@agentjido/llmdb 2026.8.2

package/dist/providers/vercel.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":null,"catalog_only":true,"config_schema":null,"doc":"https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway","env":["AI_GATEWAY_API_KEY"],"exclude_models":null,"extra":null,"id":"vercel","models":{"alibaba/qwen-3-14b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.12,"output":0.24},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"alibaba/qwen-3-14b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-14B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"alibaba/qwen-3-235b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.22,"output":0.88},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"alibaba/qwen-3-235b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"alibaba/qwen-3-30b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.12,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"alibaba/qwen-3-30b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-30B-A3B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"alibaba/qwen-3-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.16,"output":0.64},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":38912,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen-3-32b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3.32B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"alibaba/qwen-3.6-max-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"cache_write":1.625,"input":1.3,"output":7.8},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"max":131072,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen-3.6-max-preview","knowledge":null,"last_updated":"2026-04-24","lifecycle":null,"limits":{"context":240000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3.6 Max Preview","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"alibaba/qwen3-235b-a22b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"max":81920,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3-235b-a22b-thinking","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Thinking 2507","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"alibaba/qwen3-coder":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"alibaba/qwen3-coder","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 480B A35B Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"alibaba/qwen3-coder-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"alibaba/qwen3-coder-30b-a3b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Coder 30B A3B Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"alibaba/qwen3-coder-next":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"alibaba/qwen3-coder-next","knowledge":null,"last_updated":"2026-02-19","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"alibaba/qwen3-coder-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"alibaba/qwen3-coder-plus","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Plus","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"alibaba/qwen3-embedding-0.6b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"alibaba/qwen3-embedding-0.6b","knowledge":null,"last_updated":"2025-11-14","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Embedding 0.6B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-14","retired":false,"tags":null},"alibaba/qwen3-embedding-4b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"alibaba/qwen3-embedding-4b","knowledge":null,"last_updated":"2025-06-05","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Embedding 4B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-05","retired":false,"tags":null},"alibaba/qwen3-embedding-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"alibaba/qwen3-embedding-8b","knowledge":null,"last_updated":"2025-06-05","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Embedding 8B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-05","retired":false,"tags":null},"alibaba/qwen3-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"alibaba/qwen3-max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"alibaba/qwen3-max-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"alibaba/qwen3-max-preview","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max Preview","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-05","retired":false,"tags":null},"alibaba/qwen3-max-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[{"max":81920,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3-max-thinking","knowledge":"2025-01","last_updated":"2025-01","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Max Thinking","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-23","retired":false,"tags":null},"alibaba/qwen3-next-80b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"alibaba/qwen3-next-80b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Next 80B A3B Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-11","retired":false,"tags":null},"alibaba/qwen3-next-80b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","open_weights":true,"reasoning_options":[{"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3-next-80b-a3b-thinking","knowledge":"2025-09","last_updated":"2025-09","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Next 80B A3B Thinking","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-11","retired":false,"tags":null},"alibaba/qwen3-vl-235b-a22b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"alibaba/qwen3-vl-235b-a22b-instruct","knowledge":null,"last_updated":"2026-05-01","lifecycle":null,"limits":{"context":131072,"output":129024},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B A22B Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"alibaba/qwen3-vl-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"alibaba/qwen3-vl-instruct","knowledge":"2025-04","last_updated":"2025-09-24","lifecycle":null,"limits":{"context":131072,"output":129024},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"alibaba/qwen3-vl-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"max":81920,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3-vl-thinking","knowledge":"2025-09","last_updated":"2025-09-24","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen3 VL Thinking","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"alibaba/qwen3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.001,"cache_write":0.125,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":81920,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3.5-flash","knowledge":null,"last_updated":"2026-02-24","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen 3.5 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"alibaba/qwen3.5-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"cache_write":0.5,"input":0.4,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":81920,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3.5-plus","knowledge":"2025-04","last_updated":"2026-02-16","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen 3.5 Plus","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"alibaba/qwen3.6-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":131072,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"alibaba/qwen3.6-27b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen 3.6 27B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"alibaba/qwen3.6-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":0.625,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":131072,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3.6-plus","knowledge":"2025-04","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen 3.6 Plus","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"alibaba/qwen3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.006,"cache_write":0.038,"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"alibaba/qwen3.7-flash","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":991000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen 3.7 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-28","retired":false,"tags":null},"alibaba/qwen3.7-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":3.125,"input":2.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":262144,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":991000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3.7 Max","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"alibaba/qwen3.7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"cache_write":0.5,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen3.7-plus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":262144,"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Qwen 3.7 Plus","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"alibaba/qwen3.8-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"max":262144,"min":0,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"alibaba/qwen3.8-max","knowledge":null,"last_updated":"2026-07-19","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 3.8 Max","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-08-02","retired":false,"tags":null},"alibaba/wan-v2.5-t2v-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.5-t2v-preview","knowledge":null,"last_updated":"2025-09-24","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.5 Text-to-Video Preview","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-24","retired":false,"tags":null},"alibaba/wan-v2.6-i2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.6-i2v","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.6 Image-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"alibaba/wan-v2.6-i2v-flash":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.6-i2v-flash","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.6 Image-to-Video Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"alibaba/wan-v2.6-r2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.6-r2v","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.6 Reference-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"alibaba/wan-v2.6-r2v-flash":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.6-r2v-flash","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.6 Reference-to-Video Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"alibaba/wan-v2.6-t2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.6-t2v","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.6 Text-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"alibaba/wan-v2.7-r2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.7-r2v","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.7 Reference-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"alibaba/wan-v2.7-t2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"alibaba/wan-v2.7-t2v","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Wan