_raw":201365316160,"pipeline_tag":"image-text-to-text","provider":"stepfun-ai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_effort":"medium","mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"stepfun/step-3.7-flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"StepFun: Step 3.7 Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"tencent/hunyuan-a13b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.14,"output":0.57},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","expiration_date":null,"family":"hunyuan","hugging_face_id":"tencent/Hunyuan-A13B-Instruct","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/tencent/hunyuan-a13b-instruct/endpoints"},"llmfit":{"architecture":"hunyuan_v1_moe","context_length":32768,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/Hunyuan-A13B-Instruct-GGUF"},{"provider":"mradermacher","repo":"mradermacher/Hunyuan-A13B-Instruct-GGUF"}],"hf_downloads":50454,"hf_likes":796,"matched_hugging_face_id":"tencent/Hunyuan-A13B-Instruct","memory":{"min_ram_gb":44.9,"min_vram_gb":41.2,"recommended_ram_gb":74.9},"model_id":"tencent/Hunyuan-A13B-Instruct","parameter_count":"80.4B","parameters_raw":80393183232,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","release_date":"2025-06-25","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"tencent/hunyuan-a13b-instruct","knowledge":"2025-03-31","last_updated":"2025-07-08","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Tencent: Hunyuan A13B Instruct","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-08","retired":false,"tags":null},"tencent/hy3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.033,"input":0.132,"output":0.528},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1231,"rank":37,"win_rate":43.8},{"arena":"models","category":"codecategories","elo":1206,"rank":46,"win_rate":41.1},{"arena":"models","category":"dataviz","elo":1154,"rank":67,"win_rate":36.1},{"arena":"models","category":"gamedev","elo":1190,"rank":54,"win_rate":38.6},{"arena":"models","category":"uicomponent","elo":1197,"rank":52,"win_rate":40.2},{"arena":"models","category":"website","elo":1206,"rank":53,"win_rate":41.4}]},"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","expiration_date":null,"family":"Hy","hugging_face_id":"tencent/Hy3","knowledge_cutoff":null,"links":{"details":"/api/v1/models/tencent/hy3-20260706/endpoints"},"llmfit":{"architecture":"hy_v3","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":23137,"hf_likes":0,"matched_hugging_face_id":"tencent/Hy3","memory":{"min_ram_gb":167.0,"min_vram_gb":153.0,"recommended_ram_gb":278.3},"model_id":"tencent/Hy3","moe":{"active_experts":8,"active_parameters":26766259780,"is_moe":true,"num_experts":192},"parameter_count":"298.8B","parameters_raw":298786155776,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["high","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"tencent/hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Tencent: Hy3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"tencent/hy3-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.021,"input":0.063,"output":0.21},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":30.7,"coding_index":58.8,"intelligence_index":41.2},"design_arena":[]},"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","expiration_date":null,"family":"Hy","hugging_face_id":"tencent/Hy3-preview","knowledge_cutoff":null,"links":{"details":"/api/v1/models/tencent/hy3-preview-20260421/endpoints"},"llmfit":{"architecture":"hy_v3","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":64911,"hf_likes":300,"matched_hugging_face_id":"tencent/Hy3-preview","memory":{"min_ram_gb":167.0,"min_vram_gb":153.0,"recommended_ram_gb":278.3},"model_id":"tencent/Hy3-preview","moe":{"active_experts":8,"active_parameters":26766259780,"is_moe":true,"num_experts":192},"parameter_count":"298.8B","parameters_raw":298786155776,"pipeline_tag":"text-generation","provider":"tencent","quantization":"Q4_K_M","release_date":"2026-04-13","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["high","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"tencent/hy3-preview","knowledge":null,"last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Tencent: Hy3 preview","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"thedrummer/cydonia-24b-v4.1":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"cache_read":0.15,"input":0.3,"output":0.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"thedrummer/cydonia-24b-v4.1","knowledge_cutoff":"2024-04-30","links":{"details":"/api/v1/models/thedrummer/cydonia-24b-v4.1/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"thedrummer/cydonia-24b-v4.1","knowledge":"2024-04-30","last_updated":"2025-09-27","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: Cydonia 24B V4.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-27","retired":false,"tags":null},"thedrummer/rocinante-12b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.25,"output":0.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"TheDrummer/Rocinante-12B-v1.1","knowledge_cutoff":"2024-04-30","links":{"details":"/api/v1/models/thedrummer/rocinante-12b/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"thedrummer/rocinante-12b","knowledge":"2024-04-30","last_updated":"2024-09-30","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: Rocinante 12B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-09-30","retired":false,"tags":null},"thedrummer/skyfall-36b-v2":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"cache_read":0.25,"input":0.55,"output":0.