@agentjido/llmdb 2026.8.2

package/dist/providers/llmgateway.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.llmgateway.io/v1","catalog_only":true,"config_schema":null,"doc":"https://llmgateway.io/docs","env":["LLMGATEWAY_API_KEY"],"exclude_models":null,"extra":null,"id":"llmgateway","models":{"auto":{"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":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"auto","knowledge":null,"last_updated":"2024-01-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Auto Route","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"claude-3-opus":{"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":1.5,"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","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"claude-3-opus","knowledge":null,"last_updated":"2024-03-04","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude 3 Opus","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-03-04","retired":false,"tags":null},"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":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"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","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"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 (latest)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-haiku-4-5-20251001":{"aliases":[],"base_url":null,"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 model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"claude-haiku-4-5-20251001","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":"llmgateway","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-haiku-4-5-free":{"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":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"claude-haiku-4-5-free","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":200000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5 (latest)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1-20250805":{"aliases":[],"base_url":null,"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":[{"type":"effort","values":["low","medium","high","xhigh"]},{"max":31999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-1-20250805","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":"llmgateway","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-5-20251101":{"aliases":[],"base_url":null,"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":31999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-5-20251101","knowledge":"2025-05","last_updated":"2025-11-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-11-01","retired":false,"tags":null},"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","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"temperature":true},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"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":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"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":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"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":"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":"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":"llmgateway","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"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":[{"type":"effort","values":["low","medium","high","xhigh","max"]},{"max":63999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5 (latest)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-5-20250929":{"aliases":[],"base_url":null,"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":[{"type":"effort","values":["low","medium","high","xhigh","max"]},{"max":63999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-5-20250929","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"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","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]},{"max":63999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"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":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"codestral-2508":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Mistral coding model for code completion, generation, and developer workflows","family":"mistral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"codestral-2508","knowledge":null,"last_updated":"2025-07-30","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Codestral","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"cosmos3-super-reasoner":{"aliases":[],"base_url":null,"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":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"cosmos3-super-reasoner","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Cosmos 3 Super Reasoner","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"custom":{"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":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"custom","knowledge":null,"last_updated":"2024-01-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Custom Model","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":0.26,"output":0.38},"deprecated":false,"extra":{"attachment":true,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v3.2","knowledge":null,"last_updated":"2025-09-29","lifecycle":null,"limits":{"context":163840,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"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":0.014,"input":0.076,"output":0.153},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1050000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"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":0.003625,"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-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1050000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"devstral-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","open_weights":true,"status":"deprecated","temperature":true},"family":null,"id":"devstral-2512","knowledge":"2025-12","last_updated":"2025-12-09","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Devstral 2","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-09","retired":false,"tags":null},"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","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"fugu-ultra","knowledge":null,"last_updated":"2026-06-22","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Fugu Ultra","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-22","retired":false,"tags":null},"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,"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":"effort","values":["minimal","low","medium","high"]},{"max":24576,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-2.5-flash-lite","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-Lite","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"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":[{"type":"effort","values":["minimal","low","medium","high"]},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"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":0.025,"cache_write":0.08333,"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-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"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-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"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,"cache_write":0.08333,"input":1.5,"output":9},"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"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"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,"cache_write":0.08333,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"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,"cache_write":0.08333,"input":1.5,"output":7.5},"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"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-pro-latest":{"aliases":[],"base_url":null,"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":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-pro-latest","knowledge":null,"last_updated":"2026-02-27","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemini Pro Latest","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-27","retired":false,"tags":null},"gemma-3-27b":{"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":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"gemma-3-27b","knowledge":null,"last_updated":"2025-03-12","lifecycle":null,"limits":{"context":110000,"output":110000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 3 27B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"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":{"input":0.07,"output":0.34},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.012,"input":0.102,"output":0.297},"deprecated":false,"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemma-4-31b-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 31B IT","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"glm-4-32b-0414-128k":{"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":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"glm-4-32b-0414-128k","knowledge":null,"last_updated":"2025-04-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4 32B (0414-128k)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"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,"cache_write":0,"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","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"glm-4.5","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131000,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"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":0.025,"cache_write":0,"input":0.13,"output":0.85},"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":[],"temperature":true},"family":null,"id":"glm-4.5-air","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":131000,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5-Air","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"glm-4.5-airx":{"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":0.22,"input":1.1,"output":4.5},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"glm-4.5-airx","knowledge":null,"last_updated":"2025-07-28","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5 