v2.7 Text-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"amazon/nova-2-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"amazon/nova-2-lite","knowledge":"2024-10","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Nova 2 Lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"amazon/nova-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.06,"output":0.24},"deprecated":false,"extra":{"attachment":true,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","open_weights":false,"temperature":true},"family":null,"id":"amazon/nova-lite","knowledge":"2024-10","last_updated":"2024-12-03","lifecycle":null,"limits":{"context":300000,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Nova Lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-03","retired":false,"tags":null},"amazon/nova-micro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.00875,"input":0.035,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","open_weights":false,"temperature":true},"family":null,"id":"amazon/nova-micro","knowledge":"2024-10","last_updated":"2024-12-03","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nova Micro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-03","retired":false,"tags":null},"amazon/nova-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.8,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","open_weights":false,"temperature":true},"family":null,"id":"amazon/nova-pro","knowledge":"2024-10","last_updated":"2024-12-03","lifecycle":null,"limits":{"context":300000,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Nova Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-03","retired":false,"tags":null},"amazon/titan-embed-text-v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"titan-embed","open_weights":false,"temperature":true},"family":null,"id":"amazon/titan-embed-text-v2","knowledge":null,"last_updated":"2024-04","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Titan Text Embeddings V2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-04-30","retired":false,"tags":null},"anthropic/claude-3-haiku":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.3,"input":0.25,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"anthropic/claude-3-haiku","knowledge":"2023-08-31","last_updated":"2024-03-13","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Haiku 3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-03-13","retired":false,"tags":null},"anthropic/claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":false},"family":null,"id":"anthropic/claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-01","retired":false,"tags":null},"anthropic/claude-haiku-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","interleaved":true,"open_weights":false,"reasoning_options":[{"type":"toggle"},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-haiku-4.5","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"anthropic/claude-opus-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"anthropic/claude-opus-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-opus-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4.1","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"anthropic/claude-opus-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","interleaved":true,"open_weights":false,"reasoning_options":[{"type":"toggle"},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.5","knowledge":"2025-05","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"anthropic/claude-opus-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","interleaved":true,"open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"anthropic/claude-opus-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic/claude-opus-4.8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic/claude-opus-4.8-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.8-fast","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8 (Fast)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic/claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"anthropic/claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-opus-5-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"anthropic/claude-opus-5-fast","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5 (Fast)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-sonnet-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":1000000,"output":8192},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-sonnet-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4.5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"anthropic/claude-sonnet-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","interleaved":true,"open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4.6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"anthropic/claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":false},"family":null,"id":"anthropic/claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-29","retired":false,"tags":null},"arcee-ai/trinity-large-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.8999999999999999},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"trinity","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"arcee-ai/trinity-large-thinking","knowledge":null,"last_updated":"2026-04-03","lifecycle":null,"limits":{"context":262100,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Trinity Large Thinking","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"arcee-ai/trinity-mini":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.045,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"trinity","open_weights":false,"temperature":true},"family":null,"id":"arcee-ai/trinity-mini","knowledge":"2024-10","last_updated":"2025-12","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Trinity Mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"bfl/flux-2-flex":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-2-flex","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.2 [flex]","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-25","retired":false,"tags":null},"bfl/flux-2-klein-4b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-2-klein-4b","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.2 [klein] 4B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-15","retired":false,"tags":null},"bfl/flux-2-klein-9b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-2-klein-9b","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.2 [klein] 9B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-15","retired":false,"tags":null},"bfl/flux-2-max":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-2-max","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":{"context":67300,"output":67300},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.2 [max]","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"bfl/flux-2-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-2-pro","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":{"context":67300,"output":67300},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.2 [pro]","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-25","retired":false,"tags":null},"bfl/flux-kontext-max":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-kontext-max","knowledge":null,"last_updated":"2025-06","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.1 Kontext Max","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-29","retired":false,"tags":null},"bfl/flux-kontext-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-kontext-pro","knowledge":null,"last_updated":"2025-06","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.1 Kontext Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-29","retired":false,"tags":null},"bfl/flux-pro-1.0-fill":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-pro-1.0-fill","knowledge":null,"last_updated":"2024-10","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX.1 Fill [pro]","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"bfl/flux-pro-1.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-pro-1.1","knowledge":null,"last_updated":"2024-10","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX1.1 [pro]","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-10-02","retired":false,"tags":null},"bfl/flux-pro-1.1-ultra":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"bfl/flux-pro-1.1-ultra","knowledge":null,"last_updated":"2024-11","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"FLUX1.1 [pro] Ultra","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"bytedance/seed-1.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"bytedance/seed-1.6","knowledge":"2024-10","last_updated":"2025-09","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 1.6","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null},"bytedance/seed-1.8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"bytedance/seed-1.8","knowledge":"2024-10","last_updated":"2025-10","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 1.8","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null},"bytedance/seedance-2.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedance-2.0","knowledge":null,"last_updated":"2026-04-14","lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Seedance 2.0","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-14","retired":false,"tags":null},"bytedance/seedance-2.0-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedance-2.0-fast","knowledge":null,"last_updated":"2026-04-14","lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Seedance 2.0 Fast","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-14","retired":false,"tags":null},"bytedance/seedance-v1.0-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedance-v1.0-pro","knowledge":null,"last_updated":"2025-06-11","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Seedance v1.0 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-11","retired":false,"tags":null},"bytedance/seedance-v1.0-pro-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedance-v1.0-pro-fast","knowledge":null,"last_updated":"2025-10-31","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Seedance v1.0 Pro Fast","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-24","retired":false,"tags":null},"bytedance/seedance-v1.5-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedance-v1.5-pro","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Seedance v1.5 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"bytedance/seedream-4.