@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/greenpt.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.greenpt.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.greenpt.ai","env":["GREENPT_API_KEY"],"exclude_models":null,"extra":null,"id":"greenpt","models":{"deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0456,"input":0.1596,"output":0.399},"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":"effort","values":["none","minimal","low","medium","high"]}],"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":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"devstral-2-123b-instruct-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.57,"output":2.736},"deprecated":false,"extra":{"attachment":false,"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","open_weights":true,"temperature":true},"family":null,"id":"devstral-2-123b-instruct-2512","knowledge":"2025-12","last_updated":"2025-12-09","lifecycle":null,"limits":{"context":200000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Devstral 2","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-12-09","retired":false,"tags":null},"gemma-3-27b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.342,"output":0.684},"deprecated":false,"extra":{"attachment":true,"description":"Google Gemma 3 multimodal model for chat, reasoning, and image understanding","family":"gemma","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"gemma-3-27b-it","knowledge":"2024-08","last_updated":"2025-03-12","lifecycle":null,"limits":{"context":40000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 3 27B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"gemma4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.57,"output":1.71},"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":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemma4","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gemma4","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-02","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":{"input":1.756,"output":5.518},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"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":"effort","values":["none","minimal","low","medium","high"]}],"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":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-caveman":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-caveman","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 Caveman","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-caveman-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":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-caveman-lite","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 Caveman Lite","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-caveman-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-caveman-ultra","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 Caveman Ultra","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-honey":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-honey","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 Honey","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-honey-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":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-honey-lite","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 Honey Lite","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-honey-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-honey-ultra","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 Honey Ultra","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-ponytail":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-ponytail","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 Ponytail","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-ponytail-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":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-ponytail-lite","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 Ponytail Lite","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-ponytail-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-ponytail-ultra","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 Ponytail Ultra","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.228,"output":0.798},"deprecated":false,"extra":{"attachment":true,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"green-l":{"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":0.285,"output":0.912},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"green-l","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green L","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"green-l-raw":{"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":0.285,"output":0.912},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"green-l-raw","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green L Raw","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"green-r":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.399,"output":1.083},"deprecated":false,"extra":{"attachment":true,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"green-r","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green R","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"green-r-raw":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.399,"output":1.083},"deprecated":false,"extra":{"attachment":true,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"green-r-raw","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green R Raw","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"green-s":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.00437,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"GreenPT speech-to-text model for pre-recorded and live transcription","open_weights":false,"temperature":false},"family":null,"id":"green-s","knowledge":null,"last_updated":"2025-01","lifecycle":null,"limits":{"output":8192},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Green S","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-01","retired":false,"tags":null},"green-s-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.00437,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"GreenPT advanced speech-to-text model with multilingual transcription support","open_weights":false,"temperature":false},"family":null,"id":"green-s-pro","knowledge":null,"last_updated":"2025-02","lifecycle":null,"limits":{"output":8192},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Green S Pro","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-02","retired":false,"tags":null},"holo2-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.399,"output":0.969},"deprecated":false,"extra":{"attachment":true,"description":"H