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"TheDrummer/Skyfall-36B-v2","knowledge_cutoff":"2024-06-30","links":{"details":"/api/v1/models/thedrummer/skyfall-36b-v2/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"thedrummer/skyfall-36b-v2","knowledge":"2024-06-30","last_updated":"2025-03-10","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: Skyfall 36B V2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-03-10","retired":false,"tags":null},"thedrummer/unslopnemo-12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.4,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"TheDrummer/UnslopNemo-12B-v4.1","knowledge_cutoff":"2024-04-30","links":{"details":"/api/v1/models/thedrummer/unslopnemo-12b/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"thedrummer/unslopnemo-12b","knowledge":"2024-04-30","last_updated":"2024-11-08","lifecycle":null,"limits":{"context":1024000,"output":1024000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"TheDrummer: UnslopNemo 12B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2024-11-08","retired":false,"tags":null},"thenlper/gte-base":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":768,"max_dimensions":768,"min_dimensions":768},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.005,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"thenlper/gte-base","knowledge_cutoff":null,"links":{"details":"/api/v1/models/thenlper/gte-base-20251117/endpoints"},"supported_voices":null},"family":null,"id":"thenlper/gte-base","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Thenlper: GTE-Base","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"thenlper/gte-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":{"default_dimensions":1024,"max_dimensions":1024,"min_dimensions":1024},"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.01,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":"thenlper/gte-large","knowledge_cutoff":null,"links":{"details":"/api/v1/models/thenlper/gte-large-20251117/endpoints"},"supported_voices":null},"family":null,"id":"thenlper/gte-large","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"Thenlper: GTE-Large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"thinkingmachines/inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.17,"input":1.0,"output":4.05},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":32.3,"coding_index":52.1,"intelligence_index":40.7},"design_arena":[{"arena":"models","category":"3d","elo":1164,"rank":59,"win_rate":36},{"arena":"models","category":"codecategories","elo":1218,"rank":41,"win_rate":43},{"arena":"models","category":"dataviz","elo":1186,"rank":56,"win_rate":41.8},{"arena":"models","category":"website","elo":1230,"rank":39,"win_rate":44.9}]},"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"ling","hugging_face_id":"thinkingmachines/Inkling","knowledge_cutoff":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-20260715/endpoints"},"llmfit":{"architecture":"inkling_mm_model","context_length":4096,"discovered":true,"gguf_sources":[],"hf_downloads":65012,"hf_likes":0,"matched_hugging_face_id":"thinkingmachines/Inkling","memory":{"min_ram_gb":532.2,"min_vram_gb":487.8,"recommended_ram_gb":887.0},"model_id":"thinkingmachines/Inkling","moe":{"active_experts":6,"active_parameters":68824164203,"is_moe":true,"num_experts":256},"parameter_count":"952.4B","parameters_raw":952377623626,"pipeline_tag":"image-text-to-text","provider":"thinkingmachines","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["max","high","medium","low","minimal","none"]},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"thinkingmachines/inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Thinking Machines: Inkling","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-17","retired":false,"tags":null},"thinkingmachines/inkling-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":30.8,"coding_index":52.9,"intelligence_index":40.2},"design_arena":[]},"description":"Multimodal reasoning model for visual analysis, planning, and tool use","expiration_date":null,"family":"ling","hugging_face_id":"thinkingmachines/Inkling-Small","knowledge_cutoff":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-small-20260730/endpoints"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["max","high","medium","low","minimal","none"]},"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"thinkingmachines/inkling-small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":524288,"output":262144},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Thinking Machines: Inkling Small","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"undi95/remm-slerp-l2-13b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.45,"output":0.65},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","expiration_date":null,"hugging_face_id":"Undi95/ReMM-SLERP-L2-13B","knowledge_cutoff":"2023-06-30","links":{"details":"/api/v1/models/undi95/remm-slerp-l2-13b/endpoints"},"open_weights":true,"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"undi95/remm-slerp-l2-13b","knowledge":"2023-06-30","last_updated":"2023-07-22","lifecycle":null,"limits":{"context":6144,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ReMM SLERP 13B","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2023-07-22","retired":false,"tags":null},"upstage/solar-pro-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":2.7,"coding_index":16.2,"intelligence_index":14.1},"design_arena":[]},"description":"Flagship model for demanding analysis, coding, and production agent workflows","expiration_date":null,"family":"solar-pro","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/upstage/solar-pro-3/endpoints"},"open_weights":false,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"upstage/solar-pro-3","knowledge":null,"last_updated":"2026-01-27","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Upstage: Solar Pro 3","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"voyageai/rerank-2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/voyageai/rerank-2.5-20260727/endpoints"},"supported_voices":null},"family":null,"id":"voyageai/rerank-2.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["rerank"]},"model":null,"name":"VoyageAI by MongoDB: rerank-2.