{"object":"list","data":[{"id":"anyrouter/hermes","object":"model","canonical_slug":"anyrouter/hermes","owned_by":"anyrouter","hugging_face_id":null,"name":"AnyRouter Hermes","display_name":"AnyRouter Hermes","provider":"anyrouter","providers":["AnyRouter"],"category":"text","capabilities":["chat","streaming","function-calling","coding"],"created":1780876800,"description":"Auto-routes across the top tool-calling models for autonomous agents like Nous Research's Hermes — one best model per upstream provider, ranked by agentic score, with automatic fallback. No BYOK required: billed to your AnyRouter credits at each underlying model's rate.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Anyrouter","instruct_type":null},"pricing":{"prompt":"0.042448","completion":"0.084896","input_per_1m":0.042448,"output_per_1m":0.084896},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anyrouter/hermes","metrics":"/api/v1/models/anyrouter%2Fhermes/metrics"},"per_upstream":[{"backend":"freebuff","model_name":"deepseek/deepseek-v4-flash","llm_provider":"freebuff","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"antigravity","model_name":"google/gemini-2.5-flash","llm_provider":"antigravity","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576,"max_completion_tokens":65536},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"kilo","model_name":"stealth/glyph-cluster","llm_provider":"kilo","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":256000,"max_completion_tokens":256000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}],"members":[{"id":"thinkingmachines/inkling","name":"Inkling","owner":"thinkingmachines","release_date":"2026-07-15","position":1},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","owner":"qwen","release_date":"2026-03-12","position":2},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek-V4-Flash","owner":"deepseek","release_date":"2026-07-08","position":3},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","owner":"google","release_date":"2026-02-01","position":4},{"id":"dots-studio/dots-3-note-preview","name":"Dots3-Note Preview","owner":"dots-studio","release_date":"2026-08-14","position":5},{"id":"inclusionai/ling-3.1-flash","name":"Ling-3.1-flash","owner":"inclusionai","release_date":"2026-10-02","position":6},{"id":"stealth/glyph-cluster","name":"Glyph Cluster","owner":"stealth","release_date":"2026-10-07","position":7},{"id":"z-ai/glm-5.3","name":"GLM-5.3","owner":"z-ai","release_date":"2026-08-14","position":8}]},{"id":"anyrouter/cowork","object":"model","canonical_slug":"anyrouter/cowork","owned_by":"anyrouter","hugging_face_id":null,"name":"AnyRouter Cowork","display_name":"AnyRouter Cowork","provider":"anyrouter","providers":["AnyRouter"],"category":"text","capabilities":["chat","streaming","function-calling","vision"],"created":1780876800,"description":"Routes across the best tool-calling models for everyday assistant work — one per provider, with automatic fallback. No setup required: billed to your AnyRouter credits at each underlying model's rate.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Anyrouter","instruct_type":null},"pricing":{"prompt":"0.042448","completion":"0.084896","input_per_1m":0.042448,"output_per_1m":0.084896},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anyrouter/cowork","metrics":"/api/v1/models/anyrouter%2Fcowork/metrics"},"per_upstream":[{"backend":"freebuff","model_name":"deepseek/deepseek-v4-flash","llm_provider":"freebuff","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"antigravity","model_name":"google/gemini-2.5-flash","llm_provider":"antigravity","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576,"max_completion_tokens":65536},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"kilo","model_name":"stealth/glyph-cluster","llm_provider":"kilo","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":256000,"max_completion_tokens":256000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}],"members":[{"id":"thinkingmachines/inkling","name":"Inkling","owner":"thinkingmachines","release_date":"2026-07-15","position":1},{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","owner":"qwen","release_date":"2026-03-12","position":2},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek-V4-Flash","owner":"deepseek","release_date":"2026-07-08","position":3},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","owner":"google","release_date":"2026-02-01","position":4},{"id":"dots-studio/dots-3-note-preview","name":"Dots3-Note Preview","owner":"dots-studio","release_date":"2026-08-14","position":5},{"id":"inclusionai/ling-3.1-flash","name":"Ling-3.1-flash","owner":"inclusionai","release_date":"2026-10-02","position":6},{"id":"stealth/glyph-cluster","name":"Glyph Cluster","owner":"stealth","release_date":"2026-10-07","position":7},{"id":"z-ai/glm-5.3","name":"GLM-5.3","owner":"z-ai","release_date":"2026-08-14","position":8}]},{"id":"anyrouter/free","object":"model","canonical_slug":"anyrouter/free","owned_by":"anyrouter","hugging_face_id":null,"name":"AnyRouter Free","display_name":"AnyRouter Free","provider":"anyrouter","providers":["AnyRouter"],"category":"text","capabilities":["chat","streaming","function-calling"],"created":1780876800,"description":"Curated $0 platform models plus the donated free pool (`:free` aggregator keys). Never paid pool, never credits. No daily request limit.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Anyrouter","instruct_type":null},"pricing":{"prompt":"0.042448","completion":"0.084896","input_per_1m":0.042448,"output_per_1m":0.084896},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort","stop"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anyrouter/free","metrics":"/api/v1/models/anyrouter%2Ffree/metrics"},"per_upstream":[{"backend":"anyrouter","model_name":"foundation-model","llm_provider":"anyrouter","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":true},"features":{"streaming":true}},{"backend":"freebuff","model_name":"deepseek/deepseek-v4-flash","llm_provider":"freebuff","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"antigravity","model_name":"google/gemini-2.5-flash","llm_provider":"antigravity","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576,"max_completion_tokens":65536},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nvidia","model_name":"nvidia/nemotron-3-super-120b-a12b","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"pollinations","model_name":"openai-fast","llm_provider":"pollinations","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"kilo","model_name":"stealth/glyph-cluster","llm_provider":"kilo","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":256000,"max_completion_tokens":256000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}],"members":[{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron-3 Super 120B","owner":"nvidia","release_date":"2024-01-01","position":1},{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","owner":"poolside","release_date":"2026-07-21","position":2},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek-V4-Flash","owner":"deepseek","release_date":"2026-07-08","position":3},{"id":"liquid/lfm-2.5-2.6b","name":"LFM 2.5 2.6B","owner":"liquid","release_date":"2026-08-01","position":4},{"id":"google/gemma-4-31b","name":"Gemma 4 31B","owner":"google","release_date":"2026-06-03","position":5}]},{"id":"anyrouter/auto","object":"model","canonical_slug":"anyrouter/auto","owned_by":"anyrouter","hugging_face_id":null,"name":"AnyRouter Auto","display_name":"AnyRouter Auto","provider":"anyrouter","providers":["AnyRouter"],"category":"text","capabilities":["chat","streaming","function-calling","coding","vision"],"created":1780876800,"description":"Top usage + top stable platform models mixing free-tier and credit-billed routes, with health-aware fallback. Tools are optional — pass `tools` when you need them. Billed at each hop's rate ($0 on free hops).","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Anyrouter","instruct_type":null},"pricing":{"prompt":"0.042448","completion":"0.084896","input_per_1m":0.042448,"output_per_1m":0.084896},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort","stop"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anyrouter/auto","metrics":"/api/v1/models/anyrouter%2Fauto/metrics"},"per_upstream":[{"backend":"anyrouter","model_name":"foundation-model","llm_provider":"anyrouter","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":true},"features":{"streaming":true}},{"backend":"freebuff","model_name":"deepseek/deepseek-v4-flash","llm_provider":"freebuff","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"antigravity","model_name":"google/gemini-2.5-flash","llm_provider":"antigravity","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576,"max_completion_tokens":65536},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nvidia","model_name":"nvidia/nemotron-3-super-120b-a12b","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"pollinations","model_name":"openai-fast","llm_provider":"pollinations","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"kilo","model_name":"stealth/glyph-cluster","llm_provider":"kilo","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":256000,"max_completion_tokens":256000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}],"members":[{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron-3 Super 120B","owner":"nvidia","release_date":"2024-01-01","position":1},{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","owner":"poolside","release_date":"2026-07-21","position":2},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek-V4-Flash","owner":"deepseek","release_date":"2026-07-08","position":3},{"id":"liquid/lfm-2.5-2.6b","name":"LFM 2.5 2.6B","owner":"liquid","release_date":"2026-08-01","position":4},{"id":"google/gemma-4-31b","name":"Gemma 4 31B","owner":"google","release_date":"2026-06-03","position":5},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","owner":"google","release_date":"2026-04-03","position":6}]},{"id":"anyrouter/decision","object":"model","canonical_slug":"anyrouter/decision","owned_by":"anyrouter","hugging_face_id":null,"name":"AnyRouter Decision","display_name":"AnyRouter Decision","provider":"anyrouter","providers":["AnyRouter"],"category":"text","capabilities":["systemone"],"created":1780876800,"description":"Free on every plan. Routes across the System One decision models AnyRouter serves on its own platform keys — TypeSafe Jev, Microsoft Decision 1, Perplexity Decider, Liquid D1, and peers — with health-aware fallback for POST /api/v1/decisions and /api/v1/systemone. No BYOK key and no credits needed: every hop is $0. No plan quota; a per-key fair-use burst cap of 60 requests per minute applies.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Anyrouter","instruct_type":null},"pricing":{"prompt":"0.04","completion":"0","input_per_1m":0.04,"output_per_1m":0},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anyrouter/decision","metrics":"/api/v1/models/anyrouter%2Fdecision/metrics"},"per_upstream":[{"backend":"fpt-byok","model_name":"Quyet-1.0-Large","llm_provider":"fpt-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.08,"output_per_1m":0},"context":{"max_length":10000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"vercel-byok","model_name":"convaiinnovations/laya-free","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"fastino-byok","model_name":"fastino/gliner2.5-multi-v1","llm_provider":"fastino-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hal-x","model_name":"thx-01","llm_provider":"hal-x","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1024},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"inception/mercury-decide:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"siliconflow-byok","model_name":"Kev-4B","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"liquid-byok","model_name":"d1:free","llm_provider":"liquid-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"azure-byok","model_name":"Microsoft-Decision-1","llm_provider":"azure-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"nace-ai-byok","model_name":"drex-v1.5","llm_provider":"nace-ai-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"perplexity-byok","model_name":"pplx-decider-v1-27b","llm_provider":"perplexity-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.04,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"scira","model_name":"amos-1-large","llm_provider":"scira","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false,"prompt_training":true},"supported_parameters":["state","model","questions"]},{"backend":"strands-decider-byok","model_name":"StrandsAgents/strands-decider-2B-hobson-v19","llm_provider":"strands-decider-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"subq-byok","model_name":"subq-snap-preview","llm_provider":"subq-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"typesafe-byok","model_name":"jev-latest","llm_provider":"typesafe-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"llmgateway-byok","model_name":"jev-1.13.0","llm_provider":"llmgateway-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"aihubmix-byok","model_name":"jev-1.13","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.0462,"output_per_1m":0},"context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"experiential-byok","model_name":"jev-latest","llm_provider":"experiential-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"aimlapi-byok","model_name":"typesafe/jev","llm_provider":"aimlapi-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.0577668,"output_per_1m":0},"context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"autojev-byok","model_name":"~typesafe/jev-latest","llm_provider":"autojev-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"anyrouter/latest","object":"model","canonical_slug":"anyrouter/latest","owned_by":"anyrouter","hugging_face_id":null,"name":"AnyRouter Latest","display_name":"AnyRouter Latest","provider":"anyrouter","providers":["AnyRouter"],"category":"text","capabilities":["chat","streaming","function-calling","coding","vision"],"created":1780876800,"description":"Routes to the latest stable production chat model that is actually serving traffic — not a preview, experimental, or unused catalog SKU. Ranked from live request volume; if usage data is unavailable, uses a documented fallback of current platform-served flagships. Billed at each hop's rate.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Anyrouter","instruct_type":null},"pricing":{"prompt":"0.042448","completion":"0.084896","input_per_1m":0.042448,"output_per_1m":0.084896},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort","stop"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/anyrouter/latest","metrics":"/api/v1/models/anyrouter%2Flatest/metrics"},"per_upstream":[{"backend":"anyrouter","model_name":"foundation-model","llm_provider":"anyrouter","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":true},"features":{"streaming":true}},{"backend":"freebuff","model_name":"deepseek/deepseek-v4-flash","llm_provider":"freebuff","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"antigravity","model_name":"google/gemini-2.5-flash","llm_provider":"antigravity","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576,"max_completion_tokens":65536},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nvidia","model_name":"meta/muse-glimmer-30b","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"pollinations","model_name":"openai-fast","llm_provider":"pollinations","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"kilo","model_name":"stealth/glyph-cluster","llm_provider":"kilo","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":256000,"max_completion_tokens":256000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}],"members":[{"id":"nvidia/nemotron-3.5-super-vl-120b-a12b","name":"Nemotron 3.5 Super VL 120B A12B","owner":"nvidia","release_date":"2026-10-15","position":1},{"id":"stealth/glyph-cluster","name":"Glyph Cluster","owner":"stealth","release_date":"2026-10-07","position":2},{"id":"reflection/beam-1.0","name":"Beam 1.0","owner":"reflection","release_date":"2026-10-05","position":3},{"id":"inclusionai/ling-3.1-flash","name":"Ling-3.1-flash","owner":"inclusionai","release_date":"2026-10-02","position":4},{"id":"x-ai/grok-4.7","name":"Grok 4.7","owner":"x-ai","release_date":"2026-09-16","position":5},{"id":"xingchen-agi/xing4.0-29b-a4b","name":"Xing4.0 29B A4B","owner":"xingchen-agi","release_date":"2026-09-16","position":6},{"id":"z-ai/glm-5.3","name":"GLM-5.3","owner":"z-ai","release_date":"2026-08-14","position":7},{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","owner":"qwen","release_date":"2026-08-03","position":8},{"id":"liquid/lfm-2.5-2.6b","name":"LFM 2.5 2.6B","owner":"liquid","release_date":"2026-08-01","position":9},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","owner":"meta","release_date":"2026-08-01","position":10},{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","owner":"nvidia","release_date":"2026-08-01","position":11},{"id":"thinkingmachines/inkling-small","name":"Inkling Small","owner":"thinkingmachines","release_date":"2026-07-30","position":12},{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","owner":"poolside","release_date":"2026-07-21","position":13},{"id":"moonshotai/kimi-k3","name":"Kimi K3","owner":"moonshotai","release_date":"2026-07-16","position":14},{"id":"thinkingmachines/inkling","name":"Inkling","owner":"thinkingmachines","release_date":"2026-07-15","position":15},{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","owner":"poolside","release_date":"2026-07-09","position":16},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek-V4-Flash","owner":"deepseek","release_date":"2026-07-08","position":17},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","owner":"moonshotai","release_date":"2026-07-08","position":18},{"id":"qwen/qwen3-8b","name":"Qwen3-8B","owner":"qwen","release_date":"2026-07-08","position":19},{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","owner":"qwen","release_date":"2026-06-12","position":20}]},{"id":"baai/bge-base-en-v1.5","object":"model","canonical_slug":"baai/bge-base-en-v1.5","owned_by":"baai","hugging_face_id":null,"name":"BGE Base EN v1.5","display_name":"BGE Base EN v1.5","provider":"baai","providers":["respan-byok"],"category":"embedding","capabilities":["embedding"],"created":1694390400,"description":"BGE Base EN v1.5 is an English text embedding model that maps sentences and paragraphs to 768-dimensional vectors for retrieval, semantic search and document matching. 