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedream-4.0","knowledge":null,"last_updated":"2025-08-28","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Seedream 4.0","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-09","retired":false,"tags":null},"bytedance/seedream-4.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedream-4.5","knowledge":null,"last_updated":"2025-11-28","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Seedream 4.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null},"bytedance/seedream-5.0-lite":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedream-5.0-lite","knowledge":null,"last_updated":"2026-01-28","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Seedream 5.0 Lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-13","retired":false,"tags":null},"bytedance/seedream-5.0-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","open_weights":false,"temperature":true},"family":null,"id":"bytedance/seedream-5.0-pro","knowledge":null,"last_updated":"2026-07-11","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Seedream 5.0 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-11","retired":false,"tags":null},"cohere/command-a":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command","open_weights":false,"temperature":true},"family":null,"id":"cohere/command-a","knowledge":"2024-10","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":256000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command A","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"cohere/embed-v4.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","open_weights":false,"temperature":true},"family":null,"id":"cohere/embed-v4.0","knowledge":null,"last_updated":"2025-04-15","lifecycle":null,"limits":{"context":128000,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Embed v4.0","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-15","retired":false,"tags":null},"cohere/rerank-v3.5":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"o","open_weights":false,"temperature":true},"family":null,"id":"cohere/rerank-v3.5","knowledge":null,"last_updated":"2024-12-02","lifecycle":null,"limits":{"context":4096,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere Rerank 3.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-02","retired":false,"tags":null},"cohere/rerank-v4-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"o","open_weights":false,"temperature":true},"family":null,"id":"cohere/rerank-v4-fast","knowledge":null,"last_updated":"2025-12-11","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere Rerank 4 Fast","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"cohere/rerank-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"o","open_weights":false,"temperature":true},"family":null,"id":"cohere/rerank-v4-pro","knowledge":null,"last_updated":"2025-12-11","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Cohere Rerank 4 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"deepseek/deepseek-r1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.35,"output":5.4},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek/deepseek-r1","knowledge":"2024-07","last_updated":"2025-05-29","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek/deepseek-v3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.135,"input":0.27,"output":1.12},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"temperature":true},"family":null,"id":"deepseek/deepseek-v3","knowledge":"2024-07","last_updated":"2024-12-26","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3 0324","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepseek/deepseek-v3.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":0.25,"output":0.95},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1","knowledge":"2024-07","last_updated":"2025-08-21","lifecycle":null,"limits":{"context":163840,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-21","retired":false,"tags":null},"deepseek/deepseek-v3.1-terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.135,"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"deepseek/deepseek-v3.1-terminus","knowledge":"2025-07","last_updated":"2025-09-22","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1 Terminus","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-22","retired":false,"tags":null},"deepseek/deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.028,"input":0.28,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":128000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-v3.2-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.62,"output":1.85},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","interleaved":true,"open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek/deepseek-v3.2-thinking","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":128000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2 Thinking","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"deepseek/deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.13,"output":0.26},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"deepseek/deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0036,"input":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"google/gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"input_audio":1,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","open_weights":false,"temperature":true},"family":null,"id":"google/gemini-2.5-flash-image","knowledge":"2025-01","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":65536},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana (Gemini 2.5 Flash Image)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"google/gemini-2.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":512,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-flash-lite","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash Lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-3-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"google/gemini-3-flash","knowledge":"2025-03","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1000000,"output":65000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"google/gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":false,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"temperature":true},"family":null,"id":"google/gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null},"google/gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"google/gemini-3.1-flash-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image-preview","knowledge":"2025-01","last_updated":"2026-02-26","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"google/gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1000000,"output":65000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"google/gemini-3.1-flash-lite-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-image","knowledge":"2025-01","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":65536,"output":4096},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"google/gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1000000,"output":65000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemini-embedding-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini-embedding","open_weights":false,"temperature":true},"family":null,"id":"google/gemini-embedding-001","knowledge":"2025-05","last_updated":"2025-05-20","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemini Embedding 001","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"google/gemini-embedding-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini-embedding","open_weights":false,"temperature":true},"family":null,"id":"google/gemini-embedding-2","knowledge":"2025-11","last_updated":"2026-04-22","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemini Embedding 2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"google/gemini-omni-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"gemini","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"google/gemini-omni-flash-preview","knowledge":null,"last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":57920},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini Omni Flash Preview","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"google/gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":131072},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/imagen-4.0-fast-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","open_weights":false,"temperature":true},"family":null,"id":"google/imagen-4.0-fast-generate-001","knowledge":null,"last_updated":"2025-06","lifecycle":null,"limits":{"context":480},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Imagen 4 Fast","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"google/imagen-4.0-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","open_weights":false,"temperature":true},"family":null,"id":"google/imagen-4.0-generate-001","knowledge":null,"last_updated":"2025-05-22","lifecycle":null,"limits":{"context":480},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Imagen 4","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"google/imagen-4.0-ultra-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","open_weights":false,"temperature":false},"family":null,"id":"google/imagen-4.0-ultra-generate-001","knowledge":null,"last_updated":"2025-05-24","lifecycle":null,"limits":{"context":480},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Imagen 4 Ultra","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-24","retired":false,"tags":null},"google/text-embedding-005":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"temperature":true},"family":null,"id":"google/text-embedding-005","knowledge":null,"last_updated":"2024-08","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Text Embedding 005","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-08-01","retired":false,"tags":null},"google/text-multilingual-embedding-002":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"temperature":true},"family":null,"id":"google/text-multilingual-embedding-002","knowledge":null,"last_updated":"2024-03","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Text Multilingual Embedding 002","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-03-01","retired":false,"tags":null},"google/veo-3.0-fast-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false,"temperature":true},"family":null,"id":"google/veo-3.0-fast-generate-001","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Veo 3.0 Fast Generate","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"google/veo-3.0-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false,"temperature":true},"family":null,"id":"google/veo-3.0-generate-001","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Veo 3.0","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"google/veo-3.1-fast-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false,"temperature":true},"family":null,"id":"google/veo-3.1-fast-generate-001","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Veo 3.1 Fast Generate","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"google/veo-3.1-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false,"temperature":true},"family":null,"id":"google/veo-3.1-generate-001","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Veo 3.