Company Holo2 vision model for GUI navigation and computer-use agents","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"holo2-30b-a3b","knowledge":null,"last_updated":"2025-11","lifecycle":null,"limits":{"context":22016,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Holo2 30B A3B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-11","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":0.2508,"input":0.7524,"output":4.275},"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":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-k2.6-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.655,"output":8.778},"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":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6-fast","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6 Fast","pricing":null,"provider":"greenpt","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":0.1881,"input":0.9006,"output":4.389},"deprecated":false,"extra":{"attachment":false,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.9405,"input":3.762,"output":18.81},"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":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"llama-3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.254,"output":1.254},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":100000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0627,"input":0.1938,"output":1.129},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"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":2.052,"output":10.26},"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":"mistral-medium-3.5-128b","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistral-small-3.2-24b-instruct-2506":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.228,"output":0.456},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"mistral-small-3.2-24b-instruct-2506","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 3.2","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"pixtral-12b-2409":{"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":0.285,"output":0.285},"deprecated":false,"extra":{"attachment":true,"description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","open_weights":true,"temperature":true},"family":null,"id":"pixtral-12b-2409","knowledge":"2024-09","last_updated":"2024-09-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Pixtral 12B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2024-09-01","retired":false,"tags":null},"qwen3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.026,"output":3.078},"deprecated":false,"extra":{"attachment":false,"description":"Qwen3 235B MoE instruct model for long-context multilingual chat and reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-235b-a22b-instruct-2507","knowledge":"2025-04","last_updated":"2025-07-21","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-07-21","retired":false,"tags":null},"qwen3-coder-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.285,"output":1.083},"deprecated":false,"extra":{"attachment":false,"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen3-coder-30b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 30B-A3B Instruct","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-04","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":{"input":0.798,"output":4.959},"deprecated":false,"extra":{"attachment":false,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"qwen3.6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.342,"output":2.052},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-35b-a3b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"voxtral-small-24b-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.228,"output":0.513},"deprecated":false,"extra":{"attachment":true,"description":"Mistral Voxtral audio-understanding model for speech and transcription tasks","family":"mistral","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"voxtral-small-24b-2507","knowledge":"2025-07","last_updated":"2025-07-15","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text","audio"],"output":["text"]},"model":null,"name":"Voxtral Small 24B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-07-15","retired":false,"tags":null}},"name":"GreenPT","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://api.greenpt.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://docs.greenpt.ai","env":["GREENPT_API_KEY"],"exclude_models":null,"extra":null,"id":"greenpt","models":{"deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0456,"input":0.1596,"output":0.399},"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":"effort","values":["none","minimal","low","medium","high"]}],"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":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"devstral-2-123b-instruct-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.57,"output":2.736},"deprecated":false,"extra":{"attachment":false,"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","open_weights":true,"temperature":true},"family":null,"id":"devstral-2-123b-instruct-2512","knowledge":"2025-12","last_updated":"2025-12-09","lifecycle":null,"limits":{"context":200000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Devstral 2","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-12-09","retired":false,"tags":null},"gemma-3-27b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.342,"output":0.684},"deprecated":false,"extra":{"attachment":true,"description":"Google Gemma 3 multimodal model for chat, reasoning, and image understanding","family":"gemma","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"gemma-3-27b-it","knowledge":"2024-08","last_updated":"2025-03-12","lifecycle":null,"limits":{"context":40000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 3 27B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-03-12","retired":false,"tags":null},"gemma4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.57,"output":1.71},"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":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemma4","knowledge":null,"last_updated":"2026-04-02","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"gemma4","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-02","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":{"input":1.756,"output":5.518},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"glm-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"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":"effort","values":["none","minimal","low","medium","high"]}],"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":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-caveman":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-caveman","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 