512-token input.","context_length":512,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.005","completion":"0","input_per_1m":0.005,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.005,"output_per_1m":0}},"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","model","encoding_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/baai/bge-base-en-v1.5","metrics":"/api/v1/models/baai%2Fbge-base-en-v1.5/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"bge-base-en-v1.5","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.005,"output_per_1m":0},"billing":"byok","context":{"max_length":512},"data_policy":{"zdr":false},"supported_parameters":["input","model","encoding_format"]}]},{"id":"cohere/rerank-multilingual-v3.0","object":"model","canonical_slug":"cohere/rerank-multilingual-v3.0","owned_by":"cohere","hugging_face_id":null,"name":"Rerank Multilingual 3.0","display_name":"Rerank Multilingual 3.0","provider":"Cohere","providers":["cohere-rerank","cohere-rerank-byok"],"category":"rerank","capabilities":["rerank"],"created":1712793600,"description":"Cohere's Rerank Multilingual 3.0 scores how relevant each document is to a query, for non-English and mixed-language search. Use it as a second stage after vector or keyword search.","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["scores"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"2","completion":"0","input_per_1m":2,"output_per_1m":0},"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/cohere/rerank-multilingual-v3.0","metrics":"/api/v1/models/cohere%2Frerank-multilingual-v3.0/metrics"},"per_upstream":[{"backend":"cohere-rerank","model_name":"rerank-multilingual-v3.0","llm_provider":"cohere-rerank","pricing":{"input_per_1m":2,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":false}},{"backend":"cohere-rerank-byok","model_name":"rerank-multilingual-v3.0","llm_provider":"cohere-rerank-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":false}}]},{"id":"cohere/rerank-v3.5","object":"model","canonical_slug":"cohere/rerank-v3.5","owned_by":"cohere","hugging_face_id":null,"name":"Rerank 3.5","display_name":"Rerank 3.5","provider":"Cohere","providers":["cohere-rerank","cohere-rerank-byok"],"category":"rerank","capabilities":["rerank"],"created":1733097600,"description":"Cohere's Rerank 3.5 scores how relevant each document is to a query. It handles 100+ languages and long, semi-structured documents (emails, tables, JSON, code). Use it as a second stage after vector or keyword search to put the best passages first.","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["scores"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"2","completion":"0","input_per_1m":2,"output_per_1m":0},"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/cohere/rerank-v3.5","metrics":"/api/v1/models/cohere%2Frerank-v3.5/metrics"},"per_upstream":[{"backend":"cohere-rerank","model_name":"rerank-v3.5","llm_provider":"cohere-rerank","pricing":{"input_per_1m":2,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":false}},{"backend":"cohere-rerank-byok","model_name":"rerank-v3.5","llm_provider":"cohere-rerank-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":false}}]},{"id":"cohere/rerank-v4.0-fast","object":"model","canonical_slug":"cohere/rerank-v4.0-fast","owned_by":"cohere","hugging_face_id":null,"name":"Rerank 4.0 Fast","display_name":"Rerank 4.0 Fast","provider":"Cohere","providers":["cohere-rerank","cohere-rerank-byok"],"category":"rerank","capabilities":["rerank"],"created":1765411200,"description":"Cohere's Rerank 4.0 Fast is the low-latency Rerank 4 variant. It scores how relevant each document is to a query across 100+ languages. Use it as a second stage after vector or keyword search when latency matters more than the last bit of quality.","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["scores"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"2","completion":"0","input_per_1m":2,"output_per_1m":0},"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/cohere/rerank-v4.0-fast","metrics":"/api/v1/models/cohere%2Frerank-v4.0-fast/metrics"},"per_upstream":[{"backend":"cohere-rerank","model_name":"rerank-v4.0-fast","llm_provider":"cohere-rerank","pricing":{"input_per_1m":2,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false}},{"backend":"cohere-rerank-byok","model_name":"rerank-v4.0-fast","llm_provider":"cohere-rerank-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false}}]},{"id":"cohere/rerank-v4.0-pro","object":"model","canonical_slug":"cohere/rerank-v4.0-pro","owned_by":"cohere","hugging_face_id":null,"name":"Rerank 4.0 Pro","display_name":"Rerank 4.0 Pro","provider":"Cohere","providers":["cohere-rerank","cohere-rerank-byok"],"category":"rerank","capabilities":["rerank"],"created":1765411200,"description":"Cohere's Rerank 4.0 Pro is the highest-quality Cohere reranker. It scores how relevant each document is to a query across 100+ languages, with a longer context per document than Rerank 3.5. Use it as a second stage after vector or keyword search when ranking quality matters most.","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["scores"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":"2.5","completion":"0","input_per_1m":2.5,"output_per_1m":0},"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/cohere/rerank-v4.0-pro","metrics":"/api/v1/models/cohere%2Frerank-v4.0-pro/metrics"},"per_upstream":[{"backend":"cohere-rerank","model_name":"rerank-v4.0-pro","llm_provider":"cohere-rerank","pricing":{"input_per_1m":2.5,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false}},{"backend":"cohere-rerank-byok","model_name":"rerank-v4.0-pro","llm_provider":"cohere-rerank-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2.5,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false}}]},{"id":"deepseek/deepseek-v4-flash","object":"model","canonical_slug":"deepseek/deepseek-v4-flash","owned_by":"deepseek","hugging_face_id":null,"name":"DeepSeek-V4-Flash","display_name":"DeepSeek-V4-Flash","provider":"DeepSeek","providers":["freebuff","freebuff-byok","deepseek-byok","siliconflow-byok","opencode-zen-byok","opencode-go-byok","openrouter-byok","commandcode-byok","fpt-byok","experiential-byok","aihubmix-byok","router-byok","vercel-byok","deepinfra-byok","gmicloud-byok","huggingface-byok","venice-byok","nousresearch-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding","reasoning","vision","agentic"],"created":1783468800,"description":"Fast and cheap DeepSeek-V4 MoE variant via SiliconFlow free tier for high-throughput chat and coding.","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Deepseek","instruct_type":null},"pricing":{"prompt":"0.042448","completion":"0.084896","input_per_1m":0.042448,"output_per_1m":0.084896},"top_provider":{"context_length":1050000,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort","stop","response_format","structured_outputs","frequency_penalty","logit_bias","logprobs","max_completion_tokens","min_p","presence_penalty","repetition_penalty","seed","top_a","top_k","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash","metrics":"/api/v1/models/deepseek%2Fdeepseek-v4-flash/metrics"},"per_upstream":[{"backend":"freebuff","model_name":"deepseek/deepseek-v4-flash","llm_provider":"freebuff","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"freebuff-byok","model_name":"deepseek/deepseek-v4-flash","llm_provider":"freebuff-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepseek-byok","model_name":"deepseek-flash","llm_provider":"deepseek-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"context":{"max_length":1048576,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"siliconflow-byok","model_name":"deepseek-ai/DeepSeek-V4-Flash","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"opencode-zen-byok","model_name":"deepseek-v4-flash","llm_provider":"opencode-zen-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"opencode-go-byok","model_name":"deepseek-v4-flash","llm_provider":"opencode-go-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"deepseek/deepseek-v4-flash","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.077,"output_per_1m":0.154},"context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"commandcode-byok","model_name":"deepseek/deepseek-v4-flash","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"fpt-byok","model_name":"DeepSeek-V4-Flash","llm_provider":"fpt-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.14,"output_per_1m":0.28},"context":{"max_length":500000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p"],"features":{"streaming":true}},{"backend":"experiential-byok","model_name":"deepseek-v4-flash","llm_provider":"experiential-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"aihubmix-byok","model_name":"deepseek-v4-flash-0731-fast","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.28,"output_per_1m":0.56},"context":{"max_length":1000000,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"router-byok","model_name":"deepseek-v4-flash","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.14,"output_per_1m":0.28},"context":{"max_length":1050000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"deepseek/deepseek-v4-flash","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.13,"output_per_1m":0.26},"context":{"max_length":1000000,"max_completion_tokens":384000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"deepseek-ai/DeepSeek-V4-Flash","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.09,"output_per_1m":0.18},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"reasoning":true}},{"backend":"gmicloud-byok","model_name":"deepseek-ai/DeepSeek-V4-Flash","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.14,"output_per_1m":0.28},"context":{"max_length":1048575},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"huggingface-byok","model_name":"deepseek-ai/DeepSeek-V4-Flash","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042448,"output_per_1m":0.084896},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"venice-byok","model_name":"deepseek-v4-flash","llm_provider":"venice-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.138,"output_per_1m":0.275},"context":{"max_length":1000000,"max_completion_tokens":32768},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"deepseek/deepseek-v4-flash","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":1.28},"context":{"max_length":1048576,"max_completion_tokens":943718},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"deepseek/deepseek-v4.1-flash-1017","object":"model","canonical_slug":"deepseek/deepseek-v4.1-flash-1017","owned_by":"deepseek","hugging_face_id":null,"name":"DeepSeek V4.1 Flash 1017","display_name":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","providers":["openrouter-byok","deepseek-byok","vercel-byok","deepinfra-byok","nousresearch-byok","aihubmix-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding","reasoning","vision"],"created":1792195200,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. Sparse mixture-of-experts with native vision in, text out, and a 1M-token context window. Hosts bill it as its own model: OpenRouter lists it at $0.15 / $0.60 per 1M input / output tokens, against $0.04 / $0.144 for the original September checkpoint `deepseek/deepseek-v4.1-flash`.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Deepseek","instruct_type":null},"pricing":{"prompt":"0.075","completion":"0.3","input_per_1m":0.075,"output_per_1m":0.3,"billing":"byok","list_pricing":{"input_per_1m":0.075,"output_per_1m":0.3}},"top_provider":{"context_length":1048576,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-1017","metrics":"/api/v1/models/deepseek%2Fdeepseek-v4.1-flash-1017/metrics"},"per_upstream":[{"backend":"openrouter-byok","model_name":"deepseek/deepseek-v4.1-flash-1017","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.15,"output_per_1m":0.6},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":393216},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepseek-byok","model_name":"deepseek-flash","llm_provider":"deepseek-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"deepseek/deepseek-v4.1-flash-1017","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.075,"output_per_1m":0.3},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.2,"output_per_1m":0.6},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"deepseek/deepseek-v4.1-flash-1017","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.15,"output_per_1m":0.6},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"aihubmix-byok","model_name":"deepseek-v4.1-flash-1017","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.155,"output_per_1m":0.62},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"deepseek/deepseek-v4.1-flash","object":"model","canonical_slug":"deepseek/deepseek-v4.1-flash","owned_by":"deepseek","hugging_face_id":null,"name":"DeepSeek V4.1 Flash","display_name":"DeepSeek V4.1 Flash","provider":"DeepSeek","providers":["nvidia-byok","openrouter-byok","ollama-byok","aihubmix-byok","deepinfra-byok","router-byok","vercel-byok","novita-byok","siliconflow-byok","gmicloud-byok","huggingface-byok","venice-byok","nousresearch-byok","baseten-byok","fireworks-byok","wafer-byok","onetoken-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding","reasoning","vision"],"created":1788998400,"description":"DeepSeek V4.1 Flash is the cost-efficient sparse MoE tier of the V4.1 family, built on the Causal Encoder-Decoder (CED) architecture: 552B total parameters with 8B active on input and 16B on output. Native vision in, text out, 1M context. Compressed KV cache needs roughly a quarter of the previous Flash's HBM. This is the original September 2026 checkpoint, listed by OpenRouter as `deepseek/deepseek-v4.1-flash`. The official API id `deepseek-flash` now serves the October 17 snapshot, which has its own listing `deepseek/deepseek-v4.1-flash-1017`.","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Deepseek","instruct_type":null},"pricing":{"prompt":"0.04","completion":"0.144","input_per_1m":0.04,"output_per_1m":0.144,"billing":"byok","list_pricing":{"input_per_1m":0.04,"output_per_1m":0.144}},"top_provider":{"context_length":1050000,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs","frequency_penalty","logprobs","presence_penalty","reasoning_effort","repetition_penalty","seed","top_a","top_k","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash","metrics":"/api/v1/models/deepseek%2Fdeepseek-v4.1-flash/metrics"},"per_upstream":[{"backend":"nvidia-byok","model_name":"deepseek-ai/deepseek-v4.1-flash","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"deepseek/deepseek-v4.1-flash","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.04,"output_per_1m":0.144},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"ollama-byok","model_name":"deepseek-v4.1-flash:cloud","llm_provider":"ollama-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":384000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"aihubmix-byok","model_name":"deepseek-v4.1-flash","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.155,"output_per_1m":0.62},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.2,"output_per_1m":0.6},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"router-byok","model_name":"deepseek-v4.1-flash","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.22,"output_per_1m":0.66},"billing":"byok","context":{"max_length":1050000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"deepseek/deepseek-v4.1-flash","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"novita-byok","model_name":"deepseek/deepseek-v4.1-flash","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":393216},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"siliconflow-byok","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"gmicloud-byok","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048575},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"huggingface-byok","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"venice-byok","model_name":"deepseek-v4-1-flash","llm_provider":"venice-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"deepseek/deepseek-v4.1-flash","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.106,"output_per_1m":0.513},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"baseten-byok","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","llm_provider":"baseten-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"fireworks-byok","model_name":"accounts/fireworks/models/deepseek-v4p1-flash","llm_provider":"fireworks-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"wafer-byok","model_name":"DeepSeek-V4.1-Flash","llm_provider":"wafer-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"onetoken-byok","model_name":"deepseek-v4.1-flash","llm_provider":"onetoken-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.011,"output_per_1m":0.044},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"dots-studio/dots-3-note-preview","object":"model","canonical_slug":"dots-studio/dots-3-note-preview","owned_by":"dots-studio","hugging_face_id":null,"name":"Dots3-Note Preview","display_name":"Dots3-Note Preview","provider":"dots-studio","providers":["aihubmix-byok","hue","hagiang","openrouter-byok"],"category":"text","capabilities":["chat","streaming","function-calling","vision","reasoning"],"created":1786665600,"description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total and a 512,000-token context window. Served on the free platform pool.","context_length":512000,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Dots-studio","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":512000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/dots-studio/dots-3-note-preview","metrics":"/api/v1/models/dots-studio%2Fdots-3-note-preview/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"dots-3-note-preview-free","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":512000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"hue","model_name":"dots-studio/dots-3-note-preview:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":512000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"hagiang","model_name":"dots-studio/dots-3-note-preview:free","llm_provider":"hagiang","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":512000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"dots-studio/dots-3-note-preview:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":512000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true}}]},{"id":"fastino/gliner2.5-multi-v1","object":"model","canonical_slug":"fastino/gliner2.5-multi-v1","owned_by":"fastino","hugging_face_id":null,"name":"GLiNER2.5-Decide","display_name":"GLiNER2.5-Decide","provider":"fastino","providers":["fastino-byok"],"category":"text","capabilities":["systemone"],"created":1790035200,"description":"Fastino GLiNER2.5-Decide is a decision model: send application state and typed questions (noul / choice / score) and get structured answers with confidence — not generated chat text. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). Upstream, GLiNER2.5 runs schema-driven classifications on an OpenAI-compatible chat-completions API; the gateway adapts the System One envelope for this hop.","context_length":32000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Fastino","instruct_type":null},"pricing":{"prompt":"0.042","completion":"0","input_per_1m":0.042,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.042,"output_per_1m":0}},"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/fastino/gliner2.5-multi-v1","metrics":"/api/v1/models/fastino%2Fgliner2.5-multi-v1/metrics"},"per_upstream":[{"backend":"fastino-byok","model_name":"fastino/gliner2.5-multi-v1","llm_provider":"fastino-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"google/gemma-4-26b-a4b-it","object":"model","canonical_slug":"google/gemma-4-26b-a4b-it","owned_by":"google","hugging_face_id":null,"name":"Gemma 4 26B A4B","display_name":"Gemma 4 26B A4B","provider":"Google","providers":["aihubmix-byok","openrouter-byok","google-aistudio-byok","google-agent-platform-byok","hue","fpt-byok","vercel-byok","deepinfra-byok","novita-byok","siliconflow-byok","gmicloud-byok","huggingface-byok","nousresearch-byok","respan-byok"],"category":"text","capabilities":["chat","reasoning","streaming","function-calling","vision","coding"],"created":1775174400,"description":"Gemma 4 is Google's most intelligent family of open models, built from Gemini 3 research to maximize intelligence-per-parameter.