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"google/veo-3.1-lite-generate-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false},"family":null,"id":"google/veo-3.1-lite-generate-001","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Veo 3.1 Lite Generate","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"inception/mercury-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.024999999999999998,"input":0.25,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"inception/mercury-2","knowledge":null,"last_updated":"2026-03-06","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mercury 2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"inception/mercury-coder-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"mercury","open_weights":false,"temperature":true},"family":null,"id":"inception/mercury-coder-small","knowledge":null,"last_updated":"2025-02-26","lifecycle":null,"limits":{"context":32000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mercury Coder Small Beta","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-02-26","retired":false,"tags":null},"inclusionai/ling-3.0-flash-free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","open_weights":false,"reasoning_options":[]},"family":null,"id":"inclusionai/ling-3.0-flash-free","knowledge":null,"last_updated":"2026-07-23","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ling 3.0 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"interfaze/interfaze-beta":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":1.5,"output":3.5},"deprecated":false,"extra":{"attachment":false,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"interfaze/interfaze-beta","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Interfaze Beta","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-07","retired":false,"tags":null},"klingai/kling-v2.5-turbo-i2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v2.5-turbo-i2v","knowledge":null,"last_updated":"2025-09-23","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v2.5 Turbo Image-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"klingai/kling-v2.5-turbo-t2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v2.5-turbo-t2v","knowledge":null,"last_updated":"2025-09-23","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v2.5 Turbo Text-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"klingai/kling-v2.6-i2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v2.6-i2v","knowledge":null,"last_updated":"2025-12-21","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v2.6 Image-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null},"klingai/kling-v2.6-motion-control":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v2.6-motion-control","knowledge":null,"last_updated":"2025-12-21","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v2.6 Motion Control","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-18","retired":false,"tags":null},"klingai/kling-v2.6-t2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v2.6-t2v","knowledge":null,"last_updated":"2025-12-21","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v2.6 Text-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-03","retired":false,"tags":null},"klingai/kling-v3.0-i2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v3.0-i2v","knowledge":null,"last_updated":"2026-02-05","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v3.0 Image-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"klingai/kling-v3.0-motion-control":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v3.0-motion-control","knowledge":null,"last_updated":"2026-03-04","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v3.0 Motion Control","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-04","retired":false,"tags":null},"klingai/kling-v3.0-t2v":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","open_weights":false,"temperature":true},"family":null,"id":"klingai/kling-v3.0-t2v","knowledge":null,"last_updated":"2026-02-05","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Kling v3.0 Text-to-Video","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"kwaipilot/kat-coder-air-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"kwaipilot/kat-coder-air-v2.5","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":256000,"output":80000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kat Coder Air V2.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-10","retired":false,"tags":null},"kwaipilot/kat-coder-pro-v1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro-v1","knowledge":"2024-10","last_updated":"2025-10-24","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"KAT-Coder-Pro V1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-09","retired":false,"tags":null},"kwaipilot/kat-coder-pro-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro-v2","knowledge":null,"last_updated":"2026-03-30","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kat Coder Pro V2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-27","retired":false,"tags":null},"kwaipilot/kat-coder-pro-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":0.74,"output":2.96},"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"kwaipilot/kat-coder-pro-v2.5","knowledge":null,"last_updated":"2026-07-10","lifecycle":null,"limits":{"context":256000,"output":80000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kat Coder Pro V2.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-10","retired":false,"tags":null},"meta/llama-3.1-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.72,"output":0.72},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"meta/llama-3.1-70b","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 70B Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta/llama-3.1-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.22,"output":0.22},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"meta/llama-3.1-8b","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"meta/llama-3.3-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta/llama-3.3-70b","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta/llama-4-maverick":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta/llama-4-maverick","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama-4-Maverick-17B-128E-Instruct-FP8","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta/llama-4-scout":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"meta/llama-4-scout","knowledge":"2024-08","last_updated":"2025-04-05","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama-4-Scout-17B-16E-Instruct-FP8","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"meta/muse-spark-1.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.25,"output":4.25},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"muse","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"meta/muse-spark-1.1","knowledge":null,"last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1048576,"output":1048576},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Muse Spark 1.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"minimax/minimax-h3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"minimax","open_weights":false},"family":null,"id":"minimax/minimax-h3","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":null,"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"MiniMax H3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"minimax/minimax-m2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","interleaved":true,"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2","knowledge":"2024-10","last_updated":"2025-10-27","lifecycle":null,"limits":{"context":205000,"output":205000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-27","retired":false,"tags":null},"minimax/minimax-m2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","interleaved":true,"open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.1","knowledge":"2024-10","last_updated":"2025-12-23","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"minimax/minimax-m2.1-lightning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.375,"input":0.3,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.1-lightning","knowledge":"2024-10","last_updated":"2025-10-27","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.1 Lightning","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"minimax/minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/minimax-m2.5-highspeed":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.375,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.5-highspeed","knowledge":null,"last_updated":"2026-02-13","lifecycle":null,"limits":{"context":204800,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5 High Speed","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/minimax-m2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.375,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Minimax M2.7","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/minimax-m2.7-highspeed":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.375,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.7-highspeed","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131100},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.7 High Speed","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/minimax-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax-m3","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"minimax/minimax-m3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"MiniMax M3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-31","retired":false,"tags":null},"mistral/codestral":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","open_weights":true,"temperature":true},"family":null,"id":"mistral/codestral","knowledge":"2024-10","last_updated":"2025-01-04","lifecycle":null,"limits":{"context":256000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Codestral (latest)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-05-29","retired":false,"tags":null},"mistral/codestral-embed":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"codestral-embed","open_weights":false,"temperature":true},"family":null,"id":"mistral/codestral-embed","knowledge":null,"last_updated":"2025-05-28","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Codestral