Caveman","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-caveman-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":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-caveman-lite","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 Caveman Lite","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-caveman-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-caveman-ultra","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 Caveman Ultra","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-honey":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-honey","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 Honey","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-honey-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":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-honey-lite","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 Honey Lite","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-honey-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-honey-ultra","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 Honey Ultra","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-ponytail":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-ponytail","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 Ponytail","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-ponytail-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":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-ponytail-lite","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 Ponytail Lite","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"glm-5.2-ponytail-ultra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3135,"input":1.254,"output":5.016},"deprecated":false,"extra":{"attachment":false,"description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"glm-5.2-ponytail-ultra","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 Ponytail Ultra","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.228,"output":0.798},"deprecated":false,"extra":{"attachment":true,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"green-l":{"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":0.285,"output":0.912},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"green-l","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green L","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"green-l-raw":{"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":0.285,"output":0.912},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"green-l-raw","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green L Raw","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"green-r":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.399,"output":1.083},"deprecated":false,"extra":{"attachment":true,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"green-r","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green R","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"green-r-raw":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.399,"output":1.083},"deprecated":false,"extra":{"attachment":true,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"green-r-raw","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Green R Raw","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"green-s":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.00437,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"GreenPT speech-to-text model for pre-recorded and live transcription","open_weights":false,"temperature":false},"family":null,"id":"green-s","knowledge":null,"last_updated":"2025-01","lifecycle":null,"limits":{"output":8192},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Green S","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-01","retired":false,"tags":null},"green-s-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.00437,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"GreenPT advanced speech-to-text model with multilingual transcription support","open_weights":false,"temperature":false},"family":null,"id":"green-s-pro","knowledge":null,"last_updated":"2025-02","lifecycle":null,"limits":{"output":8192},"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Green S Pro","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-02","retired":false,"tags":null},"holo2-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.399,"output":0.969},"deprecated":false,"extra":{"attachment":true,"description":"H Company Holo2 vision model for GUI navigation and computer-use agents","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"holo2-30b-a3b","knowledge":null,"last_updated":"2025-11","lifecycle":null,"limits":{"context":22016,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Holo2 30B A3B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-11","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":0.2508,"input":0.7524,"output":4.275},"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":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"kimi-k2.6-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.655,"output":8.778},"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":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"kimi-k2.6-fast","knowledge":"2025-01","last_updated":"2026-04-21","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6 Fast","pricing":null,"provider":"greenpt","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":0.1881,"input":0.9006,"output":4.389},"deprecated":false,"extra":{"attachment":false,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.9405,"input":3.762,"output":18.81},"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":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"llama-3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.254,"output":1.254},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":100000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"minimax-m2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0627,"input":0.1938,"output":1.129},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m2.5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.5","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"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":2.052,"output":10.26},"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":"mistral-medium-3.5-128b","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistral-small-3.2-24b-instruct-2506":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.228,"output":0.456},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"mistral-small-3.2-24b-instruct-2506","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 