@agentjido/llmdb 2026.8.2

package/dist/providers/empiriolabs.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.empiriolabs.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.empiriolabs.ai","env":["EMPIRIOLABS_API_KEY"],"exclude_models":null,"extra":null,"id":"empiriolabs","models":{"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":0.14,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":393216,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":1000000,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.14,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":393216,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1000000,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-07-31","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":1.65,"input":1.65,"output":3.3},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":393216,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":1000000,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"gemma-4-26b-a4b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.05,"output":0.29},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":32768,"min":128,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"gemma-4-26b-a4b","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Gemma 4 26B-A4B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"glm-4-5-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":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-4-5-flash","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":200000,"output":98304},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.5 Flash","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2025-07-28","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":{"input":0,"output":0},"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":[{"type":"toggle"}],"structured_output":true,"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":"empiriolabs","provider_model_id":null,"release_date":"2026-01-19","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":0.165,"input":0.825,"output":3.301},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":38912,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5-1","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":202000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"empiriolabs","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":1.4,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5-2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-06-13","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":0.1788,"input":0.8939,"output":3.7131},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":81920,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2-6","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":256000,"output":16000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"empiriolabs","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":0.95,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2-7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"empiriolabs","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":1.9,"input":1.9,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","open_weights":true,"reasoning_options":[],"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":256000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code Highspeed","pricing":null,"provider":"empiriolabs","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":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":["low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-07-16","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":0.014,"input":0.7,"output":1.4},"deprecated":false,"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"mimo-v2-5","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo V2.5","pricing":null,"provider":"empiriolabs","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":0.018,"input":2.175,"output":4.35},"deprecated":false,"extra":{"attachment":false,"description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"mimo-v2-5-pro","knowledge":"2024-12","last_updated":"2026-04-22","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiMo V2.5 Pro","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-04-22","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":0.03,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax-m2-7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":200000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.7","pricing":null,"provider":"empiriolabs","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":0.03,"input":0.3,"output":1.2},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax-m2-7-highspeed","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":200000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.7 Highspeed","pricing":null,"provider":"empiriolabs","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":0.045,"input":0.225,"output":0.9},"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":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"minimax-m3","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":1000000,"output":524288},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax M3","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"mistral-medium-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistral-medium-3","knowledge":"2025-05","last_updated":"2025-05-07","lifecycle":null,"limits":{"context":130000,"output":40000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"mistral-small-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":0.15,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral-small-4","knowledge":"2025-06","last_updated":"2026-03-16","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-03-16","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":1,"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":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Muse Spark 1.1","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-04-08","retired":false,"tags":null},"qwen3-5-122b-a10b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.115,"input":0.115,"output":0.917},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":80000,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-122b-a10b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 