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.042","completion":"0.22","input_per_1m":0.042,"output_per_1m":0.22,"billing":"byok","list_pricing":{"input_per_1m":0.042,"output_per_1m":0.22}},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","include_reasoning","structured_outputs","frequency_penalty","logit_bias","logprobs","min_p","presence_penalty","repetition_penalty","seed","top_k","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it","metrics":"/api/v1/models/google%2Fgemma-4-26b-a4b-it/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"gemma-4-26b-a4b-it","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"google/gemma-4-26b-a4b-it:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"google/gemma-4-26b-a4b-it","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"google-aistudio-byok","model_name":"gemma-4-26b-a4b-it","llm_provider":"google-aistudio-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","context":{"max_length":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"google-agent-platform-byok","model_name":"google/gemma-4-26b-a4b-it-maas","llm_provider":"google-agent-platform-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","context":{"max_length":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"hue","model_name":"google/gemma-4-26b-a4b-it:free","llm_provider":"hue","pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"fpt-byok","model_name":"gemma-4-26B-A4B-it","llm_provider":"fpt-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.14,"output_per_1m":0.4},"billing":"byok","context":{"max_length":262000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p"],"features":{"streaming":true}},{"backend":"vercel-byok","model_name":"google/gemma-4-26b-a4b-it","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.15,"output_per_1m":0.6},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"google/gemma-4-26B-A4B-it","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.07,"output_per_1m":0.34},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"vision":true,"reasoning":true}},{"backend":"novita-byok","model_name":"google/gemma-4-26b-a4b-it","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.13,"output_per_1m":0.4},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"siliconflow-byok","model_name":"google/gemma-4-26B-A4B-it","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"gmicloud-byok","model_name":"google/gemma-4-26b-a4b-it","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.13,"output_per_1m":0.4},"billing":"byok","context":{"max_length":256000},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"huggingface-byok","model_name":"google/gemma-4-26B-A4B-it","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nousresearch-byok","model_name":"google/gemma-4-26b-a4b-it","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0.22},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"respan-byok","model_name":"gemma-4-26b-a4b-it","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.3},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"vision":true}}]},{"id":"google/gemma-4-31b","object":"model","canonical_slug":"google/gemma-4-31b","owned_by":"google","hugging_face_id":null,"name":"Gemma 4 31B","display_name":"Gemma 4 31B","provider":"Google","providers":["aihubmix-byok","ollama-byok","openrouter-byok","google-aistudio-byok","hue","fpt-byok","respan-byok"],"category":"text","capabilities":["chat","reasoning","streaming","function-calling","vision","thinking"],"created":1780444800,"description":"Gemma 4 31B is Google's dense frontier-level open reasoning model, optimized for complex reasoning, agentic workflows, coding, and multimodal understanding.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.1","completion":"0.34","input_per_1m":0.1,"output_per_1m":0.34,"billing":"byok","list_pricing":{"input_per_1m":0.1,"output_per_1m":0.34}},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-4-31b","metrics":"/api/v1/models/google%2Fgemma-4-31b/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"gemma-4-31b-it","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"ollama-byok","model_name":"gemma4:31b-cloud","llm_provider":"ollama-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"google/gemma-4-31b-it:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"google/gemma-4-31b-it","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"google-aistudio-byok","model_name":"gemma-4-31b-it","llm_provider":"google-aistudio-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"hue","model_name":"google/gemma-4-31b-it:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"fpt-byok","model_name":"gemma-4-31B-it","llm_provider":"fpt-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p"],"features":{"streaming":true}},{"backend":"respan-byok","model_name":"gemma-4-31b-it","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"vision":true}}]},{"id":"hal-x/thx-01","object":"model","canonical_slug":"hal-x/thx-01","owned_by":"hal-x","hugging_face_id":null,"name":"THX-01","display_name":"THX-01","provider":"hal-x","providers":["hal-x"],"category":"text","capabilities":["systemone"],"created":1791676800,"description":"THX-01 is a 322M multilingual decision model from HAL-X AI, trained with reinforcement learning on a strictly proper scoring rule so its probabilities are calibrated. Send a state and typed questions (noul / choice / score) and get an answer with probabilities for each question in one forward pass of about 10 ms — not generated chat text. Post-trained in 18 languages, 100+ supported. Apache 2.0. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":1024,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Hal-x","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":1024,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/hal-x/thx-01","metrics":"/api/v1/models/hal-x%2Fthx-01/metrics"},"per_upstream":[{"backend":"hal-x","model_name":"thx-01","llm_provider":"hal-x","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1024},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"inception/mercury-decide","object":"model","canonical_slug":"inception/mercury-decide","owned_by":"inception","hugging_face_id":null,"name":"Mercury Decide","display_name":"Mercury Decide","provider":"inception","providers":["hue","openrouter-byok"],"category":"text","capabilities":["systemone"],"created":1790726400,"description":"Mercury Decide is Inception's structured decision model. Send application state and typed questions (noul / choice / score) and get back a choice, a score, or a yes/no answer, each with a calibrated probability taken straight from the model rather than written out as text, so no output tokens are generated. It answers up to 14 decisions per second, which is fast enough to run on every case and escalate only the unsure ones. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Inception","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/inception/mercury-decide","metrics":"/api/v1/models/inception%2Fmercury-decide/metrics"},"per_upstream":[{"backend":"hue","model_name":"inception/mercury-decide:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"inception/mercury-decide:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"inclusionai/ling-3.1-flash","object":"model","canonical_slug":"inclusionai/ling-3.1-flash","owned_by":"inclusionai","hugging_face_id":null,"name":"Ling-3.1-flash","display_name":"Ling-3.1-flash","provider":"inclusionai","providers":["hermes-agent","novita-byok","openrouter-byok","commandcode-byok","vercel-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding","agentic"],"created":1790899200,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total. Nous Portal platform hop is paid ($0.075/$0.225 per 1M, repriced by Nous 2026-10-16); the OpenRouter platform hop is commented out (#4527) after 402-ing on every attempt, and Novita/OpenRouter/Command Code/Vercel BYOK hops serve it at $0.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Ling","instruct_type":null},"pricing":{"prompt":"0.075","completion":"0.225","input_per_1m":0.075,"output_per_1m":0.225,"billing":"byok","list_pricing":{"input_per_1m":0.075,"output_per_1m":0.225}},"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","frequency_penalty","presence_penalty","seed","reasoning","include_reasoning"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/inclusionai/ling-3.1-flash","metrics":"/api/v1/models/inclusionai%2Fling-3.1-flash/metrics"},"per_upstream":[{"backend":"hermes-agent","model_name":"inclusionai/ling-3.1-flash","llm_provider":"hermes-agent","pricing":{"input_per_1m":0.075,"output_per_1m":0.225,"input_cache_read_per_1m":0.015},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"novita-byok","model_name":"inclusionai/ling-3.1-flash","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":32768},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"inclusionai/ling-3.1-flash","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","tools","tool_choice","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"commandcode-byok","model_name":"inclusionai/ling-3.1-flash:free","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"inclusionai/ling-3.1-flash-free","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"intfloat/e5-base-v2","object":"model","canonical_slug":"intfloat/e5-base-v2","owned_by":"intfloat","hugging_face_id":null,"name":"E5 Base v2","display_name":"E5 Base v2","provider":"intfloat","providers":["respan-byok"],"category":"embedding","capabilities":["embedding"],"created":1684454400,"description":"E5 Base v2 is an English text embedding model that maps sentences and paragraphs to 768-dimensional vectors for semantic search and similarity. 512-token input.","context_length":512,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.005","completion":"0","input_per_1m":0.005,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.005,"output_per_1m":0}},"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","model","encoding_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/intfloat/e5-base-v2","metrics":"/api/v1/models/intfloat%2Fe5-base-v2/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"e5-base-v2","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.005,"output_per_1m":0},"billing":"byok","context":{"max_length":512},"data_policy":{"zdr":false},"supported_parameters":["input","model","encoding_format"]}]},{"id":"jaredpalmer/kev-4b","object":"model","canonical_slug":"jaredpalmer/kev-4b","owned_by":"jaredpalmer","hugging_face_id":null,"name":"Kev 4B","display_name":"Kev 4B","provider":"jaredpalmer","providers":["siliconflow-byok","openrouter-byok","hue"],"category":"text","capabilities":["systemone"],"created":1790294400,"description":"Kev 4B is a small open-weight decision model from Jared Palmer — a LoRA adapter and pointer head on Qwen3.5-4B-Base. Send state and typed questions (noul / choice / score) and get a calibrated probability per question in one forward pass, not generated text. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Jaredpalmer","instruct_type":null},"pricing":{"prompt":"0.042","completion":"0","input_per_1m":0.042,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.042,"output_per_1m":0}},"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/jaredpalmer/kev-4b","metrics":"/api/v1/models/jaredpalmer%2Fkev-4b/metrics"},"per_upstream":[{"backend":"siliconflow-byok","model_name":"Kev-4B","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"jaredpalmer/kev-4b","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"jaredpalmer/kev-4b","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"liquid/d1","object":"model","canonical_slug":"liquid/d1","owned_by":"liquid","hugging_face_id":null,"name":"Liquid d1","display_name":"Liquid d1","provider":"liquid","providers":["liquid-byok","hue"],"category":"text","capabilities":["systemone"],"created":1790640000,"description":"Liquid d1 is Liquid AI's first decision model: send application state and typed questions (noul / choice / score) and get calibrated probabilities back in a single call with zero generated tokens — not chat text. Built for classification, routing, scoring, moderation and guardrails. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":32000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Liquid","instruct_type":null},"pricing":{"prompt":"0.04","completion":"0","input_per_1m":0.04,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.04,"output_per_1m":0}},"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/liquid/d1","metrics":"/api/v1/models/liquid%2Fd1/metrics"},"per_upstream":[{"backend":"liquid-byok","model_name":"d1:free","llm_provider":"liquid-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"liquid/d1","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.04,"output_per_1m":0},"context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"liquid/lfm-2.5-2.6b","object":"model","canonical_slug":"liquid/lfm-2.5-2.6b","owned_by":"liquid","hugging_face_id":null,"name":"LFM 2.5 2.6B","display_name":"LFM 2.5 2.6B","provider":"liquid","providers":["aihubmix-byok","hue","hagiang","openrouter-byok"],"category":"text","capabilities":["chat","streaming","coding","function-calling"],"created":1785542400,"description":"Liquid AI LFM2.5-2.6B is a compact free chat model for general assistant and coding tasks. Served free via the platform free pool and BYOK free SKU.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","response_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/liquid/lfm-2.5-2.6b","metrics":"/api/v1/models/liquid%2Flfm-2.5-2.6b/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"lfm-2.5-2.6b-free","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"hue","model_name":"liquid/lfm-2.5-2.6b:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":65536,"max_completion_tokens":8192},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"hagiang","model_name":"liquid/lfm-2.5-2.6b:free","llm_provider":"hagiang","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":65536,"max_completion_tokens":8192},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"liquid/lfm-2.5-2.6b:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":128000,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}}]},{"id":"meituan/longcat-2.5-preview","object":"model","canonical_slug":"meituan/longcat-2.5-preview","owned_by":"meituan","hugging_face_id":null,"name":"LongCat-2.5-Preview","display_name":"LongCat-2.5-Preview","provider":"meituan","providers":["hermes-agent","longcat-byok","vercel-byok"],"category":"text","capabilities":["chat","streaming","reasoning","coding","agentic","function-calling","vision"],"created":1790294400,"description":"LongCat-2.5-Preview is Meituan's sparse mixture-of-experts frontier model — ~1.6T total parameters with ~48B active — over a 1M-token context window. It adds native multimodal understanding (image input), stronger coding ability, and a `thinking` toggle, and is built for long-horizon agentic work across terminals, browsers, GUIs, spreadsheets, and design tools. Served over the OpenAI-compatible and Anthropic-compatible APIs.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Meituan","instruct_type":null},"pricing":{"prompt":"0.3","completion":"1.2","input_per_1m":0.3,"output_per_1m":1.2,"billing":"byok","list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2}},"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","tools","tool_choice","response_format","reasoning","include_reasoning","reasoning_effort","stop","structured_outputs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meituan/longcat-2.5-preview","metrics":"/api/v1/models/meituan%2Flongcat-2.5-preview/metrics"},"per_upstream":[{"backend":"hermes-agent","model_name":"meituan/longcat-2.5-preview:free","llm_provider":"hermes-agent","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576,"max_completion_tokens":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","top_k","tools","tool_choice","response_format","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"longcat-byok","model_name":"LongCat-2.5-Preview","llm_provider":"longcat-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.75,"output_per_1m":2.95},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"meituan/longcat-2.5-preview","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"meta/muse-glimmer-30b","object":"model","canonical_slug":"meta/muse-glimmer-30b","owned_by":"meta","hugging_face_id":null,"name":"Muse Glimmer 30B","display_name":"Muse Glimmer 30B","provider":"meta","providers":["nvidia","nvidia-byok","vercel-byok","nousresearch-byok","openrouter-byok"],"category":"multimodal","capabilities":["chat","streaming","function-calling","reasoning","vision","coding","agentic"],"created":1785542400,"description":"Meta Muse Glimmer 30B is a ~30B dense multimodal instruct model (text and image in, text out) with a 131K context window, chain-of-thought reasoning, and function calling. Available on NVIDIA NIM for chat and agent workflows.","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Meta","instruct_type":null},"pricing":{"prompt":"0.3","completion":"1.2","input_per_1m":0.3,"output_per_1m":1.2},"top_provider":{"context_length":131072,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-glimmer-30b","metrics":"/api/v1/models/meta%2Fmuse-glimmer-30b/metrics"},"per_upstream":[{"backend":"nvidia","model_name":"meta/muse-glimmer-30b","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nvidia-byok","model_name":"meta/muse-glimmer-30b","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"meta/muse-glimmer-30b","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.35,"output_per_1m":1.5},"context":{"max_length":131072,"max_completion_tokens":131072},"data_policy":{"zdr":true},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"meta/muse-glimmer-30b","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"context":{"max_length":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"meta/muse-glimmer-30b","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"context":{"max_length":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"meta/muse-spark-1.2-contributor","object":"model","canonical_slug":"meta/muse-spark-1.2-contributor","owned_by":"meta","hugging_face_id":null,"name":"Muse Spark 1.2 Contributor","display_name":"Muse Spark 1.2 Contributor","provider":"meta","providers":["meta-byok","openrouter-byok","vercel-byok"],"category":"multimodal","capabilities":["chat","reasoning","streaming","function-calling","vision"],"created":1785888000,"description":"The cost-efficient contributor tier of Meta's multimodal reasoning model Muse Spark 1.2, for experimentation and early-stage agentic and coding workflows.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Meta","instruct_type":null},"pricing":{"prompt":"0.1","completion":"0.2","input_per_1m":0.1,"output_per_1m":0.2,"billing":"byok","list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2}},"top_provider":{"context_length":1048576,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/meta/muse-spark-1.2-contributor","metrics":"/api/v1/models/meta%2Fmuse-spark-1.2-contributor/metrics"},"per_upstream":[{"backend":"meta-byok","model_name":"muse-spark-1.2-contributor","llm_provider":"meta-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2},"billing":"byok","data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"meta/muse-spark-1.2-contributor","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"vercel-byok","model_name":"meta/muse-spark-1.2-contributor","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true}}]},{"id":"microsoft/microsoft-decision-1","object":"model","canonical_slug":"microsoft/microsoft-decision-1","owned_by":"microsoft","hugging_face_id":null,"name":"Microsoft-Decision-1","display_name":"Microsoft-Decision-1","provider":"microsoft","providers":["azure-byok","openrouter-byok","hue"],"category":"text","capabilities":["systemone"],"created":1791504000,"description":"Microsoft-Decision-1 is a small Microsoft model built for fast decisions: yes/no, multiple-choice and rating questions, plus rubric-based grading of AI responses and agent actions. Send application state and typed questions (noul / choice / score) and get back a calibrated probability for each fixed answer option, not generated chat text. It has a 32,768-token context window. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Microsoft","instruct_type":null},"pricing":{"prompt":"0.042","completion":"0","input_per_1m":0.042,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.042,"output_per_1m":0}},"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/microsoft/microsoft-decision-1","metrics":"/api/v1/models/microsoft%2Fmicrosoft-decision-1/metrics"},"per_upstream":[{"backend":"azure-byok","model_name":"Microsoft-Decision-1","llm_provider":"azure-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"microsoft/microsoft-decision-1","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"microsoft/microsoft-decision-1","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"moonshotai/kimi-k2.6","object":"model","canonical_slug":"moonshotai/kimi-k2.6","owned_by":"moonshot ai","hugging_face_id":null,"name":"Kimi K2.6","display_name":"Kimi K2.6","provider":"Moonshot AI","providers":["aihubmix-byok","siliconflow-byok","cline-byok","nvidia","nvidia-byok","commandcode-byok","router-byok","vercel-byok","nousresearch-byok","novita-byok","openrouter-byok"],"category":"multimodal","capabilities":["chat","reasoning","streaming","function-calling","vision"],"created":1783468800,"description":"Moonshot AI Kimi-K2.6 — large MoE with agentic tool use, vision input, and long-context memory, served via Cloudflare Workers AI and SiliconFlow's free tier.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Moonshotai","instruct_type":null},"pricing":{"prompt":"0.4323","completion":"1.82","input_per_1m":0.4323,"output_per_1m":1.82},"top_provider":{"context_length":262144,"max_completion_tokens":262000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k2.6","metrics":"/api/v1/models/moonshotai%2Fkimi-k2.6/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"kimi-k2.6","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4},"context":{"max_length":256000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"siliconflow-byok","model_name":"moonshotai/Kimi-K2.6","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4},"context":{"max_length":256000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"cline-byok","model_name":"moonshotai/kimi-k2.6","llm_provider":"cline-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nvidia","model_name":"moonshotai/kimi-k2.6","llm_provider":"nvidia","pricing":{"input_per_1m":0.95,"output_per_1m":4},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nvidia-byok","model_name":"moonshotai/kimi-k2.6","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"commandcode-byok","model_name":"moonshotai/Kimi-K2.6","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4},"context":{"max_length":256000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"router-byok","model_name":"kimi-k2.6-fast","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":8},"context":{"max_length":262000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"moonshotai/kimi-k2.6","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4},"context":{"max_length":262000,"max_completion_tokens":262000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"moonshotai/kimi-k2.6","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.4323,"output_per_1m":1.82},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"novita-byok","model_name":"moonshotai/kimi-k2.6","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.8,"output_per_1m":3.4},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"moonshotai/kimi-k2.6","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.65,"output_per_1m":3.41},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"moonshotai/kimi-k3","object":"model","canonical_slug":"moonshotai/kimi-k3","owned_by":"moonshot ai","hugging_face_id":null,"name":"Kimi K3","display_name":"Kimi K3","provider":"Moonshot AI","providers":["aihubmix-byok","nvidia","nvidia-byok","moonshotai-byok","zenmux-byok","openrouter-byok","orcarouter-byok","cline-byok","novita-byok","fireworks-byok","baseten-byok","siliconflow-byok","gmicloud-byok","nousresearch-byok","venice-byok","commandcode-byok","opencode-go-byok","router-byok","vercel-byok"],"category":"multimodal","capabilities":["chat","reasoning","streaming","function-calling","vision","coding","agentic"],"created":1784160000,"description":"Kimi K3 is an open-source multimodal reasoning model from Moonshot AI with a 1M-token context window and native visual understanding. It accepts text, image, and video inputs and is built for long-horizon software engineering, knowledge work, and deep reasoning, with particular strength where code meets visual and spatial reasoning — frontend, game development, and CAD workflows. Its architecture uses KDA and Attention Residuals for computational efficiency, and its thinking mode is always on.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Moonshotai","instruct_type":null},"pricing":{"prompt":"3","completion":"15","input_per_1m":3,"output_per_1m":15},"top_provider":{"context_length":1050000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","reasoning_effort","seed","structured_outputs","include_reasoning"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3","metrics":"/api/v1/models/moonshotai%2Fkimi-k3/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"coding-kimi-k3","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nvidia","model_name":"moonshotai/kimi-k3","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nvidia-byok","model_name":"moonshotai/kimi-k3","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"moonshotai-byok","model_name":"kimi-k3","llm_provider":"moonshotai-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"zenmux-byok","model_name":"moonshotai/kimi-k3","llm_provider":"zenmux-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"moonshotai/kimi-k3","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"orcarouter-byok","model_name":"kimi/kimi-k3","llm_provider":"orcarouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"cline-byok","model_name":"moonshotai/kimi-k3","llm_provider":"cline-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"novita-byok","model_name":"moonshotai/kimi-k3","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"fireworks-byok","model_name":"accounts/fireworks/models/kimi-k3","llm_provider":"fireworks-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"baseten-byok","model_name":"moonshotai/Kimi-K3","llm_provider":"baseten-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"siliconflow-byok","model_name":"moonshotai/Kimi-K3","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"gmicloud-byok","model_name":"moonshotai/kimi-k3","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nousresearch-byok","model_name":"moonshotai/kimi-k3","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","reasoning_effort","seed","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"venice-byok","model_name":"kimi-k3","llm_provider":"venice-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"commandcode-byok","model_name":"moonshotai/Kimi-K3","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"opencode-go-byok","model_name":"kimi-k3","llm_provider":"opencode-go-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"router-byok","model_name":"kimi-k3","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1050000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"moonshotai/kimi-k3","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"nace-ai/drex-v1.5","object":"model","canonical_slug":"nace-ai/drex-v1.5","owned_by":"nace-ai","hugging_face_id":null,"name":"Drex v1.5","display_name":"Drex v1.5","provider":"nace-ai","providers":["nace-ai","nace-ai-byok","openrouter-byok","hue"],"category":"text","capabilities":["systemone"],"created":1791504000,"description":"Drex v1.5 is a small decision model from Nace AI, served over the same System One contract as TypeSafe's Jev. Send application state and typed questions (noul / choice / score) and get back a calibrated probability for each fixed answer option, not generated chat text. It has a 131,072-token context window. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nace-ai","instruct_type":null},"pricing":{"prompt":"0.05","completion":"0","input_per_1m":0.05,"output_per_1m":0},"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nace-ai/drex-v1.5","metrics":"/api/v1/models/nace-ai%2Fdrex-v1.5/metrics"},"per_upstream":[{"backend":"nace-ai","model_name":"drex-v1.5","llm_provider":"nace-ai","pricing":{"input_per_1m":0.05,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"nace-ai-byok","model_name":"drex-v1.5","llm_provider":"nace-ai-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"nace-ai/drex-v1.5","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.04,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"nace-ai/drex-v1.5","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.04,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"nace-ai/drex-v2.0","object":"model","canonical_slug":"nace-ai/drex-v2.0","owned_by":"nace-ai","hugging_face_id":null,"name":"Drex v2.0","display_name":"Drex v2.0","provider":"nace-ai","providers":["nace-ai","nace-ai-byok","openrouter-byok"],"category":"text","capabilities":["systemone"],"created":1791244800,"description":"Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace AI, the larger successor to Drex v1.5. Send application state (text or JSON) and typed questions (noul / choice / score) and get back a calibrated probability for every answer option in a single forward pass, with no text generation. It is TypeSafe System One compatible and suits routing, classification and policy checks that need a scored answer instead of prose. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nace-ai","instruct_type":null},"pricing":{"prompt":"0.06","completion":"0","input_per_1m":0.06,"output_per_1m":0},"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nace-ai/drex-v2.0","metrics":"/api/v1/models/nace-ai%2Fdrex-v2.0/metrics"},"per_upstream":[{"backend":"nace-ai","model_name":"drex-v2.0","llm_provider":"nace-ai","pricing":{"input_per_1m":0.06,"output_per_1m":0},"context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"nace-ai-byok","model_name":"drex-v2.0","llm_provider":"nace-ai-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0},"context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"nace-ai/drex-v2.0","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"nvidia/nemotron-3-embed-1b","object":"model","canonical_slug":"nvidia/nemotron-3-embed-1b","owned_by":"nvidia","hugging_face_id":null,"name":"Nemotron 3 Embed 1B","display_name":"Nemotron 3 Embed 1B","provider":"nvidia","providers":["nvidia","nvidia-byok"],"category":"embedding","capabilities":["embedding"],"created":1784160000,"description":"NVIDIA Nemotron-3-Embed-1B is a 1.14B-parameter multilingual text embedding model (2048 dimensions, 34 languages) for semantic search, retrieval, and RAG. Built on Ministral-3-3B-Instruct; state-of-the-art on multilingual retrieval benchmarks (MMTEB 71.05, RTEB 72.38). Served via NVIDIA NIM.","context_length":32768,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","model","encoding_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-embed-1b","metrics":"/api/v1/models/nvidia%2Fnemotron-3-embed-1b/metrics"},"per_upstream":[{"backend":"nvidia","model_name":"nvidia/nemotron-3-embed-1b","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["input","model","encoding_format"]},{"backend":"nvidia-byok","model_name":"nvidia/nemotron-3-embed-1b","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":32768},"data_policy":{"zdr":false},"supported_parameters":["input","model","encoding_format"]}]},{"id":"nvidia/nemotron-3-super-120b-a12b","object":"model","canonical_slug":"nvidia/nemotron-3-super-120b-a12b","owned_by":"nvidia","hugging_face_id":null,"name":"Nemotron-3 Super 120B","display_name":"Nemotron-3 Super 120B","provider":"nvidia","providers":["aihubmix-byok","hue","nvidia","openrouter-byok","vercel-byok","deepinfra-byok","nvidia-byok","nousresearch-byok"],"category":"text","capabilities":["chat","streaming","function-calling"],"created":1704067200,"description":"A 120 billion parameter model from NVIDIA's Nemotron-3 family, optimized for efficient text generation and understanding tasks.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nvidia","instruct_type":null},"pricing":{"prompt":"0.085","completion":"0.4","input_per_1m":0.085,"output_per_1m":0.4},"top_provider":{"context_length":262144,"max_completion_tokens":32000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-super-120b-a12b","metrics":"/api/v1/models/nvidia%2Fnemotron-3-super-120b-a12b/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"nvidia-nemotron-3-super-120b-a12b","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"hue","model_name":"nvidia/nemotron-3-super-120b-a12b:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}},{"backend":"nvidia","model_name":"nvidia/nemotron-3-super-120b-a12b","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"nvidia/nemotron-3-super-120b-a12b:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}},{"backend":"vercel-byok","model_name":"nvidia/nemotron-3-super-120b-a12b","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.15,"output_per_1m":0.65},"context":{"max_length":256000,"max_completion_tokens":32000},"data_policy":{"zdr":true},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.085,"output_per_1m":0.4},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"reasoning":true}},{"backend":"nvidia-byok","model_name":"nvidia/nemotron-3-super-120b-a12b","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"nousresearch-byok","model_name":"nvidia/nemotron-3-super-120b-a12b","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.08,"output_per_1m":0.45},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true}}]},{"id":"nvidia/nemotron-3-ultra-550b-a55b","object":"model","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b","owned_by":"nvidia","hugging_face_id":null,"name":"Nemotron 3 Ultra 550B","display_name":"Nemotron 3 Ultra 550B","provider":"nvidia","providers":["aihubmix-byok","openrouter-byok","hue","ollama-byok","baseten-byok","commandcode-byok","router-byok","vercel-byok","gmicloud-byok","nousresearch-byok"],"category":"text","capabilities":["chat","streaming","reasoning","function-calling","thinking"],"created":1780531200,"description":"NVIDIA Nemotron-3-Ultra-550B-A55B is a 550B parameter (55B active) frontier model built on a LatentMoE hybrid architecture combining Mamba-2, MoE, and Attention with Multi-Token Prediction. Features a 1M token context window, configurable reasoning mode (enable_thinking), and strong multilingual support across English, French, Spanish, Italian, German, Japanese, Korean, Hindi, Brazilian Portuguese, and Chinese. Best suited for complex agentic workflows, long-context analysis, tool use, and high-stakes RAG.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nemotron","instruct_type":null},"pricing":{"prompt":"0.5","completion":"2.2","input_per_1m":0.5,"output_per_1m":2.2,"billing":"byok","list_pricing":{"input_per_1m":0.5,"output_per_1m":2.2}},"top_provider":{"context_length":1000000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","include_reasoning","structured_outputs","frequency_penalty","logit_bias","min_p","presence_penalty","reasoning_effort","repetition_penalty","seed","top_k"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b","metrics":"/api/v1/models/nvidia%2Fnemotron-3-ultra-550b-a55b/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"nemotron-3-ultra-550b-a55b-free","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"nvidia/nemotron-3-ultra-550b-a55b:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"nvidia/nemotron-3-ultra-550b-a55b","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.6,"output_per_1m":3.6},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"reasoning":true}},{"backend":"hue","model_name":"nvidia/nemotron-3-ultra-550b-a55b:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1000000,"max_completion_tokens":65536},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning"],"features":{"streaming":true,"reasoning":true}},{"backend":"ollama-byok","model_name":"nemotron-3-ultra:cloud","llm_provider":"ollama-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}},{"backend":"baseten-byok","model_name":"nvidia/nemotron-ultra","llm_provider":"baseten-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"commandcode-byok","model_name":"nvidia/nemotron-3-ultra-550b-a55b","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"router-byok","model_name":"nemotron-3-ultra-nvfp4","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.6,"output_per_1m":2.4},"billing":"byok","context":{"max_length":262000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"nvidia/nemotron-3-ultra-550b-a55b","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.6,"output_per_1m":2.4},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":65000},"data_policy":{"zdr":true},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"gmicloud-byok","model_name":"nvidia/nemotron-3-ultra-550b-a55b","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.8,"output_per_1m":2.6},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"nousresearch-byok","model_name":"nvidia/nemotron-3-ultra-550b-a55b","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.5,"output_per_1m":2.2},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":16384},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"nvidia/nemotron-3.5-content-safety","object":"model","canonical_slug":"nvidia/nemotron-3.5-content-safety","owned_by":"nvidia","hugging_face_id":null,"name":"Nemotron 3.5 Content Safety","display_name":"Nemotron 3.5 Content Safety","provider":"nvidia","providers":["aihubmix-byok","nvidia","nvidia-byok","hue","openrouter-byok"],"category":"multimodal","capabilities":["moderation","chat","streaming","vision"],"created":1780531200,"description":"A compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, returning a safe/unsafe classification, safety category labels, and optional reasoning. Served via NVIDIA NIM.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-content-safety","metrics":"/api/v1/models/nvidia%2Fnemotron-3.5-content-safety/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"nemotron-3.5-content-safety-free","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nvidia","model_name":"nvidia/nemotron-3.5-content-safety","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"vision":true}},{"backend":"nvidia-byok","model_name":"nvidia/nemotron-3.5-content-safety","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"vision":true}},{"backend":"hue","model_name":"nvidia/nemotron-3.5-content-safety:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"vision":true}},{"backend":"openrouter-byok","model_name":"nvidia/nemotron-3.5-content-safety:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"vision":true}}]},{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","object":"model","canonical_slug":"nvidia/nemotron-3.5-lightning-30b-a3b","owned_by":"nvidia","hugging_face_id":null,"name":"Nemotron 3.5 Lightning 30B A3B","display_name":"Nemotron 3.5 Lightning 30B A3B","provider":"nvidia","providers":["nvidia-byok","hue","openrouter-byok","router-byok","vercel-byok","nousresearch-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding"],"created":1785542400,"description":"NVIDIA Nemotron 3.5 Lightning 30B A3B is a sparse MoE chat model optimized for low-latency agentic workloads on NVIDIA NIM.