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"voyageai/rerank-2.5-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/voyageai/rerank-2.5-lite-20260727/endpoints"},"supported_voices":null},"family":null,"id":"voyageai/rerank-2.5-lite","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["rerank"]},"model":null,"name":"VoyageAI by MongoDB: rerank-2.5-lite","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"voyageai/voyage-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":true,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.06,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/voyageai/voyage-4-20260727/endpoints"},"supported_voices":null},"family":null,"id":"voyageai/voyage-4","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"VoyageAI by MongoDB: voyage-4","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"voyageai/voyage-4-large":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":true,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.12,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/voyageai/voyage-4-large-20260727/endpoints"},"supported_voices":null},"family":null,"id":"voyageai/voyage-4-large","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"VoyageAI by MongoDB: voyage-4-large","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"voyageai/voyage-4-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":true,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.02,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/voyageai/voyage-4-lite-20260727/endpoints"},"supported_voices":null},"family":null,"id":"voyageai/voyage-4-lite","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["embeddings"]},"model":null,"name":"VoyageAI by MongoDB: voyage-4-lite","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"voyageai/voyage-multimodal-3.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":true,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"input":0.12,"output":0.0},"deprecated":false,"execution":{"embed":{"family":"openai_embeddings","path":"/embeddings","supported":true,"wire_protocol":"openai_embeddings"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/voyageai/voyage-multimodal-3.5-20260727/endpoints"},"supported_voices":null},"family":null,"id":"voyageai/voyage-multimodal-3.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text","image"],"output":["embeddings"]},"model":null,"name":"VoyageAI by MongoDB: voyage-multimodal-3.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"writer/palmyra-x5":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.6,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","expiration_date":null,"family":"palmyra","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/writer/palmyra-x5-20250428/endpoints"},"open_weights":false,"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"writer/palmyra-x5","knowledge":null,"last_updated":"2026-01-21","lifecycle":null,"limits":{"context":1040000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Writer: Palmyra X5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-21","retired":false,"tags":null},"x-ai/grok-4.20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1082,"rank":29,"win_rate":35.1},{"arena":"agents","category":"fullstack","elo":1094,"rank":23,"win_rate":41.1},{"arena":"agents","category":"godotgamedev","elo":1089,"rank":26,"win_rate":38.5},{"arena":"agents","category":"htmlslides","elo":1183,"rank":15,"win_rate":45.7},{"arena":"agents","category":"mobileapps","elo":1150,"rank":26,"win_rate":45.4},{"arena":"agents","category":"webapps","elo":1192,"rank":19,"win_rate":49.6},{"arena":"models","category":"3d","elo":1246,"rank":34,"win_rate":52.9},{"arena":"models","category":"asciiart","elo":1213,"rank":18,"win_rate":48.5},{"arena":"models","category":"codecategories","elo":1248,"rank":33,"win_rate":53.5},{"arena":"models","category":"dataviz","elo":1240,"rank":34,"win_rate":52.7},{"arena":"models","category":"gamedev","elo":1249,"rank":33,"win_rate":53.3},{"arena":"models","category":"svg","elo":1210,"rank":26,"win_rate":53.5},{"arena":"models","category":"uicomponent","elo":1238,"rank":36,"win_rate":51.2},{"arena":"models","category":"website","elo":1251,"rank":32,"win_rate":53.5}]},"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","expiration_date":null,"family":"grok","hugging_face_id":"","knowledge_cutoff":"2025-09-01","links":{"details":"/api/v1/models/x-ai/grok-4.20-20260309/endpoints"},"open_weights":false,"reasoning":{"default_enabled":false,"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"x-ai/grok-4.20","knowledge":"2025-09-01","last_updated":"2026-03-31","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"SpaceXAI: Grok 4.20","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-31","retired":false,"tags":null},"x-ai/grok-4.20-multi-agent":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","expiration_date":null,"family":"grok","hugging_face_id":"","knowledge_cutoff":"2025-09-01","links":{"details":"/api/v1/models/x-ai/grok-4.20-multi-agent-20260309/endpoints"},"open_weights":false,"reasoning":{"default_effort":"medium","default_enabled":true,"mandatory":true,"supported_efforts":["xhigh","high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"x-ai/grok-4.20-multi-agent","knowledge":"2025-09-01","last_updated":"2026-03-31","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"SpaceXAI: Grok 4.20 Multi-Agent","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-31","retired":false,"tags":null},"x-ai/grok-4.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":24.1,"coding_index":42.2,"intelligence_index":37.6},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1011,"rank":19,"win_rate":28},{"arena":"agents","category":"agentichtmlslides","elo":1066,"rank":10,"win_rate":31.8},{"arena":"agents","category":"agenticslides","elo":1072,"rank":10,"win_rate":31.9},{"arena":"agents","category":"agenticslides(html)","elo":1066,"rank":10,"win_rate":31.7},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1068,"rank":10,"win_rate":32.4},{"arena":"agents","category":"androidnative","elo":989,"rank":31,"win_rate":22},{"arena":"agents","category":"fullstack","elo":1046,"rank":30,"win_rate":30.1},{"arena":"agents","category":"godotgamedev","elo":1035,"rank":29,"win_rate":31.2},{"arena":"agents","category":"htmlslides","elo":1046,"rank":20,"win_rate":29.2},{"arena":"agents","category":"mobileapps","elo":1115,"rank":30,"win_rate":37.3},{"arena":"agents","category":"pptxslides","elo":1071,"rank":9,"win_rate":32.5},{"arena":"agents","category":"python-pptxslides","elo":1072,"rank":18,"win_rate":30.8},{"arena":"agents","category":"webapps","elo":1177,"rank":21,"win_rate":45.4},{"arena":"models","category":"3d","elo":1179,"rank":52,"win_rate":43.4},{"arena":"models","category":"asciiart","elo":1178,"rank":35,"win_rate":46.3},{"arena":"models","category":"codecategories","elo":1215,"rank":42,"win_rate":47.1},{"arena":"models","category":"dataviz","elo":1211,"rank":43,"win_rate":46.9},{"arena":"models","category":"gamedev","elo":1229,"rank":39,"win_rate":49},{"arena":"models","category":"svg","elo":1130,"rank":49,"win_rate":41},{"arena":"models","category":"uicomponent","elo":1227,"rank":38,"win_rate":47.4},{"arena":"models","category":"website","elo":1215,"rank":44,"win_rate":46.9}]},"description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","expiration_date":null,"family":"grok","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-4.3-20260430/endpoints"},"open_weights":false,"reasoning":{"default_effort":"low","default_enabled":true,"mandatory":false,"supported_efforts":["high","medium","low","none"]},"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"x-ai/grok-4.3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"SpaceXAI: Grok 4.3","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"x-ai/grok-4.5":{"aliases":["~x-ai/grok-latest"],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"input":2.0,"output":6.