122B-A10B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen3-5-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.086,"input":0.086,"output":0.688},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":80000,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-27b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 27B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen3-5-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.057,"input":0.057,"output":0.459},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":80000,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-35b-a3b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 35B-A3B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen3-5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.172,"input":0.172,"output":1.032},"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":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":80000,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-397b-a17b","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"qwen3-5-4b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.04,"output":0.07},"deprecated":false,"extra":{"attachment":true,"description":"Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":32768,"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-4b","knowledge":null,"last_updated":"2026-03-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 4B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-03-02","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":{"cache_read":0.045,"input":0.09,"output":0.13},"deprecated":false,"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":32768,"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-9b","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 9B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-23","retired":false,"tags":null},"qwen3-5-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.36,"input":0.36,"output":2.21},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-plus","knowledge":"2025-04","last_updated":"2026-02-16","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 Plus","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"qwen3-6-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.412564,"input":0.412564,"output":2.475384},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":80000,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-27b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-04-22","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":{"cache_read":0.035,"input":0.07,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-35b-a3b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B","pricing":null,"provider":"empiriolabs","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":0.25,"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":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":64000,"min":1,"type":"budget_tokens"}],"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":"empiriolabs","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":1.31,"input":1.31,"output":7.88},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":393216,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-max-preview","knowledge":"2025-04","last_updated":"2026-04-20","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.6 Max Preview","pricing":null,"provider":"empiriolabs","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":0.5,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-plus","knowledge":"2025-04","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.6 Plus","pricing":null,"provider":"empiriolabs","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,"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":true,"description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":131072,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-7-flash","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Flash","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-07-15","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":2.5,"input":2.5,"output":7.5},"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":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":64000,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-7-max","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.7 Max","pricing":null,"provider":"empiriolabs","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":0.4,"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":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":256000,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-7-plus","knowledge":"2025-04","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.7 Plus","pricing":null,"provider":"empiriolabs","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":2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"max":262144,"min":1,"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-8-max","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.8 Max","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"qwen3-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":1.08,"input":1.08,"output":5.52},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"step-3-5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"step-3-5-flash","knowledge":"2025-01","last_updated":"2026-02-13","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Step 3.5 Flash","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"step-3-5-flash-2603":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.1,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"step-3-5-flash-2603","knowledge":"2025-01","last_updated":"2026-04-02","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Step 3.5 Flash 2603","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"step-3-7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"step-3-7-flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Step 3.7 Flash","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-05-29","retired":false,"tags":null}},"name":"EmpirioLabs AI","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/evroc.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "evroc",