AirX","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"glm-4.5-x":{"aliases":[],"base_url":null,"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":2.2,"output":8.9},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":false,"reasoning_options":[{"type":"toggle"}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"glm-4.5-x","knowledge":null,"last_updated":"2025-07-28","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.5 X","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"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":"glm-4.5v","knowledge":"2025-04","last_updated":"2025-08-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"GLM-4.5V","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-08-11","retired":false,"tags":null},"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,"cache_write":0,"input":0.55,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"glm-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"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":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"glm-4.6v","knowledge":"2025-04","last_updated":"2025-12-08","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"GLM-4.6V","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"glm-4.6v-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":0.004,"input":0.04,"output":0.4},"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"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-4.6v-flashx","knowledge":null,"last_updated":"2025-12-08","lifecycle":null,"limits":{"context":128000,"output":16000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GLM-4.6V FlashX","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"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":0.19,"cache_write":0,"input":0.38,"output":1.98},"deprecated":false,"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"glm-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"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":{"cache_read":0.01,"cache_write":0,"input":0.06,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"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,"cache_write":0,"input":0.07,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"glm-4.7-flashx","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-FlashX","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"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":{"cache_read":0.144,"cache_write":0,"input":0.72,"output":2.3},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":203000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"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":0.173,"cache_write":0,"input":0.931,"output":2.93},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"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":0.16,"cache_write":0,"input":0.8,"output":2.55},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-3.5-turbo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0,"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":"gpt-3.5-turbo","knowledge":"2021-09-01","last_updated":"2023-11-06","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-3.5-turbo","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2023-03-01","retired":false,"tags":null},"gpt-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"gpt-4","knowledge":"2023-11","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-4","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"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,"structured_output":false,"temperature":true},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"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":"gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"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":"gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"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,"structured_output":true,"temperature":true},"family":null,"id":"gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"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":"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":"llmgateway","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"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":"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":"llmgateway","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"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":true,"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":"gpt-4o-mini-search-preview","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o Mini Search Preview","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"gpt-4o-mini-transcribe":{"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":1.25,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"gpt-4o-mini-transcribe","knowledge":null,"last_updated":"2025-03-20","lifecycle":null,"limits":{"context":16000,"output":16000},"modalities":{"input":["text","audio"],"output":["text"]},"model":null,"name":"GPT-4o Mini Transcribe","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-03-20","retired":false,"tags":null},"gpt-4o-search-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"gpt-4o-search-preview","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o Search Preview","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"gpt-4o-transcribe":{"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":true,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"gpt-4o-transcribe","knowledge":null,"last_updated":"2025-03-20","lifecycle":null,"limits":{"context":16000,"output":16000},"modalities":{"input":["text","audio"],"output":["text"]},"model":null,"name":"GPT-4o Transcribe","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-03-20","retired":false,"tags":null},"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":"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":"llmgateway","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"gpt-5-chat-latest":{"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":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gpt-5-chat-latest","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 Chat (latest)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"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":"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":"llmgateway","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"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":"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":"llmgateway","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"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-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5-pro","knowledge":"2024-09-30","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":400000,"output":272000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5 Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"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":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"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":0.025,"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-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.1-codex-mini","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex mini","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"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":false},"family":null,"id":"gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"gpt-5.2-chat-latest":{"aliases":[],"base_url":null,"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":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.2-chat-latest","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Chat","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"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":false},"family":null,"id":"gpt-5.2-codex","knowledge":"2025-08-31","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":"llmgateway","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"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-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":false,"temperature":false},"family":null,"id":"gpt-5.2-pro","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"gpt-5.3-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"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,"structured_output":true,"temperature":true},"family":null,"id":"gpt-5.3-chat-latest","knowledge":"2025-08-31","last_updated":"2026-03-03","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Chat (latest)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"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-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"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":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"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-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"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-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"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-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":false,"temperature":false},"family":null,"id":"gpt-5.4-pro","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"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":false},"family":null,"id":"gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"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-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"gpt-5.5-pro","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5 Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"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":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"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":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"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":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"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":{"cache_read":0.032,"input":0.032,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32766},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"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":0.04,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32766},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"grok-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"grok-4","knowledge":null,"last_updated":"2025-07-09","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"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":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"grok-4-1-fast-non-reasoning","knowledge":null,"last_updated":"2025-11-19","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast Non-Reasoning","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-11-19","retired":false,"tags":null},"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":true,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-1-fast-reasoning","knowledge":null,"last_updated":"2025-11-19","lifecycle":null,"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.1 Fast Reasoning","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-11-19","retired":false,"tags":null},"grok-4-20-beta-0309-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":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,"structured_output":true,"temperature":true},"family":null,"id":"grok-4-20-beta-0309-non-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Non-Reasoning)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"grok-4-20-beta-0309-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":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-20-beta-0309-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Reasoning)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"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,"structured_output":true,"temperature":true},"family":null,"id":"grok-4-20-non-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Non-Reasoning)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"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":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-20-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.20 (Reasoning)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"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":0.3125,"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":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"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":0.5,"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":false,"temperature":true},"family":null,"id":"grok-4-5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"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":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-build-0-1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"hermes-4-405b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"hermes-4-405b","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes 4 405B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"hermes-4-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"hermes-4-70b","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes 4 70B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"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":"Hy","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"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":{"cache_read":0.5,"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":true,"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2","knowledge":null,"last_updated":"2025-07-11","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-11","retired":false,"tags":null},"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":0.06,"input":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"kimi-k2-thinking","knowledge":"2024-08","last_updated":"2025-11-06","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"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":0.225,"input":0.405,"output":1.98},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"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":0.048,"input":0.22,"output":1.137},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"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","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"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","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.7-code-highspeed","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code Highspeed","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"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":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"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":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3-fast","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1040384,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"llama-3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.51,"output":0.74},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"llama-3-70b-instruct","knowledge":null,"last_updated":"2024-04-18","lifecycle":null,"limits":{"context":8192,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3 70B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-04-18","retired":false,"tags":null},"llama-3.1-70b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"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":true,"status":"beta","structured_output":false,"temperature":true},"family":null,"id":"llama-3.1-70b-instruct","knowledge":null,"last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":2048},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 70B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"llama-3.1-nemotron-ultra-253b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.6,"output":1.8},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"llama-3.1-nemotron-ultra-253b","knowledge":null,"last_updated":"2025-04-07","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 Nemotron Ultra 253B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-07","retired":false,"tags":null},"llama-3.2-11b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.07,"output":0.33},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"llama-3.2-11b-instruct","knowledge":null,"last_updated":"2024-09-25","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 11B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"llama-3.2-3b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.03,"output":0.05},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"llama-3.2-3b-instruct","knowledge":null,"last_updated":"2024-09-18","lifecycle":null,"limits":{"context":32768,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-09-18","retired":false,"tags":null},"llama-3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"llama-4-maverick-17b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.27,"output":0.85},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"llama-4-maverick-17b-instruct","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":1048576,"output":2048},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"llama-4-scout-17b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.18,"output":0.59},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"llama-4-scout-17b-instruct","knowledge":null,"last_updated":"2025-04-05","lifecycle":null,"limits":{"context":131072,"output":2048},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Scout 17B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-05","retired":false,"tags":null},"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","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"mimo-v2.5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"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":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"mimo-v2.5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo-V2.5-Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"minicpm-v-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.658,"output":1.11},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"minicpm-v-4.5","knowledge":null,"last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"MiniCPM-V 4.