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":45.7,"coding_index":72.4,"intelligence_index":53.8},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1220,"rank":5,"win_rate":54.4},{"arena":"agents","category":"androidnative","elo":1269,"rank":3,"win_rate":64.3},{"arena":"agents","category":"fullstack","elo":1290,"rank":3,"win_rate":64.1},{"arena":"agents","category":"godotgamedev","elo":1271,"rank":2,"win_rate":62.1},{"arena":"agents","category":"htmlslides","elo":1231,"rank":5,"win_rate":56},{"arena":"agents","category":"mobileapps","elo":1272,"rank":3,"win_rate":61.6},{"arena":"agents","category":"python-pptxslides","elo":1232,"rank":8,"win_rate":54.5},{"arena":"agents","category":"webapps","elo":1259,"rank":9,"win_rate":53.3},{"arena":"models","category":"3d","elo":1314,"rank":11,"win_rate":50.2},{"arena":"models","category":"asciiart","elo":1299,"rank":6,"win_rate":58.2},{"arena":"models","category":"codecategories","elo":1312,"rank":8,"win_rate":53.3},{"arena":"models","category":"dataviz","elo":1311,"rank":10,"win_rate":54.4},{"arena":"models","category":"gamedev","elo":1333,"rank":7,"win_rate":53.3},{"arena":"models","category":"svg","elo":1273,"rank":6,"win_rate":52.5},{"arena":"models","category":"uicomponent","elo":1320,"rank":9,"win_rate":53.3},{"arena":"models","category":"website","elo":1319,"rank":7,"win_rate":56.9}]},"description":"xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk","expiration_date":null,"family":"grok","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-4.5-20260708/endpoints"},"open_weights":false,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":true,"supported_efforts":["high","medium","low"]},"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"x-ai/grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"SpaceXAI: Grok 4.5","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"x-ai/grok-build-0.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":1.0,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":28,"coding_index":51.5,"intelligence_index":39.8},"design_arena":[]},"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","expiration_date":null,"family":"grok-build","hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-build-0.1-20260520/endpoints"},"open_weights":false,"reasoning":{"mandatory":true},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"x-ai/grok-build-0.1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf","file"],"output":["text"]},"model":null,"name":"SpaceXAI: Grok Build 0.1","pricing":{"components":[{"id":"tool.web_search","kind":"tool","per":1,"rate":0.005,"tool":"web_search","unit":"call"}],"currency":"USD","merge":"merge_by_id"},"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-20","retired":false,"tags":null},"x-ai/grok-imagine-image-quality":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"image":1.0e4,"input":0.0,"output":0.0},"deprecated":false,"execution":{"image":{"family":"openai_images","path":"/images/generations","supported":true,"wire_protocol":"openai_images"}},"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-imagine-image-quality-20260512/endpoints"},"supported_voices":null},"family":null,"id":"x-ai/grok-imagine-image-quality","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":65536},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"SpaceXAI: Grok Imagine Image Quality","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-18","retired":false,"tags":null},"x-ai/grok-imagine-video":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-imagine-video-20260512/endpoints"},"supported_voices":null},"family":null,"id":"x-ai/grok-imagine-video","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"SpaceXAI: Grok Imagine Video","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-18","retired":false,"tags":null},"x-ai/grok-imagine-video-1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-imagine-video-1.5-20260719/endpoints"},"supported_voices":null},"family":null,"id":"x-ai/grok-imagine-video-1.5","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"SpaceXAI: Grok Imagine Video 1.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"x-ai/grok-stt-1.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.0e5,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-stt-20260723/endpoints"},"supported_voices":null},"family":null,"id":"x-ai/grok-stt-1.0","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["transcription"]},"model":null,"name":"SpaceXAI: Grok STT 1.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"x-ai/grok-voice-tts-1.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":15.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/x-ai/grok-voice-tts-1.0/endpoints"},"supported_voices":["eve","ara","rex","sal","leo"]},"family":null,"id":"x-ai/grok-voice-tts-1.0","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":15000},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"SpaceXAI: Grok Voice TTS 1.0","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-05-15","retired":false,"tags":null},"xiaomi/mimo-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0028,"input":0.14,"output":0.28},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"artificial_analysis":{"agentic_index":23.7,"coding_index":56.8,"intelligence_index":37.2},"design_arena":[{"arena":"models","category":"3d","elo":1271,"rank":26,"win_rate":51.9},{"arena":"models","category":"asciiart","elo":1176,"rank":38,"win_rate":46.3},{"arena":"models","category":"codecategories","elo":1290,"rank":18,"win_rate":55.3},{"arena":"models","category":"dataviz","elo":1280,"rank":18,"win_rate":55.4},{"arena":"models","category":"gamedev","elo":1293,"rank":19,"win_rate":56},{"arena":"models","category":"svg","elo":1218,"rank":24,"win_rate":52.6},{"arena":"models","category":"uicomponent","elo":1294,"rank":19,"win_rate":55.5},{"arena":"models","category":"website","elo":1293,"rank":19,"win_rate":55.6}]},"description":"Open