Embed","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-28","retired":false,"tags":null},"mistral/devstral-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","open_weights":false,"temperature":true},"family":null,"id":"mistral/devstral-2","knowledge":"2024-10","last_updated":"2025-12-09","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Devstral 2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-09","retired":false,"tags":null},"mistral/devstral-small-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","open_weights":false,"temperature":true},"family":null,"id":"mistral/devstral-small-2","knowledge":"2024-10","last_updated":"2025-05-07","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Devstral Small 2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-09","retired":false,"tags":null},"mistral/magistral-medium":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistral/magistral-medium","knowledge":"2025-06","last_updated":"2025-03-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Magistral Medium (latest)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-03-17","retired":false,"tags":null},"mistral/magistral-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-small","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"mistral/magistral-small","knowledge":"2025-06","last_updated":"2025-03-17","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Magistral Small","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-03-17","retired":false,"tags":null},"mistral/ministral-14b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.2,"output":0.2},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":false,"temperature":true},"family":null,"id":"mistral/ministral-14b","knowledge":"2024-10","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Ministral 14B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistral/ministral-3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.04,"output":0.04},"deprecated":false,"extra":{"attachment":false,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"temperature":true},"family":null,"id":"mistral/ministral-3b","knowledge":"2024-10","last_updated":"2024-10-04","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ministral 3B (latest)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"mistral/ministral-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","open_weights":true,"temperature":true},"family":null,"id":"mistral/ministral-8b","knowledge":"2024-10","last_updated":"2024-10-04","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Ministral 8B (latest)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"mistral/mistral-embed":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral-embed","open_weights":false,"temperature":true},"family":null,"id":"mistral/mistral-embed","knowledge":null,"last_updated":"2023-12-11","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Embed","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2023-12-11","retired":false,"tags":null},"mistral/mistral-large-3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":false,"temperature":true},"family":null,"id":"mistral/mistral-large-3","knowledge":"2024-10","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Large 3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistral/mistral-medium":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"temperature":true},"family":null,"id":"mistral/mistral-medium","knowledge":"2024-10","last_updated":"2025-05-07","lifecycle":null,"limits":{"context":128000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"mistral/mistral-medium-3.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","high"]}],"temperature":true},"family":null,"id":"mistral/mistral-medium-3.5","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium Latest","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistral/mistral-nemo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","open_weights":false,"temperature":true},"family":null,"id":"mistral/mistral-nemo","knowledge":"2024-04","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Nemo","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"mistral/mistral-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"mistral/mistral-small","knowledge":"2025-06","last_updated":"2026-03-16","lifecycle":null,"limits":{"context":32000,"output":4000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small (latest)","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-09-17","retired":false,"tags":null},"mistral/pixtral-12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","open_weights":true,"temperature":true},"family":null,"id":"mistral/pixtral-12b","knowledge":"2024-09","last_updated":"2024-09-01","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Pixtral 12B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-09-01","retired":false,"tags":null},"moonshotai/kimi-k2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.57,"output":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":false,"temperature":true},"family":null,"id":"moonshotai/kimi-k2","knowledge":null,"last_updated":"2025-09-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Instruct","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-11","retired":false,"tags":null},"moonshotai/kimi-k2-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.141,"input":0.47,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","interleaved":true,"open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"moonshotai/kimi-k2-thinking","knowledge":"2024-08","last_updated":"2025-11-06","lifecycle":null,"limits":{"context":216144,"output":216144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"moonshotai/kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262114,"output":262114},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-26","retired":false,"tags":null},"moonshotai/kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"moonshotai/kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshotai/kimi-k2.7-code-highspeed":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.38,"input":1.9,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.7-code-highspeed","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code High Speed","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-15","retired":false,"tags":null},"moonshotai/kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"moonshotai/kimi-k3-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.45,"input":4.5,"output":22.5},"deprecated":false,"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshotai/kimi-k3-fast","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Kimi K3 Fast","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"morph/morph-v3-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.8,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","open_weights":false,"temperature":false},"family":null,"id":"morph/morph-v3-fast","knowledge":null,"last_updated":"2024-08-15","lifecycle":null,"limits":{"context":16000,"output":16000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Morph v3 Fast","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-08-15","retired":false,"tags":null},"morph/morph-v3-large":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.9,"output":1.9},"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","open_weights":false,"temperature":false},"family":null,"id":"morph/morph-v3-large","knowledge":null,"last_updated":"2024-08-15","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Morph v3 Large","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-08-15","retired":false,"tags":null},"nvidia/nemotron-3-nano-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.05,"output":0.24},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nvidia/nemotron-3-nano-30b-a3b","knowledge":"2024-10","last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"nvidia/nemotron-3-super-120b-a12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.15,"output":0.65},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nvidia/nemotron-3-super-120b-a12b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3 Super 120B A12B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nvidia/nemotron-3-ultra-550b-a55b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nvidia/nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":1000000,"output":65000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nvidia/nemotron-nano-12b-v2-vl":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nvidia/nemotron-nano-12b-v2-vl","knowledge":"2024-10","last_updated":"2025-10-28","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Nvidia Nemotron Nano 12B V2 VL","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-28","retired":false,"tags":null},"nvidia/nemotron-nano-9b-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.06,"output":0.23},"deprecated":false,"extra":{"attachment":false,"description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nvidia/nemotron-nano-9b-v2","knowledge":"2024-10","last_updated":"2025-08-18","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nvidia Nemotron Nano 9B V2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-18","retired":false,"tags":null},"openai/gpt-3.5-turbo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo","knowledge":"2021-09","last_updated":"2023-11-06","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-3.5 Turbo","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2023-03-01","retired":false,"tags":null},"openai/gpt-4-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":10,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"status":"deprecated","structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-4-turbo","knowledge":"2023-12","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4 Turbo","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","open_weights":false,"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai/gpt-4o-mini-search-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-4o-mini-search-preview","knowledge":"2023-09","last_updated":"2025-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT 4o Mini Search Preview","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"openai/gpt-4o-mini-transcribe":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.25,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"o-mini","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-4o-mini-transcribe","knowledge":null,"last_updated":"2024-03-13","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"GPT-4o