+  "KBLab/kb-whisper-large" | "Qwen/Qwen3-Embedding-8B" | "Qwen/Qwen3-Reranker-4B" | "Qwen/Qwen3-VL-30B-A3B-Instruct" | "Qwen/Qwen3.6-35B-A3B-FP8" | "evroc/roc" | "google/gemma-4-26B-A4B-it" | "intfloat/multilingual-e5-large-instruct" | "mistralai/Mistral-Medium-3.5-128B" | "mistralai/Voxtral-Small-24B-2507" | "moonshotai/Kimi-K2.6" | "nvidia/Llama-3.3-70B-Instruct-FP8" | "openai/gpt-oss-120b" | "openai/whisper-large-v3" | "openai/whisper-large-v3-turbo" | "zai-org/GLM-5.2"
+>;
+export default provider;

package/dist/providers/evroc.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://models.think.evroc.com/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.evroc.com/products/think/overview.html","env":["EVROC_API_KEY"],"exclude_models":null,"extra":null,"id":"evroc","models":{"KBLab/kb-whisper-large":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","open_weights":true},"family":null,"id":"KBLab/kb-whisper-large","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":{"context":448,"output":448},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"KB Whisper","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"Qwen/Qwen3-Embedding-8B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.115,"output":0.115},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","llmfit":{"architecture":"qwen3","context_length":40960,"discovered":true,"gguf_sources":[],"hf_downloads":3352596,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-Embedding-8B","memory":{"min_ram_gb":4.2,"min_vram_gb":3.9,"recommended_ram_gb":7.0},"model_id":"Qwen/Qwen3-Embedding-8B","parameter_count":"7.6B","parameters_raw":7567295488,"pipeline_tag":"feature-extraction","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Text embeddings for RAG"},"open_weights":true},"family":null,"id":"Qwen/Qwen3-Embedding-8B","knowledge":null,"last_updated":"2025-07-30","lifecycle":null,"limits":{"context":40960,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Embedding 8B","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"Qwen/Qwen3-Reranker-4B":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":true,"streaming":{"text":false,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.0575,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","open_weights":true},"family":null,"id":"Qwen/Qwen3-Reranker-4B","knowledge":null,"last_updated":"2025-07-30","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Reranker 4B","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"Qwen/Qwen3-VL-30B-A3B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.23,"output":0.92},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","llmfit":{"architecture":"qwen3_vl_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":815503,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","memory":{"min_ram_gb":17.4,"min_vram_gb":15.9,"recommended_ram_gb":28.9},"model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","moe":{"active_experts":8,"active_parameters":3398363717,"is_moe":true,"num_experts":128},"parameter_count":"31.1B","parameters_raw":31070754032,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true},"family":null,"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","knowledge":null,"last_updated":"2025-07-30","lifecycle":null,"limits":{"context":100000,"output":100000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3 VL 30B","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2025-07-30","retired":false,"tags":null},"Qwen/Qwen3.6-35B-A3B-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":0.345,"output":1.38},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","llmfit":{"architecture":"qwen3_5_moe","context_length":262144,"discovered":true,"gguf_sources":[],"hf_downloads":8818827,"hf_likes":0,"matched_hugging_face_id":"Qwen/Qwen3.6-35B-A3B-FP8","memory":{"min_ram_gb":20.1,"min_vram_gb":18.4,"recommended_ram_gb":33.5},"model_id":"Qwen/Qwen3.6-35B-A3B-FP8","moe":{"active_experts":8,"active_parameters":2865078437,"is_moe":true,"num_experts":256},"parameter_count":"36.0B","parameters_raw":35953925552,"pipeline_tag":"image-text-to-text","provider":"Alibaba","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"Qwen/Qwen3.6-35B-A3B-FP8","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":"evroc","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"evroc/roc":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.875,"output":11.516},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"evroc/roc","knowledge":"2026-01","last_updated":"2026-06-06","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"roc","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2026-06-06","retired":false,"tags":null},"google/gemma-4-26B-A4B-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.144,"output":0.575},"deprecated":false,"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","llmfit":{"architecture":"gemma4","context_length":262144,"discovered":false,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gemma-4-26B-A4B-it-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gemma-4-26B-A4B-it-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gemma-4-26B-A4B-it-GGUF"}],"hf_downloads":11882790,"hf_likes":1348,"matched_hugging_face_id":"google/gemma-4-26B-A4B-it","memory":{"min_ram_gb":14.8,"min_vram_gb":13.6,"recommended_ram_gb":24.7},"model_id":"google/gemma-4-26B-A4B-it","moe":{"active_experts":8,"active_parameters":4000000000,"is_moe":true,"num_experts":128},"parameter_count":"26.5B","parameters_raw":26544131376,"pipeline_tag":"image-text-to-text","provider":"Google","quantization":"Q4_K_M","release_date":"2026-03-11","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemma-4-26B-A4B-it","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 26B A4B