3.2","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"pixtral-12b-2409":{"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":0.285,"output":0.285},"deprecated":false,"extra":{"attachment":true,"description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","open_weights":true,"temperature":true},"family":null,"id":"pixtral-12b-2409","knowledge":"2024-09","last_updated":"2024-09-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Pixtral 12B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2024-09-01","retired":false,"tags":null},"qwen3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.026,"output":3.078},"deprecated":false,"extra":{"attachment":false,"description":"Qwen3 235B MoE instruct model for long-context multilingual chat and reasoning","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-235b-a22b-instruct-2507","knowledge":"2025-04","last_updated":"2025-07-21","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct 2507","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-07-21","retired":false,"tags":null},"qwen3-coder-30b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.285,"output":1.083},"deprecated":false,"extra":{"attachment":false,"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","open_weights":true,"temperature":true},"family":null,"id":"qwen3-coder-30b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 30B-A3B Instruct","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-04","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":{"input":0.798,"output":4.959},"deprecated":false,"extra":{"attachment":false,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.5-397b-a17b","knowledge":null,"last_updated":"2026-02-15","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.5 397B-A17B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-02-15","retired":false,"tags":null},"qwen3.6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.342,"output":2.052},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3.6-35b-a3b","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":262144,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B-A3B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"voxtral-small-24b-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.228,"output":0.513},"deprecated":false,"extra":{"attachment":true,"description":"Mistral Voxtral audio-understanding model for speech and transcription tasks","family":"mistral","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"voxtral-small-24b-2507","knowledge":"2025-07","last_updated":"2025-07-15","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text","audio"],"output":["text"]},"model":null,"name":"Voxtral Small 24B","pricing":null,"provider":"greenpt","provider_model_id":null,"release_date":"2025-07-15","retired":false,"tags":null}},"name":"GreenPT","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/groq.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://api.groq.com/openai/v1","config_schema":null,"doc":"https://groq.com/docs","env":["GROQ_API_KEY"],"exclude_models":["deepseek-r1-distill-llama-70b","deepseek-r1-distill-llama-70b-specdec","deepseek-r1-distill-qwen-32b","distil-whisper-large-v3-en","gemma-7b-it","gemma2-9b-it","llama-3.1-70b-specdec","llama-3.1-70b-versatile","llama-3.2-11b-text-preview","llama-3.2-11b-vision-preview","llama-3.2-1b-preview","llama-3.2-3b-preview","llama-3.2-90b-text-preview","llama-3.2-90b-vision-preview","llama-3.3-70b-specdec","llama-guard-3-8b","llama3-70b-8192","llama3-8b-8192","llama3-groq-70b-8192-tool-use-preview","llama3-groq-8b-8192-tool-use-preview","llava-v1.5-7b-4096-preview","mistral-saba-24b","mixtral-8x7b-32768","moonshotai/kimi-k2-instruct","qwen-2.5-32b","qwen-2.5-coder-32b","qwen-qwq-32b"],"extra":null,"id":"groq","models":{"allam-2-7b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0,"output":0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"ALLaM-2-7b instruction tuned model by SDAIA","open_weights":true,"temperature":true},"family":null,"id":"allam-2-7b","knowledge":null,"last_updated":"2025-01-23","lifecycle":null,"limits":{"context":4096,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ALLaM-2-7b","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-01-23","retired":false,"tags":null},"canopylabs/orpheus-arabic-saudi":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","open_weights":false,"status":"beta","temperature":false},"family":null,"id":"canopylabs/orpheus-arabic-saudi","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":{"context":4000,"output":50000},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Canopy Labs Orpheus Arabic Saudi","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"canopylabs/orpheus-v1-english":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","open_weights":false,"status":"beta","temperature":false},"family":null,"id":"canopylabs/orpheus-v1-english","knowledge":null,"last_updated":"2025-12-19","lifecycle":null,"limits":{"context":4000,"output":50000},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Canopy Labs Orpheus V1 English","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-12-19","retired":false,"tags":null},"groq/compound":{"aliases":[],"base_url":null,"capabilities":null,"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"groq","open_weights":false,"temperature":true},"family":null,"id":"groq/compound","knowledge":null,"last_updated":"2025-09-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Compound","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"groq/compound-mini":{"aliases":[],"base_url":null,"capabilities":null,"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"groq","open_weights":false,"temperature":true},"family":null,"id":"groq/compound-mini","knowledge":null,"last_updated":"2025-09-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Compound Mini","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"llama-3.1-8b-instant":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.05,"output":0.08},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.1-8b-instant","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"llama-3.3-70b-versatile":{"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}},"cost":{"input":0.59,"output":0.79},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-versatile","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/llama-prompt-guard-2-22m":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.03,"output":0.03},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":true,"status":"beta","temperature":false},"family":null,"id":"meta-llama/llama-prompt-guard-2-22m","knowledge":null,"last_updated":"2025-05-29","lifecycle":null,"limits":{"context":512,"output":512},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama Prompt Guard 2 22M","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-05-29","retired":false,"tags":null},"meta-llama/llama-prompt-guard-2-86m":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.04,"output":0.04},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":true,"status":"beta","temperature":false},"family":null,"id":"meta-llama/llama-prompt-guard-2-86m","knowledge":null,"last_updated":"2025-05-29","lifecycle":null,"limits":{"context":512,"output":512},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Prompt Guard 2 86M","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-05-29","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}},"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":4197649,"hf_likes":5069,"matched_hugging_face_id":"openai/gpt-oss-120b","memory":{"min_ram_gb":67.3,"min_vram_gb":61.7,"recommended_ram_gb":112.1},"model_id":"openai/gpt-oss-120b","moe":{"active_experts":4,"active_parameters":9595358141,"is_moe":true,"num_experts":128},"parameter_count":"120.4B","parameters_raw":120412337472,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-10-21","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0375,"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":8501701,"hf_likes":4869,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-09-25","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-safeguard-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-safeguard-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-safeguard-20b-GGUF"}],"hf_downloads":101805,"hf_likes":243,"matched_hugging_face_id":"openai/gpt-oss-safeguard-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-safeguard-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-09-18","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-safeguard-20b","knowledge":null,"last_updated":"2026-06-29","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Safety GPT OSS 20B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-10-29","retired":false,"tags":null},"qwen/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}},"cost":{"cache_read":0.3,"input":0.6,"output":3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","default"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-27b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"whisper-large-v3":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false}},"cost":{"audio":0.111},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"api":"audio","attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","max_file_size_mb":100,"open_weights":true,"supported_formats":["flac","mp3","mp4","mpeg","mpga","m4a","ogg","wav","webm"],"temperature":true,"translation":true},"family":"whisper","id":"whisper-large-v3","knowledge":null,"last_updated":"2025-09-05","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper Large V3","pricing":{"components":[{"id":"audio.transcription","kind":"other","notes":"per hour of audio","per":1,"rate":0.111,"unit":"other"},{"id":"audio.translation","kind":"other","notes":"per hour of audio","per":1,"rate":0.111,"unit":"other"}],"currency":"USD","merge":"replace"},"provider":"groq","provider_model_id":null,"release_date":"2023-09-01","retired":false,"tags":["stt","transcription","translation"]},"whisper-large-v3-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false}},"cost":{"audio":0.04},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"api":"audio","attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","max_file_size_mb":100,"open_weights":true,"supported_formats":["flac","mp3","mp4","mpeg","mpga","m4a","ogg","wav","webm"],"temperature":true},"family":"whisper","id":"whisper-large-v3-turbo","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper Large V3 Turbo","pricing":{"components":[{"id":"audio.transcription","kind":"other","notes":"per hour of audio","per":1,"rate":0.04,"unit":"other"}],"currency":"USD","merge":"replace"},"provider":"groq","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":["stt","transcription"]}},"name":"Groq","pricing_defaults":null,"runtime":{"auth":{"env":["GROQ_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.groq.com/openai/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://groq.com/docs"}};
+export const data = {"alias_of":null,"base_url":"https://api.groq.com/openai/v1","config_schema":null,"doc":"https://groq.com/docs","env":["GROQ_API_KEY"],"exclude_models":["deepseek-r1-distill-llama-70b","deepseek-r1-distill-llama-70b-specdec","deepseek-r1-distill-qwen-32b","distil-whisper-large-v3-en","gemma-7b-it","gemma2-9b-it","llama-3.1-70b-specdec","llama-3.1-70b-versatile","llama-3.2-11b-text-preview","llama-3.2-11b-vision-preview","llama-3.2-1b-preview","llama-3.2-3b-preview","llama-3.2-90b-text-preview","llama-3.2-90b-vision-preview","llama-3.3-70b-specdec","llama-guard-3-8b","llama3-70b-8192","llama3-8b-8192","llama3-groq-70b-8192-tool-use-preview","llama3-groq-8b-8192-tool-use-preview","llava-v1.5-7b-4096-preview","mistral-saba-24b","mixtral-8x7b-32768","moonshotai/kimi-k2-instruct","qwen-2.5-32b","qwen-2.5-coder-32b","qwen-qwq-32b"],"extra":null,"id":"groq","models":{"allam-2-7b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0,"output":0},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"ALLaM-2-7b instruction tuned model by SDAIA","open_weights":true,"temperature":true},"family":null,"id":"allam-2-7b","knowledge":null,"last_updated":"2025-01-23","lifecycle":null,"limits":{"context":4096,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"ALLaM-2-7b","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-01-23","retired":false,"tags":null},"canopylabs/orpheus-arabic-saudi":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","open_weights":false,"status":"beta","temperature":false},"family":null,"id":"canopylabs/orpheus-arabic-saudi","knowledge":null,"last_updated":"2025-12-16","lifecycle":null,"limits":{"context":4000,"output":50000},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Canopy Labs Orpheus Arabic Saudi","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-12-16","retired":false,"tags":null},"canopylabs/orpheus-v1-english":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","open_weights":false,"status":"beta","temperature":false},"family":null,"id":"canopylabs/orpheus-v1-english","knowledge":null,"last_updated":"2025-12-19","lifecycle":null,"limits":{"context":4000,"output":50000},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Canopy