mini Transcribe","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-03-13","retired":false,"tags":null},"openai/gpt-4o-transcribe":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-4o-transcribe","knowledge":null,"last_updated":"2024-03-13","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"GPT-4o Transcribe","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-03-13","retired":false,"tags":null},"openai/gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-codex","knowledge":"2024-09-30","last_updated":"2025-09-15","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5-Codex","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-15","retired":false,"tags":null},"openai/gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":15,"output":120},"deprecated":false,"extra":{"attachment":true,"description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5-pro","knowledge":"2024-10","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":400000,"output":272000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5 pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"openai/gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.1-codex","knowledge":"2024-10","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1-Codex","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-12","retired":false,"tags":null},"openai/gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.1-codex-max","knowledge":"2024-10","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.1 Codex Max","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-19","retired":false,"tags":null},"openai/gpt-5.1-codex-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.1-codex-mini","knowledge":"2024-10","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-12","retired":false,"tags":null},"openai/gpt-5.1-instant":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-5.1-instant","knowledge":"2024-10","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Instant","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-12","retired":false,"tags":null},"openai/gpt-5.1-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-5.1-thinking","knowledge":"2024-10","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text","image"]},"model":null,"name":"GPT 5.1 Thinking","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-12","retired":false,"tags":null},"openai/gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.2","knowledge":"2024-10","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.2-codex","knowledge":"2024-10","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.2-Codex","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-18","retired":false,"tags":null},"openai/gpt-5.2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":21,"output":168},"deprecated":false,"extra":{"attachment":true,"description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-5.2-pro","knowledge":"2024-10","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.2 ","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.3-chat":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-5.3-chat","knowledge":null,"last_updated":"2026-03-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.3 Chat","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"openai/gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.3 Codex","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"openai/gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.4","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.4 Mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.4 Nano","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-5.4-pro","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.4 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"openai/gpt-5.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.5-pro","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.5 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"openai/gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.6 Luna","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.6 Sol","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT 5.6 Terra","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-image-1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":5,"output":40},"deprecated":false,"extra":{"attachment":false,"description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-image-1","knowledge":null,"last_updated":"2025-04-24","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"GPT Image 1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-03-25","retired":false,"tags":null},"openai/gpt-image-1-mini":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-image-1-mini","knowledge":null,"last_updated":"2025-10-06","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"GPT Image 1 Mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"openai/gpt-image-1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":5,"output":32},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-image-1.5","knowledge":null,"last_updated":"2025-11-25","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"GPT Image 1.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"openai/gpt-image-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":1.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-image-2","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"GPT Image 2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":"2024-10","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":"2024-10","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-safeguard-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.037,"input":0.075,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-safeguard-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-safeguard-20b-GGUF"}],"hf_downloads":101805,"hf_likes":243,"matched_hugging_face_id":"openai/gpt-oss-safeguard-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-safeguard-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-09-18","source":"llmfit","use_case":"General purpose text generation"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-oss-safeguard-20b","knowledge":"2024-10","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"gpt-oss-safeguard-20b","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-29","retired":false,"tags":null},"openai/gpt-realtime-1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.4,"input":4,"output":16},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-realtime-1.5","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":null,"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"GPT-Realtime-1.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"openai/gpt-realtime-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.4,"input":4,"output":24},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-realtime-2","knowledge":null,"last_updated":"2026-05-07","lifecycle":null,"limits":null,"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"gpt-realtime-2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"openai/gpt-realtime-2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.4,"input":4,"output":24},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"openai/gpt-realtime-2.1","knowledge":"2024-09-30","last_updated":"2026-07-06","lifecycle":null,"limits":{"context":128000,"output":32000},"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"gpt-realtime-2.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-realtime-mini":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.06,"input":0.6,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-realtime-mini","knowledge":null,"last_updated":"2025-10-10","lifecycle":null,"limits":null,"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"GPT-Realtime mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-10-10","retired":false,"tags":null},"openai/gpt-realtime-whisper":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","family":"whisper","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-realtime-whisper","knowledge":null,"last_updated":"2026-05-07","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"gpt-realtime-whisper","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"openai/o1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":7.5,"input":15,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","structured_output":true,"temperature":false},"family":null,"id":"openai/o1","knowledge":"2023-09","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"openai/o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/o3-deep-research":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":2.5,"input":10,"output":40},"deprecated":false,"extra":{"attachment":true,"description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium"]}],"temperature":true},"family":null,"id":"openai/o3-deep-research","knowledge":"2024-10","last_updated":"2024-06-26","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o3-deep-research","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-26","retired":false,"tags":null},"openai/o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","structured_output":true,"temperature":false},"family":null,"id":"openai/o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"openai/o3-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":20,"output":80},"deprecated":false,"extra":{"attachment":true,"description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/o3-pro","knowledge":"2024-10","last_updated":"2025-06-10","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o3 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-06-10","retired":false,"tags":null},"openai/o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","structured_output":true,"temperature":false},"family":null,"id":"openai/o4-mini","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/text-embedding-3-large":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"temperature":true},"family":null,"id":"openai/text-embedding-3-large","knowledge":null,"last_updated":"2024-01-25","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"text-embedding-3-large","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"openai/text-embedding-3-small":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"temperature":true},"family":null,"id":"openai/text-embedding-3-small","knowledge":null,"last_updated":"2024-01-25","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"text-embedding-3-small","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"openai/text-embedding-ada-002":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","open_weights":false,"temperature":true},"family":null,"id":"openai/text-embedding-ada-002","knowledge":null,"last_updated":"2022-12-15","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"text-embedding-ada-002","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2022-12-15","retired":false,"tags":null},"openai/tts-1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","open_weights":false,"temperature":true},"family":null,"id":"openai/tts-1","knowledge":null,"last_updated":"2023-11-06","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"TTS-1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/tts-1-hd":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","open_weights":false,"temperature":true},"family":null,"id":"openai/tts-1-hd","knowledge":null,"last_updated":"2023-11-06","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"TTS-1 