MiMo model for multimodal coding agents and long-context automation","expiration_date":null,"family":"mimo","hugging_face_id":"XiaomiMiMo/MiMo-V2.5","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.5-20260422/endpoints"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":359231,"hf_likes":383,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5","memory":{"min_ram_gb":173.7,"min_vram_gb":159.2,"recommended_ram_gb":289.4},"model_id":"XiaomiMiMo/MiMo-V2.5","moe":{"active_experts":8,"active_parameters":24764886000,"is_moe":true,"num_experts":256},"parameter_count":"310.8B","parameters_raw":310775040000,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"xiaomi/mimo-v2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1050000,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Xiaomi: MiMo-V2.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"xiaomi/mimo-v2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0036,"input":0.435,"output":0.87},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":29.1,"coding_index":60.2,"intelligence_index":42.2},"design_arena":[{"arena":"models","category":"3d","elo":1305,"rank":16,"win_rate":56.7},{"arena":"models","category":"asciiart","elo":1184,"rank":33,"win_rate":47.7},{"arena":"models","category":"codecategories","elo":1304,"rank":13,"win_rate":56.4},{"arena":"models","category":"dataviz","elo":1297,"rank":13,"win_rate":54.8},{"arena":"models","category":"gamedev","elo":1326,"rank":9,"win_rate":58.8},{"arena":"models","category":"svg","elo":1225,"rank":21,"win_rate":52.3},{"arena":"models","category":"uicomponent","elo":1292,"rank":21,"win_rate":55.4},{"arena":"models","category":"website","elo":1300,"rank":10,"win_rate":55.7}]},"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","expiration_date":null,"family":"mimo","hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","interleaved":{"field":"reasoning_content"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.5-pro-20260422/endpoints"},"llmfit":{"architecture":"mimo_v2","context_length":1048576,"discovered":true,"gguf_sources":[{"provider":"bartowski","repo":"bartowski/MiMo-V2.5-Pro-GGUF"}],"hf_downloads":53020,"hf_likes":727,"matched_hugging_face_id":"XiaomiMiMo/MiMo-V2.5-Pro","memory":{"min_ram_gb":571.8,"min_vram_gb":524.1,"recommended_ram_gb":953.0},"model_id":"XiaomiMiMo/MiMo-V2.5-Pro","moe":{"active_experts":8,"active_parameters":71413954340,"is_moe":true,"num_experts":384},"parameter_count":"1023.2B","parameters_raw":1023244718976,"pipeline_tag":"text-generation","provider":"xiaomimimo","quantization":"Q4_K_M","release_date":"2026-04-27","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"xiaomi/mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1050000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Xiaomi: MiMo-V2.5-Pro","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"z-ai/glm-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1226,"rank":38,"win_rate":59.7},{"arena":"models","category":"codecategories","elo":1194,"rank":57,"win_rate":54.4},{"arena":"models","category":"dataviz","elo":1186,"rank":55,"win_rate":53.3},{"arena":"models","category":"gamedev","elo":1198,"rank":48,"win_rate":54.4},{"arena":"models","category":"svg","elo":1144,"rank":47,"win_rate":50.8},{"arena":"models","category":"uicomponent","elo":1179,"rank":58,"win_rate":55},{"arena":"models","category":"website","elo":1193,"rank":58,"win_rate":53.8}]},"description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","expiration_date":"2026-12-31","family":"glm","hugging_face_id":"zai-org/GLM-4.5","knowledge_cutoff":"2024-12-31","links":{"details":"/api/v1/models/z-ai/glm-4.5/endpoints"},"llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-GGUF"}],"hf_downloads":123213,"hf_likes":1408,"matched_hugging_face_id":"zai-org/GLM-4.5","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.5","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-4.5","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 4.5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"z-ai/glm-4.5-air":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.025,"input":0.13,"output":0.85},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1178,"rank":53,"win_rate":54.1},{"arena":"models","category":"codecategories","elo":1166,"rank":67,"win_rate":51.5},{"arena":"models","category":"dataviz","elo":1217,"rank":42,"win_rate":59.2},{"arena":"models","category":"gamedev","elo":1147,"rank":67,"win_rate":48.4},{"arena":"models","category":"svg","elo":1119,"rank":52,"win_rate":50.8},{"arena":"models","category":"uicomponent","elo":1159,"rank":63,"win_rate":54.5},{"arena":"models","category":"website","elo":1170,"rank":66,"win_rate":51.3}]},"description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","expiration_date":null,"family":"glm-air","hugging_face_id":"zai-org/GLM-4.5-Air","knowledge_cutoff":"2024-12-31","links":{"details":"/api/v1/models/z-ai/glm-4.5-air/endpoints"},"llmfit":{"architecture":"glm4_moe","context_length":131072,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.5-Air-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.5-Air-GGUF"}],"hf_downloads":441341,"hf_likes":625,"matched_hugging_face_id":"zai-org/GLM-4.5-Air","memory":{"min_ram_gb":61.7,"min_vram_gb":56.6,"recommended_ram_gb":102.9},"model_id":"zai-org/GLM-4.5-Air","moe":{"active_experts":8,"active_parameters":12082527713,"is_moe":true,"num_experts":128},"parameter_count":"110.5B","parameters_raw":110468824832,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-07-20","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-4.5-air","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131072,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 4.5 Air","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"z-ai/glm-4.5v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.11,"input":0.6,"output":1.