@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/empiriolabs.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "empiriolabs",
-  "deepseek-v4-flash" | "deepseek-v4-flash-0731" | "deepseek-v4-pro" | "gemma-4-26b-a4b" | "glm-4-5-flash" | "glm-4-7-flash" | "glm-5-1" | "glm-5-2" | "kimi-k2-6" | "kimi-k2-7-code" | "kimi-k2-7-code-highspeed" | "kimi-k3" | "mimo-v2-5" | "mimo-v2-5-pro" | "minimax-m2-7" | "minimax-m2-7-highspeed" | "minimax-m3" | "mistral-medium-3" | "mistral-small-4" | "muse-spark-1-1" | "qwen3-5-122b-a10b" | "qwen3-5-27b" | "qwen3-5-35b-a3b" | "qwen3-5-397b-a17b" | "qwen3-5-4b" | "qwen3-5-9b" | "qwen3-5-plus" | "qwen3-6-27b" | "qwen3-6-35b-a3b" | "qwen3-6-flash" | "qwen3-6-max-preview" | "qwen3-6-plus" | "qwen3-7-flash" | "qwen3-7-max" | "qwen3-7-plus" | "qwen3-8-max" | "qwen3-max" | "step-3-5-flash" | "step-3-5-flash-2603" | "step-3-7-flash"
+  "deepseek-v3-2" | "deepseek-v4-flash" | "deepseek-v4-flash-0731" | "deepseek-v4-pro" | "deepseek-v4-pro-0813" | "fugu-ultra-v1-0" | "fugu-ultra-v1-1" | "gemma-4-26b-a4b" | "glm-4-5-flash" | "glm-4-7-flash" | "glm-5-1" | "glm-5-2" | "kimi-k2-6" | "kimi-k2-7-code" | "kimi-k2-7-code-highspeed" | "kimi-k3" | "mimo-v2-5" | "mimo-v2-5-pro" | "minimax-m2-7" | "minimax-m2-7-highspeed" | "minimax-m3" | "mistral-medium-3" | "mistral-small-4" | "muse-glimmer-30b" | "muse-spark-1-1" | "muse-spark-1-2" | "qwen3-5-122b-a10b" | "qwen3-5-27b" | "qwen3-5-35b-a3b" | "qwen3-5-397b-a17b" | "qwen3-5-4b" | "qwen3-5-9b" | "qwen3-5-flash" | "qwen3-5-plus" | "qwen3-6-27b" | "qwen3-6-35b-a3b" | "qwen3-6-flash" | "qwen3-6-max-preview" | "qwen3-6-plus" | "qwen3-7-flash" | "qwen3-7-max" | "qwen3-7-plus" | "qwen3-8-27b" | "qwen3-8-max" | "qwen3-max" | "seed-2-0-code" | "seed-2-0-lite" | "seed-2-0-mini" | "seed-2-0-pro" | "seed-2-1-turbo" | "step-3-5-flash" | "step-3-5-flash-2603" | "step-3-7-flash"
 >;
 export default provider;

package/dist/providers/empiriolabs.js

@@ -1,5 +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};
+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-v3-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.57,"input":0.57,"output":1.71},"deprecated":false,"extra":{"attachment":false,"description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","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-v3-2","knowledge":"2024-07","last_updated":"2025-12-01","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.14,"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},"deepseek-v4-pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.32,"input":1.32,"output":3.96},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","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":"deepseek-v4-pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1000000,"output":393216},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"fugu-ultra-v1-0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"input":7.5,"output":45},"deprecated":false,"extra":{"attachment":true,"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","open_weights":false,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"fugu-ultra-v1-0","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Fugu Ultra v1.0","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-06-15","retired":false,"tags":null},"fugu-ultra-v1-1":{"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":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","open_weights":false,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"fugu-ultra-v1-1","knowledge":null,"last_updated":"2026-06-15","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Fugu Ultra v1.1","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-06-15","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-glimmer-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":{"cache_read":0.05,"input":0.2,"output":0.8},"deprecated":false,"extra":{"attachment":true,"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"muse-glimmer-30b","knowledge":"2026-01-04","last_updated":"2026-08-10","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Muse Glimmer 30B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-08-10","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":1048576,"output":131072},"modalities":{"input":["text","image","video","audio"],"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},"muse-spark-1-2":{"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,"input":1.25,"output":4.25},"deprecated":false,"extra":{"attachment":true,"description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","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-1-2","knowledge":null,"last_updated":"2026-08-05","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"model":null,"name":"Muse Spark 1.2","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-08-05","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-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":0.09,"input":0.09,"output":0.368},"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-flash","knowledge":null,"last_updated":"2026-02-23","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.5 Flash","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},"qwen3-8-27b":{"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":0.08,"input":0.17,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","open_weights":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-8-27b","knowledge":null,"last_updated":"2026-08-14","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.8 27B","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-08-14","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},"seed-2-0-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":0.4,"input":0.4,"output":2.4},"deprecated":false,"extra":{"attachment":true,"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-2-0-code","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Seed 2.0 Code","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"seed-2-0-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.31,"input":0.31,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-2-0-lite","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Seed 2.0 Lite","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"seed-2-0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12,"input":0.12,"output":0.5},"deprecated":false,"extra":{"attachment":true,"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-2-0-mini","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Seed 2.0 Mini","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"seed-2-0-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":0.63,"input":0.63,"output":3.79},"deprecated":false,"extra":{"attachment":true,"description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-2-0-pro","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Seed 2.0 Pro","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"seed-2-1-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.63,"input":0.63,"output":3.13},"deprecated":false,"extra":{"attachment":true,"description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","open_weights":false,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"seed-2-1-turbo","knowledge":null,"last_updated":"2026-06-23","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Seed 2.1 Turbo","pricing":null,"provider":"empiriolabs","provider_model_id":null,"release_date":"2026-06-23","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

@@ -6,6 +6,6 @@ import type {
 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"
+  "KBLab/kb-whisper-large" | "Qwen/Qwen3-Embedding-8B" | "Qwen/Qwen3-Reranker-4B" | "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

@@ -1,5 +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};
+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":2869862,"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/Qwen3.6-35B-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":11633364,"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":9990701,"hf_likes":1396,"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":2084823,"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":805859,"hf_likes":0,"matched_hugging_face_id":"moonshotai/Kimi-K2.6","memory":{"min_ram_gb":573.8,"min_vram_gb":526.0,"recommended_ram_gb":956.4},"model_id":"moonshotai/Kimi-K2.6","moe":{"active_experts":8,"active_parameters":71667623138,"is_moe":true,"num_experts":384},"parameter_count":"1026.9B","parameters_raw":1026879376368,"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":4479205,"hf_likes":5106,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":65.3,"min_vram_gb":59.8,"recommended_ram_gb":108.8},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9309823421,"is_moe":true,"num_experts":128},"parameter_count":"116.8B","parameters_raw":116829156672,"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":2705686,"hf_likes":4983,"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":524288,"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;