HD","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/whisper-1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","open_weights":false,"temperature":true},"family":null,"id":"openai/whisper-1","knowledge":null,"last_updated":"2022-09-21","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2022-09-21","retired":false,"tags":null},"perplexity/pplx-embed-v1-0.6b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"v0","open_weights":false},"family":null,"id":"perplexity/pplx-embed-v1-0.6b","knowledge":null,"last_updated":"2026-02-26","lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Embed v1 0.6b","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"perplexity/pplx-embed-v1-4b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","open_weights":false},"family":null,"id":"perplexity/pplx-embed-v1-4b","knowledge":null,"last_updated":"2026-02-26","lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Embed v1 4b","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"perplexity/sonar":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","open_weights":false,"temperature":true},"family":null,"id":"perplexity/sonar","knowledge":"2025-02","last_updated":"2025-02-19","lifecycle":null,"limits":{"context":127000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-02-19","retired":false,"tags":null},"perplexity/sonar-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","open_weights":false,"temperature":true},"family":null,"id":"perplexity/sonar-pro","knowledge":"2025-09","last_updated":"2025-02-19","lifecycle":null,"limits":{"context":200000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-02-19","retired":false,"tags":null},"perplexity/sonar-reasoning-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"perplexity/sonar-reasoning-pro","knowledge":"2025-09","last_updated":"2025-02-19","lifecycle":null,"limits":{"context":127000,"output":8000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Reasoning Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-02-19","retired":false,"tags":null},"poolside/laguna-s-2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.1,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna-s","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"poolside/laguna-s-2.1","knowledge":null,"last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Laguna S 2.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"poolside/laguna-s-2.1-free":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","family":"laguna-s","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"poolside/laguna-s-2.1-free","knowledge":null,"last_updated":"2026-07-21","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Laguna S 2.1 Free","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"prodia/flux-fast-schnell":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","open_weights":false,"temperature":true},"family":null,"id":"prodia/flux-fast-schnell","knowledge":null,"last_updated":"2026-06-08","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Flux Schnell","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-08-02","retired":false,"tags":null},"quiverai/arrow-1.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"o","open_weights":false,"temperature":true},"family":null,"id":"quiverai/arrow-1.1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Arrow 1.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"recraft/recraft-v2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v2","knowledge":null,"last_updated":"2024-03","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-03-13","retired":false,"tags":null},"recraft/recraft-v3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v3","knowledge":null,"last_updated":"2024-10","lifecycle":null,"limits":{"context":512},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-10-30","retired":false,"tags":null},"recraft/recraft-v4":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v4","knowledge":null,"last_updated":"2026-02-17","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V4","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"recraft/recraft-v4-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v4-pro","knowledge":null,"last_updated":"2026-02-17","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V4 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"recraft/recraft-v4.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v4.1","knowledge":null,"last_updated":"2026-05-14","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V4.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-14","retired":false,"tags":null},"recraft/recraft-v4.1-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v4.1-pro","knowledge":null,"last_updated":"2026-05-14","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V4.1 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-14","retired":false,"tags":null},"recraft/recraft-v4.1-utility":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v4.1-utility","knowledge":null,"last_updated":"2026-05-14","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V4.1 Utility","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-14","retired":false,"tags":null},"recraft/recraft-v4.1-utility-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","open_weights":false,"temperature":true},"family":null,"id":"recraft/recraft-v4.1-utility-pro","knowledge":null,"last_updated":"2026-05-14","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Recraft V4.1 Utility Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-14","retired":false,"tags":null},"sakana/fugu-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"aura","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"sakana/fugu-ultra","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Fugu Ultra","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-21","retired":false,"tags":null},"stepfun/step-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.09,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","family":"step","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"stepfun/step-3.5-flash","knowledge":"2025-01","last_updated":"2026-02-13","lifecycle":null,"limits":{"context":262114,"output":262114},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"StepFun 3.5 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"stepfun/step-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","family":"step","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"stepfun/step-3.7-flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Step 3.7 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"tencent/hy3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hy3","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"temperature":true},"family":null,"id":"tencent/hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"thinkingmachines/inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.17,"input":1,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"thinkingmachines/inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"thinkingmachines/inkling-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"thinkingmachines/inkling-small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"voyage/rerank-2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/rerank-2.5","knowledge":null,"last_updated":"2025-08-11","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Voyage Rerank 2.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-11","retired":false,"tags":null},"voyage/rerank-2.5-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/rerank-2.5-lite","knowledge":null,"last_updated":"2025-08-11","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Voyage Rerank 2.5 Lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-11","retired":false,"tags":null},"voyage/voyage-3-large":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-3-large","knowledge":null,"last_updated":"2024-09","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-3-large","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-01-07","retired":false,"tags":null},"voyage/voyage-3.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-3.5","knowledge":null,"last_updated":"2025-05-20","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-3.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"voyage/voyage-3.5-lite":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-3.5-lite","knowledge":null,"last_updated":"2025-05-20","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-3.5-lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"voyage/voyage-4":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-4","knowledge":null,"last_updated":"2026-03-06","lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-4","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-15","retired":false,"tags":null},"voyage/voyage-4-large":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-4-large","knowledge":null,"last_updated":"2026-03-06","lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-4-large","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-15","retired":false,"tags":null},"voyage/voyage-4-lite":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-4-lite","knowledge":null,"last_updated":"2026-03-06","lifecycle":null,"limits":{"context":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-4-lite","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-15","retired":false,"tags":null},"voyage/voyage-code-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-code-2","knowledge":null,"last_updated":"2024-01","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-code-2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"voyage/voyage-code-3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-code-3","knowledge":null,"last_updated":"2024-09","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-code-3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-12-04","retired":false,"tags":null},"voyage/voyage-finance-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-finance-2","knowledge":null,"last_updated":"2024-03","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-finance-2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-06-03","retired":false,"tags":null},"voyage/voyage-law-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","open_weights":false,"temperature":true},"family":null,"id":"voyage/voyage-law-2","knowledge":null,"last_updated":"2024-03","lifecycle":null,"limits":{"context":8192,"output":1536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"voyage-law-2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2024-04-15","retired":false,"tags":null},"xai/grok-4.1-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-4.1-fast-non-reasoning","knowledge":"2024-10","last_updated":"2025-07-09","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast Non-Reasoning","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-19","retired":false,"tags":null},"xai/grok-4.1-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.2,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"xai/grok-4.1-fast-reasoning","knowledge":"2024-10","last_updated":"2025-07-09","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast Reasoning","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-11-19","retired":false,"tags":null},"xai/grok-4.20-multi-agent":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"xai/grok-4.20-multi-agent","knowledge":null,"last_updated":"2026-03-23","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 Multi-Agent","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"xai/grok-4.20-multi-agent-beta":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"temperature":true},"family":null,"id":"xai/grok-4.20-multi-agent-beta","knowledge":null,"last_updated":"2026-03-13","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 Multi Agent Beta","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"xai/grok-4.20-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-4.20-non-reasoning","knowledge":null,"last_updated":"2026-03-23","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 Non-Reasoning","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"xai/grok-4.20-non-reasoning-beta":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.4,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-4.20-non-reasoning-beta","knowledge":null,"last_updated":"2026-03-13","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 Beta Non-Reasoning","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"xai/grok-4.20-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"xai/grok-4.20-reasoning","knowledge":null,"last_updated":"2026-03-23","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 Reasoning","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-10","retired":false,"tags":null},"xai/grok-4.20-reasoning-beta":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"xai/grok-4.20-reasoning-beta","knowledge":null,"last_updated":"2026-03-13","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 Beta Reasoning","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"xai/grok-4.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-30","retired":false,"tags":null},"xai/grok-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"xai/grok-build-0.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-build-0.1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-20","retired":false,"tags":null},"xai/grok-imagine-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-imagine-image","knowledge":null,"last_updated":"2026-02-19","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["text","image"]},"model":null,"name":"Grok Imagine Image","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"xai/grok-imagine-video":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-imagine-video","knowledge":null,"last_updated":"2026-01-28","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Grok Imagine","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-28","retired":false,"tags":null},"xai/grok-imagine-video-1.5":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-imagine-video-1.5","knowledge":null,"last_updated":"2026-05-30","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Grok Imagine Video 1.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-22","retired":false,"tags":null},"xai/grok-imagine-video-1.5-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-imagine-video-1.5-preview","knowledge":null,"last_updated":"2026-05-30","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["video"]},"model":null,"name":"Grok Imagine Video 1.5 Preview","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-05-30","retired":false,"tags":null},"xai/grok-stt":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-stt","knowledge":null,"last_updated":"2026-03-16","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Grok STT","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"xai/grok-tts":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-tts","knowledge":null,"last_updated":"2026-03-16","lifecycle":null,"limits":null,"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Grok TTS","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"xai/grok-voice-think-fast-1.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"xai/grok-voice-think-fast-1.0","knowledge":null,"last_updated":"2026-04-23","lifecycle":null,"limits":null,"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"Grok Voice Think Fast 1.0","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"xai/grok-voice-think-fast-2.0":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","open_weights":false},"family":null,"id":"xai/grok-voice-think-fast-2.0","knowledge":null,"last_updated":"2026-07-29","lifecycle":null,"limits":null,"modalities":{"input":["text","audio"],"output":["text","audio"]},"model":null,"name":"Grok Voice Think Fast 2.0","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-07-29","retired":false,"tags":null},"xiaomi/mimo-v2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo-v2.5","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"xiaomi/mimo-v2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1050000,"output":131100},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"MiMo M2.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"xiaomi/mimo-v2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0036,"input":0.435,"output":0.87},"deprecated":false,"extra":{"attachment":true,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo-v2.5-pro","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"xiaomi/mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1050000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo V2.5 Pro","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"zai/glm-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.5","knowledge":"2025-07","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":128000,"output":96000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai/glm-4.5-air":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.2,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.5-air","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":128000,"output":96000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.5 Air","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"zai/glm-4.5v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.5v","knowledge":"2025-08","last_updated":"2025-08-11","lifecycle":null,"limits":{"context":66000,"output":16000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GLM 4.5V","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-08-11","retired":false,"tags":null},"zai/glm-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":200000,"output":96000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.6","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai/glm-4.6v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.6v","knowledge":"2024-10","last_updated":"2025-12-08","lifecycle":null,"limits":{"context":128000,"output":24000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GLM-4.6V","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai/glm-4.6v-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.6v-flash","knowledge":"2024-10","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":128000,"output":24000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GLM-4.6V-Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai/glm-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","interleaved":true,"open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.7","knowledge":"2024-10","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":200000,"output":120000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai/glm-4.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":131000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7 Flash","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai/glm-4.7-flashx":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.06,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","interleaved":true,"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-4.7-flashx","knowledge":"2025-01","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7 FlashX","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"zai/glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202800,"output":131100},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai/glm-5-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5-turbo","knowledge":null,"last_updated":"2026-03-16","lifecycle":null,"limits":{"context":202800,"output":131100},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5 Turbo","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"zai/glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202000,"output":202000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai/glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":1.1,"output":3.851},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null},"zai/glm-5.2-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.21,"input":2.1,"output":6.6},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5.2-fast","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Fast","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-06-23","retired":false,"tags":null},"zai/glm-5v-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"zai/glm-5v-turbo","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GLM 5V Turbo","pricing":null,"provider":"vercel","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null}},"name":"Vercel AI Gateway","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;