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","expiration_date":null,"family":"glm","hugging_face_id":"zai-org/GLM-4.5V","knowledge_cutoff":"2024-12-31","links":{"details":"/api/v1/models/z-ai/glm-4.5v/endpoints"},"llmfit":{"architecture":"glm4v_moe","context_length":65536,"discovered":true,"gguf_sources":[{"provider":"ggml-org","repo":"ggml-org/GLM-4.5V-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.5V-GGUF"}],"hf_downloads":146121,"hf_likes":0,"matched_hugging_face_id":"zai-org/GLM-4.5V","memory":{"min_ram_gb":60.2,"min_vram_gb":55.2,"recommended_ram_gb":100.3},"model_id":"zai-org/GLM-4.5V","moe":{"active_experts":8,"active_parameters":11780883304,"is_moe":true,"num_experts":128},"parameter_count":"107.7B","parameters_raw":107710933120,"pipeline_tag":"image-text-to-text","provider":"zai-org","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[{"type":"toggle"}],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-4.5v","knowledge":"2025-04","last_updated":"2025-08-11","lifecycle":null,"limits":{"context":65536,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Z.ai: GLM 4.5V","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-08-11","retired":false,"tags":null},"z-ai/glm-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.5,"output":2.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":17.7,"coding_index":45.8,"intelligence_index":28.7},"design_arena":[{"arena":"agents","category":"androidnative","elo":1120,"rank":22,"win_rate":52.6},{"arena":"agents","category":"fullstack","elo":1073,"rank":28,"win_rate":42.3},{"arena":"agents","category":"godotgamedev","elo":1180,"rank":13,"win_rate":53.2},{"arena":"agents","category":"mobileapps","elo":1155,"rank":22,"win_rate":46.8},{"arena":"models","category":"3d","elo":1183,"rank":51,"win_rate":54},{"arena":"models","category":"codecategories","elo":1195,"rank":55,"win_rate":54.3},{"arena":"models","category":"dataviz","elo":1190,"rank":52,"win_rate":52.6},{"arena":"models","category":"gamedev","elo":1203,"rank":46,"win_rate":54.7},{"arena":"models","category":"svg","elo":1156,"rank":43,"win_rate":52.1},{"arena":"models","category":"uicomponent","elo":1194,"rank":54,"win_rate":53.9},{"arena":"models","category":"website","elo":1198,"rank":57,"win_rate":54.4}]},"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","expiration_date":null,"family":"glm","hugging_face_id":"zai-org/GLM-4.6","knowledge_cutoff":"2025-03-31","links":{"details":"/api/v1/models/z-ai/glm-4.6/endpoints"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.6-GGUF"}],"hf_downloads":26467,"hf_likes":1229,"matched_hugging_face_id":"zai-org/GLM-4.6","memory":{"min_ram_gb":199.4,"min_vram_gb":182.8,"recommended_ram_gb":332.3},"model_id":"zai-org/GLM-4.6","moe":{"active_experts":8,"active_parameters":34786625132,"is_moe":true,"num_experts":160},"parameter_count":"356.8B","parameters_raw":356785898816,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-09-29","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 4.6","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"z-ai/glm-4.6v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.055,"input":0.3,"output":0.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","expiration_date":null,"family":"glm","hugging_face_id":"zai-org/GLM-4.6V","knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-4.6-20251208/endpoints"},"open_weights":true,"reasoning":{"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-4.6v","knowledge":"2025-04","last_updated":"2025-12-08","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Z.ai: GLM 4.6V","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"z-ai/glm-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.08,"input":0.4,"output":1.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":25.4,"coding_index":45.3,"intelligence_index":33.7},"design_arena":[{"arena":"agents","category":"androidnative","elo":1148,"rank":21,"win_rate":56.1},{"arena":"agents","category":"fullstack","elo":1092,"rank":24,"win_rate":44.9},{"arena":"agents","category":"godotgamedev","elo":1058,"rank":28,"win_rate":35.8},{"arena":"agents","category":"mobileapps","elo":1168,"rank":21,"win_rate":49},{"arena":"models","category":"3d","elo":1246,"rank":33,"win_rate":54.3},{"arena":"models","category":"asciiart","elo":1202,"rank":22,"win_rate":48.1},{"arena":"models","category":"codecategories","elo":1246,"rank":34,"win_rate":54.8},{"arena":"models","category":"dataviz","elo":1222,"rank":41,"win_rate":51.2},{"arena":"models","category":"gamedev","elo":1241,"rank":35,"win_rate":55.2},{"arena":"models","category":"svg","elo":1190,"rank":34,"win_rate":54.3},{"arena":"models","category":"uicomponent","elo":1234,"rank":37,"win_rate":51},{"arena":"models","category":"website","elo":1249,"rank":34,"win_rate":55.3}]},"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","expiration_date":null,"family":"glm","hugging_face_id":"zai-org/GLM-4.7","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-4.7-20251222/endpoints"},"llmfit":{"architecture":"glm4_moe","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-4.7-GGUF"},{"provider":"mradermacher","repo":"mradermacher/GLM-4.7-GGUF"}],"hf_downloads":72466,"hf_likes":2051,"matched_hugging_face_id":"zai-org/GLM-4.7","memory":{"min_ram_gb":200.2,"min_vram_gb":183.6,"recommended_ram_gb":333.7},"model_id":"zai-org/GLM-4.7","moe":{"active_experts":8,"active_parameters":34937934644,"is_moe":true,"num_experts":160},"parameter_count":"358.3B","parameters_raw":358337791296,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2025-12-22","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 4.7","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"z-ai/glm-4.