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nvidia","instruct_type":null},"pricing":{"prompt":"0.025","completion":"0.12","input_per_1m":0.025,"output_per_1m":0.12,"billing":"byok","list_pricing":{"input_per_1m":0.025,"output_per_1m":0.12}},"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","frequency_penalty","include_reasoning","logit_bias","logprobs","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","structured_outputs","top_k","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-lightning-30b-a3b","metrics":"/api/v1/models/nvidia%2Fnemotron-3.5-lightning-30b-a3b/metrics"},"per_upstream":[{"backend":"nvidia-byok","model_name":"nvidia/nemotron-3.5-lightning-30b-a3b","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}},{"backend":"hue","model_name":"nvidia/nemotron-3.5-lightning:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1000000,"max_completion_tokens":65536},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"nvidia/nemotron-3.5-lightning:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":65536},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"nvidia/nemotron-3.5-lightning","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":65536},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}},{"backend":"router-byok","model_name":"nemotron-lightning-3.5-30b-a3b","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0.2},"billing":"byok","context":{"max_length":262000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"nvidia/nemotron-3.5-lightning","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0.2},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"nvidia/nemotron-3.5-lightning","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.025,"output_per_1m":0.12},"billing":"byok","context":{"max_length":262144,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"nvidia/nemotron-3.5-super-vl-120b-a12b","object":"model","canonical_slug":"nvidia/nemotron-3.5-super-vl-120b-a12b","owned_by":"nvidia","hugging_face_id":null,"name":"Nemotron 3.5 Super VL 120B A12B","display_name":"Nemotron 3.5 Super VL 120B A12B","provider":"nvidia","providers":["nvidia","nvidia-byok"],"category":"multimodal","capabilities":["chat","streaming","function-calling","vision","reasoning","coding"],"created":1792022400,"description":"NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, document understanding and video understanding. A hybrid Mamba-2 and Transformer mixture-of-experts with 120B total and 12B active parameters, and up to 1M tokens of context.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Nvidia","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":1000000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3.5-super-vl-120b-a12b","metrics":"/api/v1/models/nvidia%2Fnemotron-3.5-super-vl-120b-a12b/metrics"},"per_upstream":[{"backend":"nvidia","model_name":"nvidia/nemotron-3.5-super-vl-120b-a12b","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nvidia-byok","model_name":"nvidia/nemotron-3.5-super-vl-120b-a12b","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"vision":true}}]},{"id":"nvidia/nemotron-parse-2.0","object":"model","canonical_slug":"nvidia/nemotron-parse-2.0","owned_by":"nvidia","hugging_face_id":null,"name":"Nemotron Parse 2.0","display_name":"Nemotron Parse 2.0","provider":"nvidia","providers":["nvidia","nvidia-byok"],"category":"multimodal","capabilities":["chat","streaming","vision"],"created":1785715200,"description":"NVIDIA Nemotron Parse 2.0 is a document-understanding VLM: page image in, structured text out (markdown, layout classes, bounding boxes, reading order). Served via NVIDIA NIM OpenAI-compatible /v1/chat/completions. Not image generation.","context_length":8192,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nemotron","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/nemotron-parse-2.0","metrics":"/api/v1/models/nvidia%2Fnemotron-parse-2.0/metrics"},"per_upstream":[{"backend":"nvidia","model_name":"nvidia/nemotron-parse-2.0","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"vision":true}},{"backend":"nvidia-byok","model_name":"nvidia/nemotron-parse-2.0","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":8192},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"vision":true}}]},{"id":"nvidia/riva-translate-4b-instruct-v2","object":"model","canonical_slug":"nvidia/riva-translate-4b-instruct-v2","owned_by":"nvidia","hugging_face_id":null,"name":"Riva Translate 4B Instruct v2","display_name":"Riva Translate 4B Instruct v2","provider":"nvidia","providers":["nvidia","nvidia-byok"],"category":"text","capabilities":["chat","streaming","translation"],"created":1778803200,"description":"NVIDIA's Riva Translate 4B Instruct v2, a compact 4B-parameter instruction-tuned model optimized for high-quality neural machine translation across 30+ languages. Served via NVIDIA NIM.","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Riva","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/nvidia/riva-translate-4b-instruct-v2","metrics":"/api/v1/models/nvidia%2Friva-translate-4b-instruct-v2/metrics"},"per_upstream":[{"backend":"nvidia","model_name":"nvidia/riva-translate-4b-instruct-v2","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}},{"backend":"nvidia-byok","model_name":"nvidia/riva-translate-4b-instruct-v2","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":4096},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}}]},{"id":"openai/gpt-oss-20b","object":"model","canonical_slug":"openai/gpt-oss-20b","owned_by":"openai","hugging_face_id":null,"name":"GPT-OSS 20B","display_name":"GPT-OSS 20B","provider":"OpenAI","providers":["aihubmix-byok","huggingface-byok","deepinfra-byok","cline-byok","openrouter-byok","ovhcloud-byok","router-byok","vercel-byok","pollinations","siliconflow-byok","nvidia-byok","nousresearch-byok"],"category":"text","capabilities":["chat","reasoning","function-calling","streaming","coding"],"created":1744070400,"description":"OpenAI's open-weight model designed for powerful reasoning, agentic tasks, and versatile developer use cases - optimized for lower latency and specialized use-cases at the edge","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.018","completion":"0.09","input_per_1m":0.018,"output_per_1m":0.09},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs","frequency_penalty","logit_bias","logprobs","min_p","presence_penalty","reasoning_effort","repetition_penalty","seed","top_k","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openai/gpt-oss-20b","metrics":"/api/v1/models/openai%2Fgpt-oss-20b/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"gpt-oss-20b","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"huggingface-byok","model_name":"openai/gpt-oss-20b","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}},{"backend":"deepinfra-byok","model_name":"openai/gpt-oss-20b","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"]},{"backend":"cline-byok","model_name":"openai/gpt-oss-20b","llm_provider":"cline-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"openai/gpt-oss-20b","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"function_calling":true}},{"backend":"ovhcloud-byok","model_name":"gpt-oss-20b","llm_provider":"ovhcloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0.18},"context":{"max_length":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"router-byok","model_name":"gpt-oss-20b","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.07,"output_per_1m":0.3},"context":{"max_length":131000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"openai/gpt-oss-20b","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072,"max_completion_tokens":8192},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"pollinations","model_name":"openai-fast","llm_provider":"pollinations","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true,"reasoning":true}},{"backend":"siliconflow-byok","model_name":"openai/gpt-oss-20b","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"nvidia-byok","model_name":"openai/gpt-oss-20b","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.03,"output_per_1m":0.14},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"nousresearch-byok","model_name":"openai/gpt-oss-20b","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.018,"output_per_1m":0.09},"context":{"max_length":131072,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"openrouter/bodybuilder","object":"model","canonical_slug":"openrouter/bodybuilder","owned_by":"openrouter","hugging_face_id":null,"name":"OpenRouter: Body Builder (beta)","display_name":"OpenRouter: Body Builder (beta)","provider":"OpenRouter","providers":["respan-byok"],"category":"text","capabilities":["chat","streaming"],"created":1764892800,"description":"Body Builder turns a natural-language request into a structured OpenRouter API request object. Describe what you want to do with AI models and it builds the matching call. Beta router with a 128K context window. Available with a user-owned Respan key (BYOK).","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Openrouter","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/bodybuilder","metrics":"/api/v1/models/openrouter%2Fbodybuilder/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"bodybuilder","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true}}]},{"id":"openrouter/pareto-code","object":"model","canonical_slug":"openrouter/pareto-code","owned_by":"openrouter","hugging_face_id":null,"name":"OpenRouter: Pareto Code Router","display_name":"OpenRouter: Pareto Code Router","provider":"OpenRouter","providers":["respan-byok"],"category":"text","capabilities":["chat","streaming","function-calling","reasoning","coding"],"created":1776729600,"description":"The Pareto Code Router keeps a tiered shortlist of strong coding models ranked by Artificial Analysis coding percentiles. Set min_coding_score between 0 and 1 on the pareto-router plugin to trade quality against cost. 2M-token context. Available with a user-owned Respan key (BYOK).","context_length":2000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Openrouter","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":2000000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","seed"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/openrouter/pareto-code","metrics":"/api/v1/models/openrouter%2Fpareto-code/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"pareto-code","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":2000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","seed"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"perplexity/pplx-decider-v1-27b","object":"model","canonical_slug":"perplexity/pplx-decider-v1-27b","owned_by":"perplexity","hugging_face_id":null,"name":"PPLX Decider v1 (27B)","display_name":"PPLX Decider v1 (27B)","provider":"perplexity","providers":["perplexity-byok"],"category":"text","capabilities":["systemone"],"created":1790812800,"description":"PPLX Decider v1 (27B) is Perplexity's multimodal decision model: send application state and typed questions (noul / choice / score) and get back a probability distribution over a fixed set of answers — it returns probabilities, not generated chat text, and produces no free-form output. `state` may be a string, an object, or an array of OpenAI-style `image_url` parts carrying base64 PNG/JPEG/WebP data URLs, so it also scores images. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Perplexity","instruct_type":null},"pricing":{"prompt":"0.04","completion":"0","input_per_1m":0.04,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.04,"output_per_1m":0}},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/pplx-decider-v1-27b","metrics":"/api/v1/models/perplexity%2Fpplx-decider-v1-27b/metrics"},"per_upstream":[{"backend":"perplexity-byok","model_name":"pplx-decider-v1-27b","llm_provider":"perplexity-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.04,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"perplexity/pplx-decider-v1.1-27b","object":"model","canonical_slug":"perplexity/pplx-decider-v1.1-27b","owned_by":"perplexity","hugging_face_id":null,"name":"PPLX Decider v1.1 (27B)","display_name":"PPLX Decider v1.1 (27B)","provider":"perplexity","providers":["perplexity-byok","hue"],"category":"text","capabilities":["systemone"],"created":1791244800,"description":"PPLX Decider v1.1 (27B) is a newer checkpoint of Perplexity's multimodal decision model, with the same Decisions API contract as v1: send application state and typed questions (noul / choice / score) and get back a probability distribution over a fixed set of answers — it returns probabilities, not generated chat text, and produces no free-form output. `state` may be a string, an object, or an array of OpenAI-style `image_url` parts carrying base64 PNG/JPEG/WebP data URLs, so it also scores images. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Perplexity","instruct_type":null},"pricing":{"prompt":"0.02","completion":"0","input_per_1m":0.02,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.02,"output_per_1m":0}},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/pplx-decider-v1.1-27b","metrics":"/api/v1/models/perplexity%2Fpplx-decider-v1.1-27b/metrics"},"per_upstream":[{"backend":"perplexity-byok","model_name":"pplx-decider-v1.1-27b","llm_provider":"perplexity-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.02,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"perplexity/pplx-decider-v1.1-27b","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.02,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"perplexity/pplx-embed-v1-0.6b","object":"model","canonical_slug":"perplexity/pplx-embed-v1-0.6b","owned_by":"perplexity","hugging_face_id":null,"name":"pplx-embed v1 0.6B","display_name":"pplx-embed v1 0.6B","provider":"perplexity","providers":["respan-byok"],"category":"embedding","capabilities":["embedding"],"created":1768348800,"description":"pplx-embed-v1-0.6B is Perplexity's lightweight text embedding model for web-scale dense retrieval, aimed at low-latency use. 32K-token input.","context_length":32000,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.004","completion":"0","input_per_1m":0.004,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.004,"output_per_1m":0}},"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","model","encoding_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/perplexity/pplx-embed-v1-0.6b","metrics":"/api/v1/models/perplexity%2Fpplx-embed-v1-0.6b/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"pplx-embed-v1-0.6b","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.004,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["input","model","encoding_format"]}]},{"id":"poolside/laguna-s-2.1","object":"model","canonical_slug":"poolside/laguna-s-2.1","owned_by":"poolside","hugging_face_id":null,"name":"Laguna S 2.1","display_name":"Laguna S 2.1","provider":"poolside","providers":["aihubmix-byok","poolside-byok","openrouter-byok","nousresearch-byok","hermes-agent","hermes-agent-byok","hue","commandcode-byok","vercel-byok"],"category":"text","capabilities":["chat","streaming","coding","reasoning","function-calling"],"created":1784592000,"description":"A 118B total parameter Mixture-of-Experts coding model with 8B activated parameters per token, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE. Supports tool calling, reasoning, thinking and no-thinking modes, with a context window of up to 1M tokens. Open-weight under the OpenMDW-1.1 License.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Poolside","instruct_type":null},"pricing":{"prompt":"0.1","completion":"0.2","input_per_1m":0.1,"output_per_1m":0.2,"billing":"byok","list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2}},"top_provider":{"context_length":1048576,"max_completion_tokens":32768,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/poolside/laguna-s-2.1","metrics":"/api/v1/models/poolside%2Flaguna-s-2.1/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"laguna-s-2.1","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"poolside-byok","model_name":"poolside/laguna-s-2.1","llm_provider":"poolside-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true}},{"backend":"openrouter-byok","model_name":"poolside/laguna-s-2.1:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"poolside/laguna-s-2.1:free","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"hermes-agent","model_name":"poolside/laguna-s-2.1:free","llm_provider":"hermes-agent","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"hermes-agent-byok","model_name":"poolside/laguna-s-2.1:free","llm_provider":"hermes-agent-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"hue","model_name":"poolside/laguna-s-2.1:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"commandcode-byok","model_name":"poolside/laguna-s-2.1-free","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":256000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"poolside/laguna-s-2.1-free","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":256000,"max_completion_tokens":32768},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"poolside/laguna-xs-2.1","object":"model","canonical_slug":"poolside/laguna-xs-2.1","owned_by":"poolside","hugging_face_id":null,"name":"Laguna XS 2.1","display_name":"Laguna XS 2.1","provider":"poolside","providers":["aihubmix-byok","poolside-byok","openrouter-byok","nousresearch-byok","hermes-agent","hermes-agent-byok","hue"],"category":"text","capabilities":["chat","streaming","coding","reasoning","function-calling"],"created":1783555200,"description":"The latest coding agent model in the 33B-A3B category from Poolside and a step forward from Laguna XS.2. Combines tool calling and reasoning with a compact footprint, offering a 256K context window and up to 32K output tokens. Quantized to FP8 for fast, cost-efficient agentic coding workflows. Subject to the OpenMDW-1.1 License.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Poolside","instruct_type":null},"pricing":{"prompt":"0.1","completion":"0.2","input_per_1m":0.1,"output_per_1m":0.2,"billing":"byok","list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2}},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/poolside/laguna-xs-2.1","metrics":"/api/v1/models/poolside%2Flaguna-xs-2.1/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"laguna-xs-2.1","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.1,"output_per_1m":0.2},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"poolside-byok","model_name":"poolside/laguna-xs-2.1","llm_provider":"poolside-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262112},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true}},{"backend":"openrouter-byok","model_name":"poolside/laguna-xs-2.1:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"poolside/laguna-xs-2.1:free","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"hermes-agent","model_name":"poolside/laguna-xs-2.1:free","llm_provider":"hermes-agent","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"hermes-agent-byok","model_name":"poolside/laguna-xs-2.1:free","llm_provider":"hermes-agent-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"hue","model_name":"poolside/laguna-xs-2.1:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"reflection/beam-1.0","object":"model","canonical_slug":"reflection/beam-1.0","owned_by":"reflection","hugging_face_id":null,"name":"Beam 1.0","display_name":"Beam 1.0","provider":"reflection","providers":["hermes-agent","hermes-agent-byok"],"category":"text","capabilities":["chat","streaming","reasoning","coding","function-calling","structured-output"],"created":1791158400,"description":"Beam 1.0 is Reflection's open-weights mixture-of-experts model — 501B total parameters, 23B active across 256 experts — built for token-efficient reasoning, agentic tool use, and software-engineering workloads. Reasoning is always on with a tunable effort level; the Apache-2.0 weights are on Hugging Face.