IT","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"intfloat/multilingual-e5-large-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.114,"output":0.114},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","llmfit":{"architecture":"xlm-roberta","context_length":514,"discovered":true,"gguf_sources":[],"hf_downloads":2255045,"hf_likes":0,"matched_hugging_face_id":"intfloat/multilingual-e5-large-instruct","memory":{"min_ram_gb":1.0,"min_vram_gb":0.5,"recommended_ram_gb":2.0},"model_id":"intfloat/multilingual-e5-large-instruct","parameter_count":"560M","parameters_raw":559890432,"pipeline_tag":"feature-extraction","provider":"intfloat","quantization":"Q4_K_M","source":"llmfit","use_case":"Instruction following, chat"},"open_weights":true},"family":null,"id":"intfloat/multilingual-e5-large-instruct","knowledge":null,"last_updated":"2024-06-01","lifecycle":null,"limits":{"context":512,"output":512},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"E5 Multi-Lingual Large Embeddings 0.6B","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"mistralai/Mistral-Medium-3.5-128B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":1.725,"output":6.9},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistralai/Mistral-Medium-3.5-128B","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistralai/Voxtral-Small-24B-2507":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"voxtral","open_weights":true},"family":null,"id":"mistralai/Voxtral-Small-24B-2507","knowledge":null,"last_updated":"2025-03-01","lifecycle":null,"limits":{"context":32000,"output":32000},"modalities":{"input":["audio","text"],"output":["text"]},"model":null,"name":"Voxtral Small 24B","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2025-03-01","retired":false,"tags":null},"moonshotai/Kimi-K2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.4375,"output":5.75},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","llmfit":{"architecture":"kimi_k25","context_length":16777216,"discovered":true,"gguf_sources":[],"hf_downloads":875729,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":591.5,"min_vram_gb":542.2,"recommended_ram_gb":985.9},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":73880719970,"is_moe":true,"num_experts":384},"parameter_count":"1058.6B","parameters_raw":1058589420528,"pipeline_tag":"image-text-to-text","provider":"moonshotai","quantization":"Q4_K_M","source":"llmfit","use_case":"Multimodal, vision and text"},"open_weights":true,"reasoning_options":[{"type":"budget_tokens"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/Kimi-K2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"nvidia/Llama-3.3-70B-Instruct-FP8":{"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":1.15,"output":1.15},"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":"nvidia/Llama-3.3-70B-Instruct-FP8","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.23,"output":0.92},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}]},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/whisper-large-v3":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","open_weights":true},"family":null,"id":"openai/whisper-large-v3","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":{"context":448,"output":4096},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper 3 Large","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"openai/whisper-large-v3-turbo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","open_weights":true},"family":null,"id":"openai/whisper-large-v3-turbo","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":{"context":448,"output":448},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper Large v3 Turbo","pricing":null,"provider":"evroc","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"zai-org/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":{"input":1.4375,"output":5.75},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","llmfit":{"architecture":"glm_moe_dsa","context_length":1048576,"discovered":true,"gguf_sources":[],"hf_downloads":2180509,"hf_likes":4785,"matched_hugging_face_id":"zai-org/GLM-5.2","memory":{"min_ram_gb":421.0,"min_vram_gb":385.9,"recommended_ram_gb":701.6},"model_id":"zai-org/GLM-5.2","moe":{"active_experts":8,"active_parameters":60030979632,"is_moe":true,"num_experts":256},"parameter_count":"753.3B","parameters_raw":753329940480,"pipeline_tag":"text-generation","provider":"zai-org","quantization":"Q4_K_M","release_date":"2026-06-16","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org/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":"evroc","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null}},"name":"evroc","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/fastrouter.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "fastrouter",
+  "anthropic/claude-opus-4.1" | "anthropic/claude-opus-4.8" | "anthropic/claude-sonnet-4" | "anthropic/claude-sonnet-4.6" | "bytedance/seedance-2" | "deepseek-ai/deepseek-r1-distill-llama-70b" | "deepseek/deepseek-v4-pro" | "google/gemini-2.5-flash" | "google/gemini-2.5-pro" | "google/gemini-3-pro-image-preview" | "google/gemini-3.1-flash-image-preview" | "google/gemini-3.1-pro-preview" | "google/gemini-3.5-flash" | "google/gemma-4-31b-it" | "google/imagen-4.0-fast" | "google/imagen-4.0-ultra" | "google/veo3.1" | "google/veo3.1-fast" | "google/veo3.1-lite" | "leonardo-ai/lucid-origin" | "leonardo-ai/lucid-realism" | "minimax/minimax-m2.7" | "minimax/minimax-m2.7-highspeed" | "moonshotai/kimi-k2" | "moonshotai/kimi-k2.6" | "openai/gpt-4.1" | "openai/gpt-5" | "openai/gpt-5-mini" | "openai/gpt-5-nano" | "openai/gpt-5.3-codex" | "openai/gpt-5.4-mini" | "openai/gpt-5.4-nano" | "openai/gpt-5.5" | "openai/gpt-5.5-pro" | "openai/gpt-image-2" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "openai/gpt-realtime-1.5" | "qwen/qwen3-coder" | "sarvam/sarvam-105b" | "sarvam/sarvam-30b" | "wanx/wan-v2-6" | "x-ai/grok-4" | "x-ai/grok-4.3" | "x-ai/grok-build-0.1" | "z-ai/glm-5" | "z-ai/glm-5.1"
+>;
+export default provider;