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.01,"input":0.06,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1176,"rank":54,"win_rate":51.2},{"arena":"models","category":"codecategories","elo":1206,"rank":45,"win_rate":53.1},{"arena":"models","category":"dataviz","elo":1150,"rank":72,"win_rate":45.3},{"arena":"models","category":"gamedev","elo":1187,"rank":55,"win_rate":49.7},{"arena":"models","category":"svg","elo":1085,"rank":57,"win_rate":44.2},{"arena":"models","category":"uicomponent","elo":1243,"rank":35,"win_rate":57.6},{"arena":"models","category":"website","elo":1217,"rank":43,"win_rate":54}]},"description":"Budget GLM lane for fast coding help, routing, and everyday automation","expiration_date":null,"family":"glm-flash","hugging_face_id":"zai-org/GLM-4.7-Flash","interleaved":{"field":"reasoning_details"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-4.7-flash-20260119/endpoints"},"llmfit":{"architecture":"glm4_moe_lite","context_length":202752,"discovered":true,"gguf_sources":[],"hf_downloads":2074814,"hf_likes":1800,"matched_hugging_face_id":"zai-org/GLM-4.7-Flash","memory":{"min_ram_gb":17.4,"min_vram_gb":16.0,"recommended_ram_gb":29.1},"model_id":"zai-org/GLM-4.7-Flash","moe":{"active_experts":4,"active_parameters":3414850312,"is_moe":true,"num_experts":64},"parameter_count":"31.2B","parameters_raw":31221488576,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-01-19","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":202752,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 4.7 Flash","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"z-ai/glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.2,"input":0.95,"output":2.55},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"agents","category":"androidnative","elo":1183,"rank":17,"win_rate":55.4},{"arena":"agents","category":"fullstack","elo":1164,"rank":17,"win_rate":51.7},{"arena":"agents","category":"godotgamedev","elo":1144,"rank":16,"win_rate":46.7},{"arena":"agents","category":"htmlslides","elo":1171,"rank":17,"win_rate":45.5},{"arena":"agents","category":"mobileapps","elo":1197,"rank":17,"win_rate":51.7},{"arena":"models","category":"3d","elo":1285,"rank":23,"win_rate":56.3},{"arena":"models","category":"asciiart","elo":1185,"rank":32,"win_rate":48},{"arena":"models","category":"codecategories","elo":1276,"rank":23,"win_rate":55.5},{"arena":"models","category":"dataviz","elo":1256,"rank":29,"win_rate":53},{"arena":"models","category":"gamedev","elo":1287,"rank":21,"win_rate":57.4},{"arena":"models","category":"svg","elo":1215,"rank":25,"win_rate":54.4},{"arena":"models","category":"uicomponent","elo":1266,"rank":29,"win_rate":53.6},{"arena":"models","category":"website","elo":1272,"rank":25,"win_rate":55}]},"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","expiration_date":null,"family":"glm","hugging_face_id":"zai-org/GLM-5","interleaved":{"field":"reasoning_content"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-5-20260211/endpoints"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5-GGUF"}],"hf_downloads":155600,"hf_likes":2119,"matched_hugging_face_id":"zai-org/GLM-5","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5","moe":{"active_experts":8,"active_parameters":40000000000,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-02-11","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 5","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"z-ai/glm-5-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.24,"input":1.2,"output":4.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"design_arena":[{"arena":"models","category":"3d","elo":1306,"rank":13,"win_rate":58.4},{"arena":"models","category":"asciiart","elo":1188,"rank":29,"win_rate":50},{"arena":"models","category":"codecategories","elo":1297,"rank":16,"win_rate":56.4},{"arena":"models","category":"dataviz","elo":1289,"rank":15,"win_rate":57.2},{"arena":"models","category":"gamedev","elo":1308,"rank":14,"win_rate":57.4},{"arena":"models","category":"svg","elo":1255,"rank":12,"win_rate":57},{"arena":"models","category":"uicomponent","elo":1300,"rank":16,"win_rate":57.4},{"arena":"models","category":"website","elo":1294,"rank":18,"win_rate":55.6}]},"description":"Faster GLM-5 lane for coding agents that need lower latency","expiration_date":"2098-12-31","family":"glm","hugging_face_id":"","interleaved":{"field":"reasoning_content"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-5-turbo-20260315/endpoints"},"open_weights":false,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-5-turbo","knowledge":null,"last_updated":"2026-03-16","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 5 Turbo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"z-ai/glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1794,"input":0.966,"output":3.036},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":29.9,"coding_index":55.8,"intelligence_index":40.2},"design_arena":[{"arena":"models","category":"3d","elo":1336,"rank":5,"win_rate":62.6},{"arena":"models","category":"asciiart","elo":1188,"rank":27,"win_rate":47.8},{"arena":"models","category":"codecategories","elo":1303,"rank":14,"win_rate":56.7},{"arena":"models","category":"dataviz","elo":1366,"rank":3,"win_rate":67},{"arena":"models","category":"gamedev","elo":1316,"rank":12,"win_rate":58.8},{"arena":"models","category":"svg","elo":1268,"rank":8,"win_rate":59.4},{"arena":"models","category":"uicomponent","elo":1309,"rank":12,"win_rate":56},{"arena":"models","category":"website","elo":1296,"rank":15,"win_rate":55.4},{"arena":"agents","category":"agenticgamedev","elo":1177,"rank":14,"win_rate":50.8},{"arena":"agents","category":"agentichtmlslides","elo":1205,"rank":6,"win_rate":52},{"arena":"agents","category":"agenticslides","elo":1245,"rank":3,"win_rate":54.4},{"arena":"agents","category":"agenticslides(html)","elo":1204,"rank":6,"win_rate":51.8},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1240,"rank":4,"win_rate":53.3},{"arena":"agents","category":"androidnative","elo":1219,"rank":10,"win_rate":54},{"arena":"agents","category":"fullstack","elo":1209,"rank":13,"win_rate":56.2},{"arena":"agents","category":"godotgamedev","elo":1104,"rank":25,"win_rate":39.5},{"arena":"agents","category":"htmlslides","elo":1203,"rank":12,"win_rate":51.4},{"arena":"agents","category":"mobileapps","elo":1219,"rank":11,"win_rate":54.8},{"arena":"agents","category":"pptxslides","elo":1241,"rank":4,"win_rate":53.5},{"arena":"agents","category":"python-pptxslides","elo":1258,"rank":5,"win_rate":54.2},{"arena":"agents","category":"webapps","elo":1225,"rank":17,"win_rate":53.8}]},"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","expiration_date":null,"family":"glm","hugging_face_id":"zai-org/GLM-5.1","interleaved":{"field":"reasoning_content"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-5.1-20260406/endpoints"},"llmfit":{"architecture":"glm_moe_dsa","context_length":202752,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/GLM-5.1-GGUF"}],"hf_downloads":76699,"hf_likes":1840,"matched_hugging_face_id":"zai-org/GLM-5.1","memory":{"min_ram_gb":421.3,"min_vram_gb":386.1,"recommended_ram_gb":702.1},"model_id":"zai-org/GLM-5.1","moe":{"active_experts":8,"active_parameters":60073548574,"is_moe":true,"num_experts":256},"parameter_count":"753.9B","parameters_raw":753864139008,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-04-03","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":204800,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 