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Reflection","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","top_k","tools","tool_choice","response_format","reasoning","include_reasoning","reasoning_effort"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/reflection/beam-1.0","metrics":"/api/v1/models/reflection%2Fbeam-1.0/metrics"},"reasoning":{"levels":["low","medium","high","xhigh","max"],"default":"max"},"per_upstream":[{"backend":"hermes-agent","model_name":"reflection/beam-1.0-501b-a23b:free","llm_provider":"hermes-agent","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","top_k","tools","tool_choice","response_format","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"hermes-agent-byok","model_name":"reflection/beam-1.0-501b-a23b:free","llm_provider":"hermes-agent-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","top_k","tools","tool_choice","response_format","reasoning","include_reasoning","reasoning_effort"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"respan/span-01-lite","object":"model","canonical_slug":"respan/span-01-lite","owned_by":"respan","hugging_face_id":null,"name":"Span-01 Lite","display_name":"Span-01 Lite","provider":"respan","providers":["hue","openrouter-byok"],"category":"text","capabilities":["systemone","noul-only"],"created":1790380800,"description":"Span-01 Lite is a behavior-scoring classifier from Respan — the free, lighter tier of Span-01, a 4B model trained with RLAIF on classification reasoning rather than fixed taxonomies. Send a conversation span and a set of plain-language behavior definitions and get a present / absent / not_observable probability per behavior in a single forward pass, with no token-by-token generation. Respan reports it ahead of Jev 1.13 and Sonnet 5 on their English and multilingual behavior-detection suites. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":0,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Respan","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/respan/span-01-lite","metrics":"/api/v1/models/respan%2Fspan-01-lite/metrics"},"per_upstream":[{"backend":"hue","model_name":"respan/span-01-lite:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"respan/span-01-lite:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"respan/span-01-lite","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"respan/span-01-lite","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"respan/span-01","object":"model","canonical_slug":"respan/span-01","owned_by":"respan","hugging_face_id":null,"name":"Span-01","display_name":"Span-01","provider":"respan","providers":["openrouter-byok","hue"],"category":"text","capabilities":["systemone","noul-only"],"created":1790380800,"description":"Span-01 is a behavior-scoring classifier from Respan, a 4B model trained with RLAIF on classification reasoning rather than fixed taxonomies. Send a conversation span and a set of plain-language behavior definitions and get a present / absent / not_observable probability per behavior in a single forward pass, with no token-by-token generation. It is the full tier of the family; Span-01 Lite is the lighter tier. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":0,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Respan","instruct_type":null},"pricing":{"prompt":"0.02","completion":"0","input_per_1m":0.02,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.02,"output_per_1m":0}},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/respan/span-01","metrics":"/api/v1/models/respan%2Fspan-01/metrics"},"per_upstream":[{"backend":"openrouter-byok","model_name":"respan/span-01","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.02,"output_per_1m":0},"billing":"byok","data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"respan/span-01","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.02,"output_per_1m":0},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"scira/amos-1-large","object":"model","canonical_slug":"scira/amos-1-large","owned_by":"scira","hugging_face_id":null,"name":"Amos 1 Large","display_name":"Amos 1 Large","provider":"scira","providers":["scira"],"category":"text","capabilities":["systemone"],"created":1791763200,"description":"Amos 1 Large is an open-weight (Apache 2.0) decision model from Scira: a 27B decoder fine-tuned from Qwen3.8-27B and Scira's most capable decision model, for multi-step questions, long policies and trade-offs. Context 128K tokens; about 122 ms median server time. Send a state and typed questions (noul / choice / score) and get a calibrated probability per answer in one pass — not generated chat text. English only. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). Scira trains on every request, so it is skipped when Always enforce ZDR is on (Dashboard → Privacy).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Scira","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":131072,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/scira/amos-1-large","metrics":"/api/v1/models/scira%2Famos-1-large/metrics"},"per_upstream":[{"backend":"scira","model_name":"amos-1-large","llm_provider":"scira","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":131072},"data_policy":{"zdr":false,"prompt_training":true},"supported_parameters":["state","model","questions"]}]},{"id":"scira/amos-1-mini","object":"model","canonical_slug":"scira/amos-1-mini","owned_by":"scira","hugging_face_id":null,"name":"Amos 1 Mini","display_name":"Amos 1 Mini","provider":"scira","providers":["scira"],"category":"text","capabilities":["systemone"],"created":1790899200,"description":"Amos 1 Mini is an open-weight (Apache 2.0) decision model from Scira: a 0.5B encoder that answers every question in one pass on a CPU — simple decisions where the answer is in the case. Reads 9K tokens per pass; about 27 ms median server time. Send a state and typed questions (noul / choice / score) and get a calibrated probability per answer in one pass — not generated chat text. English only. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). Scira trains on every request, so it is skipped when Always enforce ZDR is on (Dashboard → Privacy).","context_length":9216,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Scira","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":9216,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/scira/amos-1-mini","metrics":"/api/v1/models/scira%2Famos-1-mini/metrics"},"per_upstream":[{"backend":"scira","model_name":"amos-1-mini","llm_provider":"scira","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":9216},"data_policy":{"zdr":false,"prompt_training":true},"supported_parameters":["state","model","questions"]}]},{"id":"scira/amos-1-small","object":"model","canonical_slug":"scira/amos-1-small","owned_by":"scira","hugging_face_id":null,"name":"Amos 1 Small","display_name":"Amos 1 Small","provider":"scira","providers":["scira"],"category":"text","capabilities":["systemone"],"created":1791763200,"description":"Amos 1 Small is an open-weight (Apache 2.0) decision model from Scira: a 2B decoder fine-tuned from Qwen3.5-2B, built for volume and for cases with photos. Context 256K tokens; about 48 ms median server time. Send a state and typed questions (noul / choice / score) and get a calibrated probability per answer in one pass — not generated chat text. English only. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler). Scira trains on every request, so it is skipped when Always enforce ZDR is on (Dashboard → Privacy).","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Scira","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/scira/amos-1-small","metrics":"/api/v1/models/scira%2Famos-1-small/metrics"},"per_upstream":[{"backend":"scira","model_name":"amos-1-small","llm_provider":"scira","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false,"prompt_training":true},"supported_parameters":["state","model","questions"]}]},{"id":"sentence-transformers/all-minilm-l6-v2","object":"model","canonical_slug":"sentence-transformers/all-minilm-l6-v2","owned_by":"sentence-transformers","hugging_face_id":null,"name":"all-MiniLM-L6-v2","display_name":"all-MiniLM-L6-v2","provider":"sentence-transformers","providers":["respan-byok"],"category":"embedding","capabilities":["embedding"],"created":1646179200,"description":"all-MiniLM-L6-v2 maps sentences and short paragraphs to 384-dimensional vectors for retrieval, clustering and semantic similarity. 512-token input.","context_length":512,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.005","completion":"0","input_per_1m":0.005,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.005,"output_per_1m":0}},"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","model","encoding_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/sentence-transformers/all-minilm-l6-v2","metrics":"/api/v1/models/sentence-transformers%2Fall-minilm-l6-v2/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"all-minilm-l6-v2","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.005,"output_per_1m":0},"billing":"byok","context":{"max_length":512},"data_policy":{"zdr":false},"supported_parameters":["input","model","encoding_format"]}]},{"id":"stealth/glyph-cluster","object":"model","canonical_slug":"stealth/glyph-cluster","owned_by":"stealth","hugging_face_id":null,"name":"Glyph Cluster","display_name":"Glyph Cluster","provider":"stealth","providers":["kilo","vercel-byok"],"category":"text","capabilities":["chat","streaming","function-calling","reasoning"],"created":1791331200,"description":"Glyph Cluster is a reasoning model designed for coding and long-context workloads. It is a stealth preview model from a third-party provider who has chosen to remain anonymous during this preview. Free during stealth for Pro/Enterprise Vercel users and on Kilo's anonymous free tier. Text-only input; function calling supported; no structured outputs; no ZDR (prompts may be used for training).","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Stealth","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0},"top_provider":{"context_length":256000,"max_completion_tokens":256000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning","messages","model","prompt","stream","max_completion_tokens","top_p","tool_choice","reasoning_effort","stop"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/stealth/glyph-cluster","metrics":"/api/v1/models/stealth%2Fglyph-cluster/metrics"},"per_upstream":[{"backend":"kilo","model_name":"stealth/glyph-cluster","llm_provider":"kilo","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":256000,"max_completion_tokens":256000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"stealth/glyph-cluster","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":256000},"data_policy":{"zdr":false},"supported_parameters":["messages","model","prompt","stream","max_tokens","max_completion_tokens","temperature","top_p","tools","tool_choice","reasoning_effort","stop"]}]},{"id":"stepfun/step-5-preview","object":"model","canonical_slug":"stepfun/step-5-preview","owned_by":"stepfun","hugging_face_id":null,"name":"Step 5 Preview","display_name":"Step 5 Preview","provider":"StepFun","providers":["aihubmix-byok","kilo","openrouter-byok","vercel-byok","nousresearch-byok","novita-byok"],"category":"text","capabilities":["chat","streaming","reasoning","coding","vision","function-calling","structured-output"],"created":1789862400,"description":"Step 5 Preview is StepFun's next-generation flagship base model designed for real-world tasks, with a focus on programming and professional expertise. A multimodal (text, image, video in / text out) base model with a 1M-token context and adjustable reasoning effort.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"StepFun","instruct_type":null},"pricing":{"prompt":"1","completion":"2.7","input_per_1m":1,"output_per_1m":2.7},"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","response_format","reasoning","include_reasoning"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/stepfun/step-5-preview","metrics":"/api/v1/models/stepfun%2Fstep-5-preview/metrics"},"reasoning":{"levels":["low","medium","high"],"default":"medium"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"step-5-preview","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.08,"output_per_1m":3.0888},"context":{"max_length":1000000,"max_completion_tokens":64000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"kilo","model_name":"stepfun/step-5-preview-free","llm_provider":"kilo","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","tools","reasoning","include_reasoning"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"stepfun/step-5-preview","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1,"output_per_1m":2.7},"context":{"max_length":1000000,"max_completion_tokens":64000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"stepfun/step-5-preview","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1,"output_per_1m":2.7},"context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"stepfun/step-5-preview","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1,"output_per_1m":2.7},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"novita-byok","model_name":"stepfun/step-5-preview","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1,"output_per_1m":2.7},"context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"strandsagents/strands-decider-2b","object":"model","canonical_slug":"strandsagents/strands-decider-2b","owned_by":"strandsagents","hugging_face_id":null,"name":"Strands Decider 2B","display_name":"Strands Decider 2B","provider":"strandsagents","providers":["strands-decider-byok"],"category":"text","capabilities":["systemone"],"created":1790812800,"description":"Strands Decider 2B is AWS Strands Labs' small open-weight decision model: send application state and typed questions (noul / choice / score) and get calibrated probabilities back in one forward pass — it returns answers with confidence scores, not generated chat text, and produces no free-form output. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":4096,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Strandsagents","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":4096,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/strandsagents/strands-decider-2b","metrics":"/api/v1/models/strandsagents%2Fstrands-decider-2b/metrics"},"per_upstream":[{"backend":"strands-decider-byok","model_name":"StrandsAgents/strands-decider-2B-hobson-v19","llm_provider":"strands-decider-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":4096},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"subquadratic/subq-preview","object":"model","canonical_slug":"subquadratic/subq-preview","owned_by":"subquadratic","hugging_face_id":null,"name":"SubQ Preview","display_name":"SubQ Preview","provider":"subquadratic","providers":["subq-byok"],"category":"text","capabilities":["chat","reasoning","function-calling","structured-output","streaming"],"created":1777939200,"description":"SubQ Preview is Subquadratic's long-context chat model, built on its Subquadratic Sparse Attention (SSA) architecture for reasoning over very large inputs such as whole repositories, contract archives and filings. It is in early access: model availability and features may change. Text in, text out, with file (document) input, function calling, JSON-schema structured outputs and a reasoning_effort control (none to max). SubQ serves it on Chat Completions and the Responses API. Reasoning text is never returned; reasoning tokens bill as output.","context_length":0,"architecture":{"modality":"text->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Subquadratic","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","reasoning_effort","response_format","tools","tool_choice"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/subquadratic/subq-preview","metrics":"/api/v1/models/subquadratic%2Fsubq-preview/metrics"},"per_upstream":[{"backend":"subq-byok","model_name":"subq-preview","llm_provider":"subq-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","reasoning_effort","response_format","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}}]},{"id":"subquadratic/subq-snap-preview","object":"model","canonical_slug":"subquadratic/subq-snap-preview","owned_by":"subquadratic","hugging_face_id":null,"name":"SubQ Snap Preview","display_name":"SubQ Snap Preview","provider":"subquadratic","providers":["subq-byok"],"category":"text","capabilities":["systemone"],"created":1791590400,"description":"SubQ Snap Preview is Subquadratic's System One decision model for routing, guardrails, triage and other fast decisions. It is in public preview. Send application state and typed questions (noul / choice / score) and get back typed answers with probabilities and confidence — not generated chat text. SubQ documents text input and output plus image input (PNG, JPEG or WebP, up to 4 images). Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":0,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Subquadratic","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":0,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/subquadratic/subq-snap-preview","metrics":"/api/v1/models/subquadratic%2Fsubq-snap-preview/metrics"},"per_upstream":[{"backend":"subq-byok","model_name":"subq-snap-preview","llm_provider":"subq-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"thenlper/gte-base","object":"model","canonical_slug":"thenlper/gte-base","owned_by":"thenlper","hugging_face_id":null,"name":"GTE Base","display_name":"GTE Base","provider":"thenlper","providers":["respan-byok"],"category":"embedding","capabilities":["embedding"],"created":1690416000,"description":"GTE Base is an English text embedding model that maps sentences and paragraphs to 768-dimensional vectors for semantic search, similarity and clustering. 512-token input.","context_length":512,"architecture":{"modality":"text->embedding","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.005","completion":"0","input_per_1m":0.005,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.005,"output_per_1m":0}},"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["input","model","encoding_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thenlper/gte-base","metrics":"/api/v1/models/thenlper%2Fgte-base/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"gte-base","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.005,"output_per_1m":0},"billing":"byok","context":{"max_length":512},"data_policy":{"zdr":false},"supported_parameters":["input","model","encoding_format"]}]},{"id":"thinkingmachines/inkling-small","object":"model","canonical_slug":"thinkingmachines/inkling-small","owned_by":"thinkingmachines","hugging_face_id":null,"name":"Inkling Small","display_name":"Inkling Small","provider":"thinkingmachines","providers":["hue","openrouter-byok","commandcode-byok","nousresearch-byok","hermes-agent-byok","vercel-byok","deepinfra-byok","huggingface-byok"],"category":"text","capabilities":["chat","streaming","reasoning","vision","function-calling"],"created":1785369600,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total and a 1M-token context window. Distinct from thinkingmachines/inkling. Served free via the platform free pool on the OpenRouter :free wire, with paid BYOK as a fallback.