package/dist/providers/fastrouter.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://go.fastrouter.ai/api/v1","catalog_only":true,"config_schema":null,"doc":"https://fastrouter.ai/models","env":["FASTROUTER_API_KEY"],"exclude_models":null,"extra":null,"id":"fastrouter","models":{"anthropic/claude-opus-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"max":32000,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-opus-4.1","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"anthropic/claude-opus-4.8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":[{"max":32000,"min":1024,"type":"budget_tokens"}],"temperature":false},"family":null,"id":"anthropic/claude-opus-4.8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic/claude-sonnet-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"max":32000,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"anthropic/claude-sonnet-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":[{"max":32000,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4.6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"bytedance/seedance-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","open_weights":false,"temperature":false},"family":null,"id":"bytedance/seedance-2","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Seedance 2","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"deepseek-ai/deepseek-r1-distill-llama-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.03,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-ai/deepseek-r1-distill-llama-70b","knowledge":"2024-10","last_updated":"2025-01-23","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 Distill Llama 70B","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-01-23","retired":false,"tags":null},"deepseek/deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.74,"output":3.48},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"google/gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0375,"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","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"google/gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.31,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"google/gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Pro","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"google/gemini-3-pro-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"google/gemini-3-pro-image-preview","knowledge":"2025-01","last_updated":"2025-11-20","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-11-20","retired":false,"tags":null},"google/gemini-3.1-flash-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image-preview","knowledge":"2025-01","last_updated":"2026-02-26","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["text","image","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"google/gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":"google/gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.38},"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":"google/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":"fastrouter","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google/imagen-4.0-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","open_weights":false,"temperature":false},"family":null,"id":"google/imagen-4.0-fast","knowledge":null,"last_updated":"2025-05-20","lifecycle":null,"limits":{"context":480},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Imagen 4 Fast","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"google/imagen-4.0-ultra":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","open_weights":false,"temperature":false},"family":null,"id":"google/imagen-4.0-ultra","knowledge":null,"last_updated":"2025-05-20","lifecycle":null,"limits":{"context":480},"modalities":{"input":["text"],"output":["image"]},"model":null,"name":"Imagen 4 Ultra","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"google/veo3.1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false,"temperature":false},"family":null,"id":"google/veo3.1","knowledge":null,"last_updated":"2026-05-01","lifecycle":null,"limits":{"context":400000},"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Veo 3.1","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-05-01","retired":false,"tags":null},"google/veo3.1-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false,"temperature":false},"family":null,"id":"google/veo3.1-fast","knowledge":null,"last_updated":"2026-05-01","lifecycle":null,"limits":{"context":400000},"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Veo 3.1 Fast","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-05-01","retired":false,"tags":null},"google/veo3.1-lite":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","open_weights":false,"temperature":false},"family":null,"id":"google/veo3.1-lite","knowledge":null,"last_updated":"2026-05-01","lifecycle":null,"limits":{"context":400000},"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Veo 3.1 Lite","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-05-01","retired":false,"tags":null},"leonardo-ai/lucid-origin":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"lucid","open_weights":false,"temperature":false},"family":null,"id":"leonardo-ai/lucid-origin","knowledge":null,"last_updated":"2025-06-01","lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Lucid Origin","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"leonardo-ai/lucid-realism":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"lucid","open_weights":false,"temperature":false},"family":null,"id":"leonardo-ai/lucid-realism","knowledge":null,"last_updated":"2025-06-01","lifecycle":null,"limits":{"context":4096},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"Lucid Realism","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"minimax/minimax-m2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"minimax/minimax-m2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/minimax-m2.7-highspeed":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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/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":"fastrouter","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"moonshotai/kimi-k2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.55,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2","knowledge":"2024-10","last_updated":"2025-07-11","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-07-11","retired":false,"tags":null},"moonshotai/kimi-k2.