5.1","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"z-ai/glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.14,"input":0.76,"output":2.42},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"benchmarks":{"artificial_analysis":{"agentic_index":43.1,"coding_index":68.8,"intelligence_index":51.1},"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1187,"rank":11,"win_rate":48.6},{"arena":"agents","category":"androidnative","elo":1215,"rank":11,"win_rate":56},{"arena":"agents","category":"fullstack","elo":1276,"rank":5,"win_rate":64},{"arena":"agents","category":"godotgamedev","elo":1142,"rank":17,"win_rate":40.1},{"arena":"agents","category":"htmlslides","elo":1206,"rank":10,"win_rate":51.6},{"arena":"agents","category":"mobileapps","elo":1222,"rank":10,"win_rate":54.2},{"arena":"agents","category":"python-pptxslides","elo":1191,"rank":10,"win_rate":48.5},{"arena":"agents","category":"webapps","elo":1268,"rank":7,"win_rate":57.1},{"arena":"models","category":"3d","elo":1365,"rank":4,"win_rate":59.7},{"arena":"models","category":"asciiart","elo":1242,"rank":15,"win_rate":50.2},{"arena":"models","category":"codecategories","elo":1343,"rank":4,"win_rate":59.8},{"arena":"models","category":"dataviz","elo":1324,"rank":6,"win_rate":57},{"arena":"models","category":"gamedev","elo":1347,"rank":4,"win_rate":59},{"arena":"models","category":"svg","elo":1259,"rank":11,"win_rate":55.2},{"arena":"models","category":"uicomponent","elo":1337,"rank":6,"win_rate":58},{"arena":"models","category":"website","elo":1339,"rank":3,"win_rate":60.4}]},"description":"Open flagship GLM for long-horizon coding agents and million-token context work","expiration_date":null,"family":"glm","hugging_face_id":"zai-org/GLM-5.2","interleaved":{"field":"reasoning_content"},"knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-5.2-20260616/endpoints"},"llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning":{"default_effort":"high","default_enabled":true,"mandatory":false,"supported_efforts":["xhigh","high"]},"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Z.ai: GLM 5.2","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null},"z-ai/glm-5v-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.24,"input":1.2,"output":4.0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"benchmarks":{"design_arena":[{"arena":"agents","category":"agenticgamedev","elo":1108,"rank":18,"win_rate":41.5},{"arena":"agents","category":"agentichtmlslides","elo":1134,"rank":8,"win_rate":41.7},{"arena":"agents","category":"agenticslides","elo":1171,"rank":6,"win_rate":51.6},{"arena":"agents","category":"agenticslides(html)","elo":1137,"rank":8,"win_rate":41.8},{"arena":"agents","category":"agenticslides(python-pptx)","elo":1183,"rank":6,"win_rate":53.9},{"arena":"agents","category":"androidnative","elo":1267,"rank":4,"win_rate":54.8},{"arena":"agents","category":"fullstack","elo":1190,"rank":16,"win_rate":52.3},{"arena":"agents","category":"godotgamedev","elo":995,"rank":30,"win_rate":26.9},{"arena":"agents","category":"htmlslides","elo":1152,"rank":18,"win_rate":44.5},{"arena":"agents","category":"mobileapps","elo":1192,"rank":19,"win_rate":50.4},{"arena":"agents","category":"pptxslides","elo":1164,"rank":6,"win_rate":52.1},{"arena":"agents","category":"python-pptxslides","elo":1165,"rank":13,"win_rate":51.9},{"arena":"agents","category":"webapps","elo":1172,"rank":23,"win_rate":44.7},{"arena":"models","category":"3d","elo":1266,"rank":28,"win_rate":54.2},{"arena":"models","category":"asciiart","elo":1136,"rank":47,"win_rate":42.2},{"arena":"models","category":"codecategories","elo":1258,"rank":32,"win_rate":51.8},{"arena":"models","category":"dataviz","elo":1224,"rank":39,"win_rate":48.1},{"arena":"models","category":"gamedev","elo":1272,"rank":24,"win_rate":54},{"arena":"models","category":"svg","elo":1198,"rank":31,"win_rate":51},{"arena":"models","category":"uicomponent","elo":1248,"rank":33,"win_rate":50.5},{"arena":"models","category":"website","elo":1254,"rank":31,"win_rate":50.5}]},"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","expiration_date":"2098-12-31","family":"glm","hugging_face_id":"","knowledge_cutoff":null,"links":{"details":"/api/v1/models/z-ai/glm-5v-turbo-20260401/endpoints"},"open_weights":false,"reasoning":{"default_enabled":true,"mandatory":false},"reasoning_options":[],"structured_output":false,"supported_voices":null,"temperature":true},"family":null,"id":"z-ai/glm-5v-turbo","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"Z.ai: GLM 5V Turbo","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"zyphra/zonos-v0.1-hybrid":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":7.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/zyphra/zonos-v0.1-hybrid/endpoints"},"supported_voices":["american_female","american_male","british_female","british_male","random"]},"family":null,"id":"zyphra/zonos-v0.1-hybrid","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Zyphra: Zonos v0.1 Hybrid","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"zyphra/zonos-v0.1-transformer":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":7.0,"output":0.0},"deprecated":false,"extra":{"expiration_date":null,"hugging_face_id":null,"knowledge_cutoff":null,"links":{"details":"/api/v1/models/zyphra/zonos-v0.1-transformer/endpoints"},"supported_voices":["american_female","american_male","british_female","british_male","random"]},"family":null,"id":"zyphra/zonos-v0.1-transformer","knowledge":null,"last_updated":null,"lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text"],"output":["speech"]},"model":null,"name":"Zyphra: Zonos v0.1 Transformer","pricing":null,"provider":"openrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null}},"name":"OpenRouter","pricing_defaults":null,"runtime":{"auth":{"env":["OPENROUTER_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://openrouter.ai/api/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://openrouter.ai/docs"}};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;