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"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,"input":0.2,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m2","knowledge":null,"last_updated":"2025-10-27","lifecycle":null,"limits":{"context":196608,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-10-27","retired":false,"tags":null},"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":{"input":0.27,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m2.1","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.1","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.12,"output":0.48},"deprecated":false,"extra":{"attachment":false,"description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"minimax-m2.1-lightning","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":196608,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.1 Lightning","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"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":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":228700,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"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":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax-m2.5-highspeed","knowledge":null,"last_updated":"2026-02-13","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5-highspeed","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-13","retired":false,"tags":null},"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":0.017,"cache_write":0.375,"input":0.08,"output":0.32},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"minimax-m2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"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":false,"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-m2.7-highspeed","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7-highspeed","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"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","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"temperature":true},"family":null,"id":"minimax-m3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":1048576,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"minimax-text-01":{"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":0.2,"output":1.1},"deprecated":false,"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"minimax-text-01","knowledge":null,"last_updated":"2025-01-15","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax Text 01","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"ministral-14b-2512":{"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":"mistral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"ministral-14b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 14B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"ministral-3b-2512":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.1,"output":0.1},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"ministral-3b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 3B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"ministral-8b-2512":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.15,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"ministral-8b-2512","knowledge":null,"last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Ministral 8B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistral-large-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","open_weights":true,"temperature":true},"family":null,"id":"mistral-large-2512","knowledge":"2024-11","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Large 3","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"mistral-large-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":4,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":true,"temperature":true},"family":null,"id":"mistral-large-latest","knowledge":"2024-11","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":128000,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Large (latest)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"mistral-small-2506":{"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":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"mistral-small-2506","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 3.2","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"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":true,"description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"muse-spark-1.1","knowledge":null,"last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1048576,"output":32000},"modalities":{"input":["text","image","pdf","video"],"output":["text"]},"model":null,"name":"Muse Spark 1.1","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"nemotron-3-nano-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":0.06,"output":0.24},"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"}],"structured_output":false,"temperature":true},"family":null,"id":"nemotron-3-nano-30b","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"nemotron-3-nano-omni":{"aliases":[],"base_url":null,"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":0.24},"deprecated":false,"extra":{"attachment":true,"description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"nemotron-3-nano-omni","knowledge":null,"last_updated":"2026-04-28","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano Omni","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-28","retired":false,"tags":null},"nemotron-3-super-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":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":false,"temperature":true},"family":null,"id":"nemotron-3-super-120b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nemotron-3-ultra-550b":{"aliases":[],"base_url":null,"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":0.5,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"nemotron-3-ultra-550b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":1048576,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra 550B A55B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"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"]}],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"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":[],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"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":[],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"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"]}],"structured_output":true,"temperature":false},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"qwen-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":{"input":0.502,"output":1.004},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen-coder-plus","knowledge":null,"last_updated":"2024-09-18","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen Coder Plus","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-09-18","retired":false,"tags":null},"qwen-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":0.01,"cache_write":0.0625,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen-flash","knowledge":"2024-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"qwen-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":{"input":1.6,"output":6.4},"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":"qwen-max","knowledge":"2024-04","last_updated":"2025-01-25","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen Max","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-04-03","retired":false,"tags":null},"qwen-max-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.6,"output":6.4},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen-max-latest","knowledge":null,"last_updated":"2025-01-25","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen Max Latest","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-01-25","retired":false,"tags":null},"qwen-omni-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":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen-omni-turbo","knowledge":"2024-04","last_updated":"2025-03-26","lifecycle":null,"limits":{"context":32768,"output":2048},"modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"model":null,"name":"Qwen-Omni Turbo","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-01-19","retired":false,"tags":null},"qwen-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":1.2,"reasoning":4},"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":"qwen-plus","knowledge":"2024-04","last_updated":"2025-09-11","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen Plus","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"qwen-plus-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"cache_write":0.5,"input":0.4,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen-plus-latest","knowledge":null,"last_updated":"2025-01-25","lifecycle":null,"limits":{"context":1000000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen Plus Latest","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-01-25","retired":false,"tags":null},"qwen2-5-vl-32b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.4,"output":4.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen2-5-vl-32b-instruct","knowledge":null,"last_updated":"2025-03-15","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen2.5 VL 32B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-03-15","retired":false,"tags":null},"qwen2-5-vl-72b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.25,"output":0.75},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen2-5-vl-72b-instruct","knowledge":"2024-04","last_updated":"2024-09","lifecycle":null,"limits":{"context":32000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen2.5-VL 72B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-09","retired":false,"tags":null},"qwen3-235b-a22b-fp8":{"aliases":[],"base_url":null,"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":0.