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.75,"output":3.5},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"openai/gpt-5","knowledge":"2024-10-01","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":"fastrouter","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-5-mini","knowledge":"2024-10-01","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":"fastrouter","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-5-nano","knowledge":"2024-10-01","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":"fastrouter","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"openai/gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/gpt-5.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.5-pro","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5 Pro","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/gpt-image-2":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-image-2","knowledge":null,"last_updated":"2026-04-21","lifecycle":null,"limits":{"context":128000},"modalities":{"input":["text","image"],"output":["image"]},"model":null,"name":"GPT Image 2","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-realtime-1.5":{"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":4,"output":16},"deprecated":false,"extra":{"attachment":true,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"openai/gpt-realtime-1.5","knowledge":null,"last_updated":"2025-06-01","lifecycle":null,"limits":{"context":32000,"output":4096},"modalities":{"input":["text","audio","image"],"output":["text","audio"]},"model":null,"name":"GPT Realtime 1.5","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"qwen/qwen3-coder":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":66536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"sarvam/sarvam-105b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.16},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"sarvam/sarvam-105b","knowledge":null,"last_updated":"2025-09-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sarvam 105B","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null},"sarvam/sarvam-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":0.02,"output":0.1},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","family":"sarvam","open_weights":true,"reasoning_options":[],"temperature":true},"family":null,"id":"sarvam/sarvam-30b","knowledge":null,"last_updated":"2026-02-18","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sarvam 30B","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-02-18","retired":false,"tags":null},"wanx/wan-v2-6":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":true,"description":"Video model for prompt-guided generation, editing, and motion workflows","open_weights":true,"temperature":false},"family":null,"id":"wanx/wan-v2-6","knowledge":null,"last_updated":"2025-12-01","lifecycle":null,"limits":{"context":400000},"modalities":{"input":["text","image"],"output":["video"]},"model":null,"name":"Wan 2.6","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"x-ai/grok-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":0.75,"cache_write":15,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"x-ai/grok-4","knowledge":"2025-07","last_updated":"2025-07-09","lifecycle":null,"limits":{"context":256000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Grok 4","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2025-07-09","retired":false,"tags":null},"x-ai/grok-4.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":"x-ai/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":"fastrouter","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"x-ai/grok-build-0.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"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":"x-ai/grok-build-0.1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"z-ai/glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.95,"output":3.15},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"z-ai/glm-5","knowledge":null,"last_updated":"2026-02-11","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"z-ai/glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.05,"output":3.5},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[{"type":"toggle"}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai/glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"fastrouter","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null}},"name":"FastRouter","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/fireworks_ai.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "fireworks_ai",
+  "accounts/fireworks/models/deepseek-v4-flash" | "accounts/fireworks/models/deepseek-v4-flash-0731" | "accounts/fireworks/models/deepseek-v4-pro" | "accounts/fireworks/models/glm-5p2" | "accounts/fireworks/models/gpt-oss-120b" | "accounts/fireworks/models/gpt-oss-20b" | "accounts/fireworks/models/kimi-k2p6" | "accounts/fireworks/models/kimi-k2p7-code" | "accounts/fireworks/models/kimi-k3" | "accounts/fireworks/models/minimax-m2p7" | "accounts/fireworks/models/minimax-m3" | "accounts/fireworks/models/qwen3p7-plus" | "accounts/fireworks/routers/glm-5p2-fast" | "accounts/fireworks/routers/kimi-k2p6-fast" | "accounts/fireworks/routers/kimi-k2p6-turbo" | "accounts/fireworks/routers/kimi-k2p7-code-fast" | "accounts/fireworks/routers/kimi-k3-fast"
+>;
+export default provider;