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Thinkingmachines","instruct_type":null},"pricing":{"prompt":"0.45","completion":"1.2","input_per_1m":0.45,"output_per_1m":1.2,"billing":"byok","list_pricing":{"input_per_1m":0.45,"output_per_1m":1.2}},"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","reasoning","tool_choice","include_reasoning","response_format","structured_outputs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling-small","metrics":"/api/v1/models/thinkingmachines%2Finkling-small/metrics"},"per_upstream":[{"backend":"hue","model_name":"thinkingmachines/inkling-small:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576,"max_completion_tokens":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","reasoning"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"thinkingmachines/inkling-small:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","reasoning"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"thinkingmachines/inkling-small","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.45,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"commandcode-byok","model_name":"thinkingmachines/inkling-small","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"thinkingmachines/inkling-small","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"hermes-agent-byok","model_name":"thinkingmachines/inkling-small","llm_provider":"hermes-agent-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"thinkingmachines/inkling-small","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.45,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":1000000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"thinkingmachines/Inkling-Small","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.45,"output_per_1m":1.2},"billing":"byok","context":{"max_length":524288},"data_policy":{"zdr":false},"features":{"streaming":true,"vision":true,"reasoning":true}},{"backend":"huggingface-byok","model_name":"thinkingmachines/Inkling-Small","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":524288},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}}]},{"id":"thinkingmachines/inkling","object":"model","canonical_slug":"thinkingmachines/inkling","owned_by":"thinkingmachines","hugging_face_id":null,"name":"Inkling","display_name":"Inkling","provider":"thinkingmachines","providers":["hue","openrouter-byok","commandcode-byok","vercel-byok","deepinfra-byok","huggingface-byok","venice-byok","nousresearch-byok"],"category":"text","capabilities":["chat","streaming","reasoning","vision","function-calling"],"created":1784073600,"description":"Inkling is Thinking Machines Lab's first open-weights foundation model: a 975B-parameter multimodal Mixture-of-Experts transformer (41B active, 256 experts) with a 1M token context window, switchable reasoning effort, and tool use. Accepts text, image, and audio inputs; outputs text. Pretrained on 45T tokens.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Thinkingmachines","instruct_type":null},"pricing":{"prompt":"0.95","completion":"4.05","input_per_1m":0.95,"output_per_1m":4.05,"billing":"byok","list_pricing":{"input_per_1m":0.95,"output_per_1m":4.05}},"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs","frequency_penalty","logit_bias","min_p","presence_penalty","reasoning_effort","repetition_penalty","seed","top_k"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/thinkingmachines/inkling","metrics":"/api/v1/models/thinkingmachines%2Finkling/metrics"},"per_upstream":[{"backend":"hue","model_name":"thinkingmachines/inkling:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"thinkingmachines/inkling:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"thinkingmachines/inkling","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4.05},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","reasoning"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"commandcode-byok","model_name":"thinkingmachines/inkling","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":256000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"vercel-byok","model_name":"thinkingmachines/inkling","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1,"output_per_1m":4.05},"billing":"byok","context":{"max_length":256000,"max_completion_tokens":256000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"thinkingmachines/Inkling","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4.05},"billing":"byok","context":{"max_length":524288},"data_policy":{"zdr":false},"features":{"streaming":true,"vision":true,"reasoning":true}},{"backend":"huggingface-byok","model_name":"thinkingmachines/Inkling","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"venice-byok","model_name":"inkling","llm_provider":"venice-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.25,"output_per_1m":5.0625},"billing":"byok","context":{"max_length":524288,"max_completion_tokens":65536},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"thinkingmachines/inkling","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.95,"output_per_1m":4.05},"billing":"byok","context":{"max_length":524288,"max_completion_tokens":262144},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"typesafe/jev","object":"model","canonical_slug":"typesafe/jev","owned_by":"typesafe","hugging_face_id":null,"name":"Jev","display_name":"Jev","provider":"typesafe","providers":["typesafe-byok","llmgateway-byok","vercel-byok","aihubmix-byok","experiential-byok","openrouter-byok","aimlapi-byok","autojev-byok","hue"],"category":"text","capabilities":["systemone"],"created":1789516800,"description":"TypeSafe Jev is a decision model: send application state and typed questions (noul / choice / score) and get structured answers with probabilities — not generated chat text. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":64000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Typesafe","instruct_type":null},"pricing":{"prompt":"0.042","completion":"0","input_per_1m":0.042,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.042,"output_per_1m":0}},"top_provider":{"context_length":64000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/typesafe/jev","metrics":"/api/v1/models/typesafe%2Fjev/metrics"},"per_upstream":[{"backend":"typesafe-byok","model_name":"jev-latest","llm_provider":"typesafe-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"typesafe-byok","model_name":"jev-1.13.0","llm_provider":"typesafe-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"typesafe-byok","model_name":"jev-preview","llm_provider":"typesafe-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"llmgateway-byok","model_name":"jev-1.13.0","llm_provider":"llmgateway-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"vercel-byok","model_name":"typesafe-ai/jev","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"aihubmix-byok","model_name":"jev-1.13","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.0462,"output_per_1m":0},"billing":"byok","context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"aihubmix-byok","model_name":"jev-latest","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.0462,"output_per_1m":0},"billing":"byok","context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"experiential-byok","model_name":"jev-latest","llm_provider":"experiential-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"typesafe/jev-1.13","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"openrouter-byok","model_name":"~typesafe/jev-latest","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"aimlapi-byok","model_name":"typesafe/jev","llm_provider":"aimlapi-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.0577668,"output_per_1m":0},"billing":"byok","context":{"max_length":32000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"autojev-byok","model_name":"~typesafe/jev-latest","llm_provider":"autojev-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"typesafe/jev-1.13","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.042,"output_per_1m":0},"context":{"max_length":64000},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"upstage/solar-decide-flash","object":"model","canonical_slug":"upstage/solar-decide-flash","owned_by":"upstage","hugging_face_id":null,"name":"Solar Decide Flash","display_name":"Solar Decide Flash","provider":"upstage","providers":["openrouter-byok","hue"],"category":"text","capabilities":["systemone"],"created":1791417600,"description":"Upstage Solar Decide Flash is the low-latency variant of Solar Decide, a decision model served as a System One endpoint on Solar Mini 4: send application state and typed questions (noul / choice / score) and get structured answers back — not generated chat text. It has a 524,288-token context window. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Upstage","instruct_type":null},"pricing":{"prompt":"0.05","completion":"0","input_per_1m":0.05,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.05,"output_per_1m":0}},"top_provider":{"context_length":524288,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/upstage/solar-decide-flash","metrics":"/api/v1/models/upstage%2Fsolar-decide-flash/metrics"},"per_upstream":[{"backend":"openrouter-byok","model_name":"upstage/solar-decide-flash","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0},"billing":"byok","context":{"max_length":524288},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"upstage/solar-decide-flash","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0},"context":{"max_length":524288},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"upstage/solar-decide","object":"model","canonical_slug":"upstage/solar-decide","owned_by":"upstage","hugging_face_id":null,"name":"Solar Decide","display_name":"Solar Decide","provider":"upstage","providers":["openrouter-byok","hue"],"category":"text","capabilities":["systemone"],"created":1790553600,"description":"Upstage Solar Decide is a decision model served as a System One endpoint on Solar Mini 4: send application state and typed questions (noul / choice / score) and get structured answers back — not generated chat text. It has a 524,288-token context window. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Upstage","instruct_type":null},"pricing":{"prompt":"0.05","completion":"0","input_per_1m":0.05,"output_per_1m":0,"billing":"byok","list_pricing":{"input_per_1m":0.05,"output_per_1m":0}},"top_provider":{"context_length":524288,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["state","model","questions"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/upstage/solar-decide","metrics":"/api/v1/models/upstage%2Fsolar-decide/metrics"},"per_upstream":[{"backend":"openrouter-byok","model_name":"upstage/solar-decide","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0},"billing":"byok","context":{"max_length":524288},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]},{"backend":"hue","model_name":"upstage/solar-decide","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.05,"output_per_1m":0},"context":{"max_length":524288},"data_policy":{"zdr":false},"supported_parameters":["state","model","questions"]}]},{"id":"x-ai/grok-4.7","object":"model","canonical_slug":"x-ai/grok-4.7","owned_by":"xai","hugging_face_id":null,"name":"Grok 4.7","display_name":"Grok 4.7","provider":"xAI","providers":["xai-byok","openrouter-byok","hue","cline-byok","opencode-zen-byok","opencode-go-byok","aihubmix-byok","router-byok","vercel-byok","venice-byok","nousresearch-byok","onetoken-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding","vision","reasoning"],"created":1789516800,"description":"SpaceXAI's frontier model for coding, agentic tasks, and knowledge work — succeeds Grok 4.6 with mandatory adjustable reasoning (low/medium/high/xhigh, default high).","context_length":500000,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"1.6","completion":"4.8","input_per_1m":1.6,"output_per_1m":4.8,"billing":"byok","list_pricing":{"input_per_1m":1.6,"output_per_1m":4.8}},"top_provider":{"context_length":500000,"max_completion_tokens":200000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","frequency_penalty","logit_bias","logprobs","presence_penalty","reasoning","seed","structured_outputs","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-4.7","metrics":"/api/v1/models/x-ai%2Fgrok-4.7/metrics"},"per_upstream":[{"backend":"xai-byok","model_name":"grok-4.7","llm_provider":"xai-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"x-ai/grok-4.7","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.6,"output_per_1m":4.8},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"hue","model_name":"x-ai/grok-4.7","llm_provider":"hue","pricing":{"input_per_1m":1.6,"output_per_1m":4.8},"list_pricing":{"input_per_1m":1.6,"output_per_1m":4.8},"context":{"max_length":500000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"cline-byok","model_name":"x-ai/grok-4.7","llm_provider":"cline-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"opencode-zen-byok","model_name":"grok-4.7","llm_provider":"opencode-zen-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"opencode-go-byok","model_name":"grok-4.7","llm_provider":"opencode-go-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"aihubmix-byok","model_name":"grok-4.7","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"router-byok","model_name":"grok-4.7","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"spacexai/grok-4.7","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"venice-byok","model_name":"grok-4-7","llm_provider":"venice-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2.27,"output_per_1m":6.8},"billing":"byok","context":{"max_length":500000,"max_completion_tokens":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"x-ai/grok-4.7","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"onetoken-byok","model_name":"grok-4-7","llm_provider":"onetoken-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0,"input_cache_write_per_1m":0},"list_pricing":{"input_per_1m":0.066,"output_per_1m":0.198},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}]},{"id":"xingchen-agi/xing4.0-29b-a4b","object":"model","canonical_slug":"xingchen-agi/xing4.0-29b-a4b","owned_by":"xingchen-agi","hugging_face_id":null,"name":"Xing4.0 29B A4B","display_name":"Xing4.0 29B A4B","provider":"xingchen-agi","providers":["hue","openrouter-byok"],"category":"text","capabilities":["chat","streaming","reasoning","function-calling","coding"],"created":1789516800,"description":"Xing4.0-29B-A4B is an open-weight mixture-of-experts reasoning model from China Telecom's TeleAI (the Xing line, formerly TeleChat). It activates 4B of 29B parameters per token, supports a 256K context, and targets agentic coding, tool calling and long-context engineering tasks.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Xingchen-agi","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/xingchen-agi/xing4.0-29b-a4b","metrics":"/api/v1/models/xingchen-agi%2Fxing4.0-29b-a4b/metrics"},"per_upstream":[{"backend":"hue","model_name":"xingchen-agi/xing4.0-29b-a4b:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"xingchen-agi/xing4.0-29b-a4b:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"z-ai/glm-4.5-flash","object":"model","canonical_slug":"z-ai/glm-4.5-flash","owned_by":"zhipu ai","hugging_face_id":null,"name":"GLM-4.5-Flash","display_name":"GLM-4.5-Flash","provider":"Zhipu AI","providers":["respan-byok"],"category":"text","capabilities":["chat","streaming","function-calling","reasoning","coding","agentic"],"created":1753660800,"description":"GLM-4.5-Flash is the free, lightweight tier of Z.ai's GLM-4.5 family, built for reasoning, coding and agent tasks with text in and text out. Served through Respan's Z.ai deployment on a user-owned Respan key.","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Z-ai","instruct_type":null},"pricing":{"prompt":"0","completion":"0","input_per_1m":0,"output_per_1m":0,"billing":"byok"},"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.5-flash","metrics":"/api/v1/models/z-ai%2Fglm-4.5-flash/metrics"},"per_upstream":[{"backend":"respan-byok","model_name":"glm-4.5-flash","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"z-ai/glm-4.7-flash","object":"model","canonical_slug":"z-ai/glm-4.7-flash","owned_by":"zhipu ai","hugging_face_id":null,"name":"GLM-4.7 Flash","display_name":"GLM-4.7 Flash","provider":"Zhipu AI","providers":["aihubmix-byok","hue","deepinfra-byok","z-ai-byok","Z-AI Coding Plan","ollama-byok","openrouter-byok","zenmux-byok","vercel-byok","novita-byok","huggingface-byok","nousresearch-byok","respan-byok"],"category":"text","capabilities":["chat","reasoning","streaming","function-calling","coding"],"created":1744243200,"description":"GLM-4.7-Flash is a fast and efficient multilingual text generation model with a 131,072 token context window. Optimized for dialogue, instruction-following, and multi-turn tool calling across 100+ languages.","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GLM","instruct_type":null},"pricing":{"prompt":"0.06","completion":"0.4","input_per_1m":0.06,"output_per_1m":0.4,"billing":"byok","list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4}},"top_provider":{"context_length":200000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","frequency_penalty","include_reasoning","logit_bias","logprobs","min_p","presence_penalty","reasoning","repetition_penalty","seed","structured_outputs","top_k","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-4.7-flash","metrics":"/api/v1/models/z-ai%2Fglm-4.7-flash/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"glm-4.7-flash-free","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"hue","model_name":"z-ai/glm-4.7-flash","llm_provider":"hue","pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"deepinfra-byok","model_name":"zai-org/GLM-4.7-Flash","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}},{"backend":"z-ai-byok","model_name":"glm-4.7-flash","llm_provider":"z-ai-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"z-ai-coding-byok","model_name":"glm-4.7-flash","llm_provider":"Z-AI Coding Plan","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"ollama-byok","model_name":"glm-4.7:cloud","llm_provider":"ollama-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"z-ai/glm-4.7-flash","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"zenmux-byok","model_name":"z-ai/glm-4.7-flash-free","llm_provider":"zenmux-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"zai/glm-4.7-flash","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.07,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":131000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"novita-byok","model_name":"zai-org/glm-4.7-flash","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.07,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"huggingface-byok","model_name":"zai-org/GLM-4.7-Flash","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nousresearch-byok","model_name":"z-ai/glm-4.7-flash","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":16384},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"respan-byok","model_name":"glm-4.7-flash","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}}]},{"id":"z-ai/glm-5.3","object":"model","canonical_slug":"z-ai/glm-5.3","owned_by":"zhipu ai","hugging_face_id":null,"name":"GLM-5.3","display_name":"GLM-5.3","provider":"Zhipu AI","providers":["aihubmix-byok","router-byok","melious","openrouter-byok","vercel-byok","deepinfra-byok","novita-byok","siliconflow-byok","gmicloud-byok","huggingface-byok","nvidia-byok","nousresearch-byok","onetoken-byok"],"category":"text","capabilities":["chat","reasoning","streaming","function-calling","thinking","coding"],"created":1786665600,"description":"GLM-5.3 is Z.AI's reasoning model for coding and agentic workflows, built for complex software engineering, long-running agents, and vulnerability analysis. It uses the same base model as GLM-5.2 with scaled post-training for stronger coding performance, task execution, and token