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-235b-a22b-fp8","knowledge":null,"last_updated":"2025-04-28","lifecycle":null,"limits":{"context":40960,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B FP8","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-235b-a22b-instruct-2507","knowledge":null,"last_updated":"2025-07-08","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct (2507)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-08","retired":false,"tags":null},"qwen3-235b-a22b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-235b-a22b-thinking-2507","knowledge":null,"last_updated":"2025-07-08","lifecycle":null,"limits":{"context":262000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Thinking (2507)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-08","retired":false,"tags":null},"qwen3-30b-a3b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-30b-a3b-instruct-2507","knowledge":null,"last_updated":"2025-07-08","lifecycle":null,"limits":{"context":262000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B Instruct (2507)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-08","retired":false,"tags":null},"qwen3-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.3,"reasoning":8.4},"deprecated":false,"extra":{"attachment":false,"description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"qwen3-32b","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":40960,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen3-coder-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.27},"deprecated":false,"extra":{"attachment":false,"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen3-coder-30b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 30B-A3B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen3-coder-480b-a35b-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":0.3,"output":1.3},"deprecated":false,"extra":{"attachment":false,"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen3-coder-480b-a35b-instruct","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":"llmgateway","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen3-coder-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.375,"input":0.3,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-coder-flash","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"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":{"cache_read":0.06,"input":0.108,"output":0.675},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-coder-next","knowledge":null,"last_updated":"2025-10-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"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":1.2,"cache_write":7.5,"input":6,"output":60},"deprecated":false,"extra":{"attachment":false,"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"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":"llmgateway","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"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":0.6,"cache_write":3.75,"input":0.845,"output":3.38},"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":"qwen3-max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"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":"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":"llmgateway","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"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":[],"temperature":true},"family":null,"id":"qwen3-next-80b-a3b-thinking","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 (Thinking)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"qwen3-vl-235b-a22b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.2,"output":0.88},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-vl-235b-a22b-instruct","knowledge":null,"last_updated":"2025-09-15","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B A22B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-15","retired":false,"tags":null},"qwen3-vl-235b-a22b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.98,"output":3.95},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-vl-235b-a22b-thinking","knowledge":null,"last_updated":"2025-09-15","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B A22B Thinking","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-15","retired":false,"tags":null},"qwen3-vl-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-vl-30b-a3b-instruct","knowledge":null,"last_updated":"2025-10-02","lifecycle":null,"limits":{"context":262144,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL 30B A3B Instruct","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-10-02","retired":false,"tags":null},"qwen3-vl-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.05,"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,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-vl-flash","knowledge":null,"last_updated":"2025-10-09","lifecycle":null,"limits":{"context":262144,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-10-09","retired":false,"tags":null},"qwen3-vl-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":0.25,"input":0.2,"output":1.6,"reasoning":4.8},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-vl-plus","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3-VL Plus","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen3.5-9b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.1,"output":0.15},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.5-9b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 9B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen3.6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.248,"output":1.485},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-35b-a3b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"qwen3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0.3125,"input":0.25,"output":1.5},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-flash","knowledge":null,"last_updated":"2026-04-27","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-27","retired":false,"tags":null},"qwen3.6-max-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"cache_write":1.625,"input":1.3,"output":7.8},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.6-max-preview","knowledge":"2025-04","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 Max Preview","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"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":0.05,"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":[],"temperature":true},"family":null,"id":"qwen3.6-plus","knowledge":"2025-04","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Plus","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"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":0.0375,"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"qwen3.7-flash","knowledge":null,"last_updated":"2026-07-27","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.7 Flash","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"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":0.125,"cache_write":3.125,"input":1.25,"output":3.75},"deprecated":false,"extra":{"attachment":false,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.7-max","knowledge":null,"last_updated":"2026-05-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"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":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3.7-plus","knowledge":"2025-04","last_updated":"2026-06-02","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"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"]},{"type":"budget_tokens"}],"temperature":true},"family":null,"id":"qwen3.8-max","knowledge":null,"last_updated":"2026-07-19","lifecycle":null,"limits":{"context":1000000,"output":1000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.8 Max Preview","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-07-19","retired":false,"tags":null},"qwen35-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen35-397b-a17b","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"seed-1-6-250615":{"aliases":[],"base_url":null,"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":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-1-6-250615","knowledge":null,"last_updated":"2025-06-25","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 1.6 (250615)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-06-25","retired":false,"tags":null},"seed-1-6-250915":{"aliases":[],"base_url":null,"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":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-1-6-250915","knowledge":null,"last_updated":"2025-09-15","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 1.6 (250915)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-09-15","retired":false,"tags":null},"seed-1-6-flash-250715":{"aliases":[],"base_url":null,"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":0.07,"output":0.3},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-1-6-flash-250715","knowledge":null,"last_updated":"2025-07-26","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 1.6 Flash (250715)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-07-26","retired":false,"tags":null},"seed-1-8-251228":{"aliases":[],"base_url":null,"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":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-1-8-251228","knowledge":null,"last_updated":"2025-12-18","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 1.8 (251228)","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2025-12-18","retired":false,"tags":null},"sonar":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","open_weights":false,"temperature":true},"family":null,"id":"sonar","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":130000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sonar","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"sonar-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","open_weights":false,"temperature":true},"family":null,"id":"sonar-pro","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"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":{"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"sonar-reasoning-pro","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Reasoning Pro","pricing":null,"provider":"llmgateway","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null}},"name":"LLM Gateway","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;