package/dist/providers/fireworks_ai.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.fireworks.ai/inference/v1","config_schema":null,"doc":"https://fireworks.ai/docs/","env":["FIREWORKS_API_KEY"],"exclude_models":null,"extra":null,"id":"fireworks_ai","models":{"accounts/fireworks/models/deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"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":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"accounts/fireworks/models/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-06-16","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"accounts/fireworks/models/deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"accounts/fireworks/models/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"accounts/fireworks/models/deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.145,"input":1.74,"output":3.48},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":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":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"accounts/fireworks/models/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1000000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"accounts/fireworks/models/glm-5p2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.14,"input":1.4,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"temperature":true},"family":null,"id":"accounts/fireworks/models/glm-5p2","knowledge":null,"last_updated":"2026-06-16","lifecycle":null,"limits":{"context":1048575,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null},"accounts/fireworks/models/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"accounts/fireworks/models/gpt-oss-120b","knowledge":null,"last_updated":"2026-06-16","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"accounts/fireworks/models/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.035,"input":0.07,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"accounts/fireworks/models/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"accounts/fireworks/models/kimi-k2p6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.16,"input":0.95,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"accounts/fireworks/models/kimi-k2p6","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"accounts/fireworks/models/kimi-k2p7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi coding model for software agents, refactors, and repository reasoning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"accounts/fireworks/models/kimi-k2p7-code","knowledge":null,"last_updated":"2026-06-16","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"accounts/fireworks/models/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}},"cost":{"cache_read":0.3,"input":3,"output":15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"accounts/fireworks/models/kimi-k3","knowledge":null,"last_updated":"2026-07-27","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null},"accounts/fireworks/models/minimax-m2p7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"accounts/fireworks/models/minimax-m2p7","knowledge":null,"last_updated":"2026-04-12","lifecycle":null,"limits":{"context":196608,"output":196608},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-04-12","retired":false,"tags":null},"accounts/fireworks/models/minimax-m3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"accounts/fireworks/models/minimax-m3","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":512000,"output":512000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"accounts/fireworks/models/qwen3p7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.08,"input":0.4,"output":1.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"min":1,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"accounts/fireworks/models/qwen3p7-plus","knowledge":null,"last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 3.7 Plus","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"accounts/fireworks/routers/glm-5p2-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.21,"input":2.1,"output":6.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"temperature":true},"family":null,"id":"accounts/fireworks/routers/glm-5p2-fast","knowledge":null,"last_updated":"2026-06-26","lifecycle":null,"limits":{"context":1048575,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2 Fast","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-06-26","retired":false,"tags":null},"accounts/fireworks/routers/kimi-k2p6-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"input":2,"output":8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"accounts/fireworks/routers/kimi-k2p6-fast","knowledge":null,"last_updated":"2026-06-05","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6 Fast","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"accounts/fireworks/routers/kimi-k2p6-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3,"input":2,"output":8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"accounts/fireworks/routers/kimi-k2p6-turbo","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6 Turbo","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"accounts/fireworks/routers/kimi-k2p7-code-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.38,"input":1.9,"output":8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi coding model for software agents, refactors, and repository reasoning","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"}],"temperature":true},"family":null,"id":"accounts/fireworks/routers/kimi-k2p7-code-fast","knowledge":null,"last_updated":"2026-06-16","lifecycle":null,"limits":{"context":262000,"output":262000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code Fast","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"accounts/fireworks/routers/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}},"cost":{"cache_read":0.45,"input":4.5,"output":22.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"structured_output":true,"temperature":false},"family":null,"id":"accounts/fireworks/routers/kimi-k3-fast","knowledge":null,"last_updated":"2026-07-27","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3 Fast","pricing":null,"provider":"fireworks_ai","provider_model_id":null,"release_date":"2026-07-27","retired":false,"tags":null}},"name":"Fireworks AI","pricing_defaults":null,"runtime":{"auth":{"env":["FIREWORKS_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.fireworks.ai/inference/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://fireworks.ai/docs/"}};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/freemodel.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "freemodel",
+  "claude-fable-5" | "claude-haiku-4-5-20251001" | "claude-opus-4-6" | "claude-opus-4-7" | "claude-opus-4-8" | "claude-sonnet-4-6" | "gpt-5.3-codex" | "gpt-5.4" | "gpt-5.4-mini" | "gpt-5.5"
+>;
+export default provider;