efficiency.","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GLM","instruct_type":null},"pricing":{"prompt":"0.06","completion":"0.22","input_per_1m":0.06,"output_per_1m":0.22,"billing":"byok","list_pricing":{"input_per_1m":0.06,"output_per_1m":0.22}},"top_provider":{"context_length":1050000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3","metrics":"/api/v1/models/z-ai%2Fglm-5.3/metrics"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"coding-glm-5.3","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.22},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"router-byok","model_name":"glm-5.3","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1050000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"melious","model_name":"melious/glm-5.3","llm_provider":"melious","pricing":{"input_per_1m":1.14,"output_per_1m":3.42},"context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"z-ai/glm-5.3","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.039,"output_per_1m":4.8},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":943718},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"zai/glm-5.3","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"zai-org/GLM-5.3","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.9,"output_per_1m":4},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"reasoning":true}},{"backend":"novita-byok","model_name":"zai-org/glm-5.3","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"siliconflow-byok","model_name":"zai-org/GLM-5.3","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"gmicloud-byok","model_name":"zai-org/GLM-5.3","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"huggingface-byok","model_name":"zai-org/GLM-5.3","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nvidia-byok","model_name":"z-ai/glm-5.3","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"nousresearch-byok","model_name":"z-ai/glm-5.3","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.91,"output_per_1m":2.86},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"onetoken-byok","model_name":"glm-5.3","llm_provider":"onetoken-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.0462,"output_per_1m":0.1452},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}}]},{"id":"google/gemma-latest","object":"model","canonical_slug":"google/gemma-latest","owned_by":"google","hugging_face_id":null,"name":"Google gemma (latest)","display_name":"gemma (latest)","provider":"Google","providers":["aihubmix-byok","ollama-byok","openrouter-byok","google-aistudio-byok","hue","fpt-byok","respan-byok"],"category":"text","capabilities":["chat","reasoning","streaming","function-calling","vision","thinking"],"created":1780444800,"description":"Alias for the newest live gemma model; currently google/gemma-4-31b.","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":"0.1","completion":"0.34","input_per_1m":0.1,"output_per_1m":0.34,"billing":"byok","list_pricing":{"input_per_1m":0.1,"output_per_1m":0.34}},"top_provider":{"context_length":262144,"max_completion_tokens":null,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/google/gemma-latest"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"gemma-4-31b-it","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"ollama-byok","model_name":"gemma4:31b-cloud","llm_provider":"ollama-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"google/gemma-4-31b-it:free","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"google/gemma-4-31b-it","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"google-aistudio-byok","model_name":"gemma-4-31b-it","llm_provider":"google-aistudio-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"hue","model_name":"google/gemma-4-31b-it:free","llm_provider":"hue","pricing":{"input_per_1m":0,"output_per_1m":0},"context":{"max_length":262144},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"fpt-byok","model_name":"gemma-4-31B-it","llm_provider":"fpt-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p"],"features":{"streaming":true}},{"backend":"respan-byok","model_name":"gemma-4-31b-it","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"billing":"byok","context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"vision":true}}],"alias":true,"resolves_to":"google/gemma-4-31b","family":"gemma"},{"id":"deepseek/deepseek-flash-latest","object":"model","canonical_slug":"deepseek/deepseek-flash-latest","owned_by":"deepseek","hugging_face_id":null,"name":"DeepSeek deepseek-flash (latest)","display_name":"deepseek-flash (latest)","provider":"DeepSeek","providers":["openrouter-byok","deepseek-byok","vercel-byok","deepinfra-byok","nousresearch-byok","aihubmix-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding","reasoning","vision"],"created":1792195200,"description":"Alias for the newest live deepseek-flash model; currently deepseek/deepseek-v4.1-flash-1017.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Deepseek","instruct_type":null},"pricing":{"prompt":"0.075","completion":"0.3","input_per_1m":0.075,"output_per_1m":0.3,"billing":"byok","list_pricing":{"input_per_1m":0.075,"output_per_1m":0.3}},"top_provider":{"context_length":1048576,"max_completion_tokens":384000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/deepseek/deepseek-flash-latest"},"per_upstream":[{"backend":"openrouter-byok","model_name":"deepseek/deepseek-v4.1-flash-1017","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.15,"output_per_1m":0.6},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":393216},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepseek-byok","model_name":"deepseek-flash","llm_provider":"deepseek-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.3,"output_per_1m":1.2},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"deepseek/deepseek-v4.1-flash-1017","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.075,"output_per_1m":0.3},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":384000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.2,"output_per_1m":0.6},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"deepseek/deepseek-v4.1-flash-1017","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.15,"output_per_1m":0.6},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"aihubmix-byok","model_name":"deepseek-v4.1-flash-1017","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.155,"output_per_1m":0.62},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}],"alias":true,"resolves_to":"deepseek/deepseek-v4.1-flash-1017","family":"deepseek-flash"},{"id":"z-ai/glm-latest","object":"model","canonical_slug":"z-ai/glm-latest","owned_by":"zhipu ai","hugging_face_id":null,"name":"Zhipu AI glm (latest)","display_name":"glm (latest)","provider":"Zhipu AI","providers":["aihubmix-byok","router-byok","melious","openrouter-byok","vercel-byok","deepinfra-byok","novita-byok","siliconflow-byok","gmicloud-byok","huggingface-byok","nvidia-byok","nousresearch-byok","onetoken-byok"],"category":"text","capabilities":["chat","reasoning","streaming","function-calling","thinking","coding"],"created":1786665600,"description":"Alias for the newest live glm model; currently z-ai/glm-5.3.","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GLM","instruct_type":null},"pricing":{"prompt":"0.06","completion":"0.22","input_per_1m":0.06,"output_per_1m":0.22,"billing":"byok","list_pricing":{"input_per_1m":0.06,"output_per_1m":0.22}},"top_provider":{"context_length":1050000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","stream"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-latest"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"coding-glm-5.3","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.22},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"router-byok","model_name":"glm-5.3","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1050000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"melious","model_name":"melious/glm-5.3","llm_provider":"melious","pricing":{"input_per_1m":1.14,"output_per_1m":3.42},"context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"z-ai/glm-5.3","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.039,"output_per_1m":4.8},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":943718},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"vercel-byok","model_name":"zai/glm-5.3","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"deepinfra-byok","model_name":"zai-org/GLM-5.3","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.9,"output_per_1m":4},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"reasoning":true}},{"backend":"novita-byok","model_name":"zai-org/glm-5.3","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1048576,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"siliconflow-byok","model_name":"zai-org/GLM-5.3","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"gmicloud-byok","model_name":"zai-org/GLM-5.3","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"huggingface-byok","model_name":"zai-org/GLM-5.3","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nvidia-byok","model_name":"z-ai/glm-5.3","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.4,"output_per_1m":4.4},"billing":"byok","data_policy":{"zdr":false},"features":{"streaming":true}},{"backend":"nousresearch-byok","model_name":"z-ai/glm-5.3","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.91,"output_per_1m":2.86},"billing":"byok","context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"onetoken-byok","model_name":"glm-5.3","llm_provider":"onetoken-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.0462,"output_per_1m":0.1452},"billing":"byok","context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}}],"alias":true,"resolves_to":"z-ai/glm-5.3","family":"glm"},{"id":"z-ai/glm-flash-latest","object":"model","canonical_slug":"z-ai/glm-flash-latest","owned_by":"zhipu ai","hugging_face_id":null,"name":"Zhipu AI glm-flash (latest)","display_name":"glm-flash (latest)","provider":"Zhipu AI","providers":["aihubmix-byok","hue","deepinfra-byok","z-ai-byok","Z-AI Coding Plan","ollama-byok","openrouter-byok","zenmux-byok","vercel-byok","novita-byok","huggingface-byok","nousresearch-byok","respan-byok"],"category":"text","capabilities":["chat","reasoning","streaming","function-calling","coding"],"created":1744243200,"description":"Alias for the newest live glm-flash model; currently z-ai/glm-4.7-flash.","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GLM","instruct_type":null},"pricing":{"prompt":"0.06","completion":"0.4","input_per_1m":0.06,"output_per_1m":0.4,"billing":"byok","list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4}},"top_provider":{"context_length":200000,"max_completion_tokens":16384,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","frequency_penalty","include_reasoning","logit_bias","logprobs","min_p","presence_penalty","reasoning","repetition_penalty","seed","structured_outputs","top_k","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/z-ai/glm-flash-latest"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"glm-4.7-flash-free","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"hue","model_name":"z-ai/glm-4.7-flash","llm_provider":"hue","pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"deepinfra-byok","model_name":"zai-org/GLM-4.7-Flash","llm_provider":"deepinfra-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop"],"features":{"streaming":true}},{"backend":"z-ai-byok","model_name":"glm-4.7-flash","llm_provider":"z-ai-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"z-ai-coding-byok","model_name":"glm-4.7-flash","llm_provider":"Z-AI Coding Plan","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":128000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"ollama-byok","model_name":"glm-4.7:cloud","llm_provider":"ollama-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice"],"features":{"streaming":true,"function_calling":true}},{"backend":"openrouter-byok","model_name":"z-ai/glm-4.7-flash","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"zenmux-byok","model_name":"z-ai/glm-4.7-flash-free","llm_provider":"zenmux-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"zai/glm-4.7-flash","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.07,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":131000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"novita-byok","model_name":"zai-org/glm-4.7-flash","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.07,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":128000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"huggingface-byok","model_name":"zai-org/GLM-4.7-Flash","llm_provider":"huggingface-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nousresearch-byok","model_name":"z-ai/glm-4.7-flash","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000,"max_completion_tokens":16384},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"reasoning":true}},{"backend":"respan-byok","model_name":"glm-4.7-flash","llm_provider":"respan-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":0.06,"output_per_1m":0.4},"billing":"byok","context":{"max_length":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}}],"alias":true,"resolves_to":"z-ai/glm-4.7-flash","family":"glm-flash"},{"id":"moonshotai/kimi-latest","object":"model","canonical_slug":"moonshotai/kimi-latest","owned_by":"moonshot ai","hugging_face_id":null,"name":"Moonshot AI kimi (latest)","display_name":"kimi (latest)","provider":"Moonshot AI","providers":["aihubmix-byok","nvidia","nvidia-byok","moonshotai-byok","zenmux-byok","openrouter-byok","orcarouter-byok","cline-byok","novita-byok","fireworks-byok","baseten-byok","siliconflow-byok","gmicloud-byok","nousresearch-byok","venice-byok","commandcode-byok","opencode-go-byok","router-byok","vercel-byok"],"category":"multimodal","capabilities":["chat","reasoning","streaming","function-calling","vision","coding","agentic"],"created":1784160000,"description":"Alias for the newest live kimi model; currently moonshotai/kimi-k3.","context_length":1050000,"architecture":{"modality":"text+image->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Moonshotai","instruct_type":null},"pricing":{"prompt":"3","completion":"15","input_per_1m":3,"output_per_1m":15},"top_provider":{"context_length":1050000,"max_completion_tokens":131072,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","reasoning_effort","seed","structured_outputs","include_reasoning"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/moonshotai/kimi-latest"},"per_upstream":[{"backend":"aihubmix-byok","model_name":"coding-kimi-k3","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"nvidia","model_name":"moonshotai/kimi-k3","llm_provider":"nvidia","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nvidia-byok","model_name":"moonshotai/kimi-k3","llm_provider":"nvidia-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"moonshotai-byok","model_name":"kimi-k3","llm_provider":"moonshotai-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"zenmux-byok","model_name":"moonshotai/kimi-k3","llm_provider":"zenmux-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"openrouter-byok","model_name":"moonshotai/kimi-k3","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"orcarouter-byok","model_name":"kimi/kimi-k3","llm_provider":"orcarouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true}},{"backend":"cline-byok","model_name":"moonshotai/kimi-k3","llm_provider":"cline-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"novita-byok","model_name":"moonshotai/kimi-k3","llm_provider":"novita-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"fireworks-byok","model_name":"accounts/fireworks/models/kimi-k3","llm_provider":"fireworks-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"baseten-byok","model_name":"moonshotai/Kimi-K3","llm_provider":"baseten-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"siliconflow-byok","model_name":"moonshotai/Kimi-K3","llm_provider":"siliconflow-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"gmicloud-byok","model_name":"moonshotai/kimi-k3","llm_provider":"gmicloud-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":262144},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"nousresearch-byok","model_name":"moonshotai/kimi-k3","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","reasoning","reasoning_effort","seed","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"venice-byok","model_name":"kimi-k3","llm_provider":"venice-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"commandcode-byok","model_name":"moonshotai/Kimi-K3","llm_provider":"commandcode-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1000000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"opencode-go-byok","model_name":"kimi-k3","llm_provider":"opencode-go-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1048576},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"router-byok","model_name":"kimi-k3","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1050000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"moonshotai/kimi-k3","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":3,"output_per_1m":15},"context":{"max_length":1000000,"max_completion_tokens":131072},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}],"alias":true,"resolves_to":"moonshotai/kimi-k3","family":"kimi"},{"id":"x-ai/grok-latest","object":"model","canonical_slug":"x-ai/grok-latest","owned_by":"xai","hugging_face_id":null,"name":"xAI grok (latest)","display_name":"grok (latest)","provider":"xAI","providers":["xai-byok","openrouter-byok","hue","cline-byok","opencode-zen-byok","opencode-go-byok","aihubmix-byok","router-byok","vercel-byok","venice-byok","nousresearch-byok","onetoken-byok"],"category":"text","capabilities":["chat","streaming","function-calling","coding","vision","reasoning"],"created":1789516800,"description":"Alias for the newest live grok model; currently x-ai/grok-4.7.","context_length":500000,"architecture":{"modality":"text->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":"1.6","completion":"4.8","input_per_1m":1.6,"output_per_1m":4.8,"billing":"byok","list_pricing":{"input_per_1m":1.6,"output_per_1m":4.8}},"top_provider":{"context_length":500000,"max_completion_tokens":200000,"is_moderated":false},"per_request_limits":null,"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format","frequency_penalty","logit_bias","logprobs","presence_penalty","reasoning","seed","structured_outputs","top_logprobs"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null},"knowledge_cutoff":null,"expiration_date":null,"links":{"details":"/api/v1/models/x-ai/grok-latest"},"per_upstream":[{"backend":"xai-byok","model_name":"grok-4.7","llm_provider":"xai-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"openrouter-byok","model_name":"x-ai/grok-4.7","llm_provider":"openrouter-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":1.6,"output_per_1m":4.8},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"hue","model_name":"x-ai/grok-4.7","llm_provider":"hue","pricing":{"input_per_1m":1.6,"output_per_1m":4.8},"list_pricing":{"input_per_1m":1.6,"output_per_1m":4.8},"context":{"max_length":500000},"data_policy":{"zdr":false},"supported_parameters":["max_tokens","temperature","top_p","stop","tools","tool_choice","response_format"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"cline-byok","model_name":"x-ai/grok-4.7","llm_provider":"cline-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"opencode-zen-byok","model_name":"grok-4.7","llm_provider":"opencode-zen-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"opencode-go-byok","model_name":"grok-4.7","llm_provider":"opencode-go-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"aihubmix-byok","model_name":"grok-4.7","llm_provider":"aihubmix-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true}},{"backend":"router-byok","model_name":"grok-4.7","llm_provider":"router-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true}},{"backend":"vercel-byok","model_name":"spacexai/grok-4.7","llm_provider":"vercel-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"venice-byok","model_name":"grok-4-7","llm_provider":"venice-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2.27,"output_per_1m":6.8},"billing":"byok","context":{"max_length":500000,"max_completion_tokens":200000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"nousresearch-byok","model_name":"x-ai/grok-4.7","llm_provider":"nousresearch-byok","pricing":{"input_per_1m":0,"output_per_1m":0},"list_pricing":{"input_per_1m":2,"output_per_1m":6},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}},{"backend":"onetoken-byok","model_name":"grok-4-7","llm_provider":"onetoken-byok","pricing":{"input_per_1m":0,"output_per_1m":0,"input_cache_read_per_1m":0,"input_cache_write_per_1m":0},"list_pricing":{"input_per_1m":0.066,"output_per_1m":0.198},"billing":"byok","context":{"max_length":500000},"data_policy":{"zdr":false},"features":{"streaming":true,"function_calling":true,"vision":true,"reasoning":true}}],"alias":true,"resolves_to":"x-ai/grok-4.7","family":"grok"}]}