Labs Orpheus V1 English","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-12-19","retired":false,"tags":null},"groq/compound":{"aliases":[],"base_url":null,"capabilities":null,"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General-purpose chat model for instruction following, writing, and analysis","family":"groq","open_weights":false,"temperature":true},"family":null,"id":"groq/compound","knowledge":null,"last_updated":"2025-09-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Compound","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"groq/compound-mini":{"aliases":[],"base_url":null,"capabilities":null,"cost":null,"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"groq","open_weights":false,"temperature":true},"family":null,"id":"groq/compound-mini","knowledge":null,"last_updated":"2025-09-04","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Compound Mini","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-09-04","retired":false,"tags":null},"llama-3.1-8b-instant":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.05,"output":0.08},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.1-8b-instant","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 8B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"llama-3.3-70b-versatile":{"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}},"cost":{"input":0.59,"output":0.79},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.3-70b-versatile","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"meta-llama/llama-prompt-guard-2-22m":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.03,"output":0.03},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":true,"status":"beta","temperature":false},"family":null,"id":"meta-llama/llama-prompt-guard-2-22m","knowledge":null,"last_updated":"2025-05-29","lifecycle":null,"limits":{"context":512,"output":512},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama Prompt Guard 2 22M","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-05-29","retired":false,"tags":null},"meta-llama/llama-prompt-guard-2-86m":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":0.04,"output":0.04},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":true,"status":"beta","temperature":false},"family":null,"id":"meta-llama/llama-prompt-guard-2-86m","knowledge":null,"last_updated":"2025-05-29","lifecycle":null,"limits":{"context":512,"output":512},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Prompt Guard 2 86M","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-05-29","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}},"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-120b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-120b-GGUF"}],"hf_downloads":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"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-10-21","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0375,"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-20b-GGUF"},{"provider":"ggml-org","repo":"ggml-org/gpt-oss-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-20b-GGUF"}],"hf_downloads":7966494,"hf_likes":4923,"matched_hugging_face_id":"openai/gpt-oss-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-08-04","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-09-25","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-safeguard-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","llmfit":{"architecture":"gpt_oss","context_length":4194304,"discovered":true,"gguf_sources":[{"provider":"unsloth","repo":"unsloth/gpt-oss-safeguard-20b-GGUF"},{"provider":"mradermacher","repo":"mradermacher/gpt-oss-safeguard-20b-GGUF"}],"hf_downloads":111793,"hf_likes":250,"matched_hugging_face_id":"openai/gpt-oss-safeguard-20b","memory":{"min_ram_gb":12.0,"min_vram_gb":11.0,"recommended_ram_gb":20.0},"model_id":"openai/gpt-oss-safeguard-20b","moe":{"active_experts":4,"active_parameters":3630142231,"is_moe":true,"num_experts":32},"parameter_count":"21.5B","parameters_raw":21511953984,"pipeline_tag":"text-generation","provider":"openai","quantization":"Q4_K_M","release_date":"2025-09-18","source":"llmfit","use_case":"General purpose text generation"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-oss-safeguard-20b","knowledge":null,"last_updated":"2026-06-29","lifecycle":null,"limits":{"context":131072,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Safety GPT OSS 20B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2025-10-29","retired":false,"tags":null},"qwen/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}},"cost":{"cache_read":0.3,"input":0.6,"output":3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","default"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.6-27b","knowledge":null,"last_updated":"2026-04-22","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 27B","pricing":null,"provider":"groq","provider_model_id":null,"release_date":"2026-04-22","retired":false,"tags":null},"whisper-large-v3":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false}},"cost":{"audio":0.111},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"api":"audio","attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","max_file_size_mb":100,"open_weights":true,"supported_formats":["flac","mp3","mp4","mpeg","mpga","m4a","ogg","wav","webm"],"temperature":true,"translation":true},"family":"whisper","id":"whisper-large-v3","knowledge":null,"last_updated":"2025-09-05","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper Large V3","pricing":{"components":[{"id":"audio.transcription","kind":"other","notes":"per hour of audio","per":1,"rate":0.111,"unit":"other"},{"id":"audio.translation","kind":"other","notes":"per hour of audio","per":1,"rate":0.111,"unit":"other"}],"currency":"USD","merge":"replace"},"provider":"groq","provider_model_id":null,"release_date":"2023-09-01","retired":false,"tags":["stt","transcription","translation"]},"whisper-large-v3-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":false,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false}},"cost":{"audio":0.04},"deprecated":false,"execution":{"transcription":{"family":"openai_transcription","path":"/audio/transcriptions","supported":true,"wire_protocol":"openai_transcription"}},"extra":{"api":"audio","attachment":false,"description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","max_file_size_mb":100,"open_weights":true,"supported_formats":["flac","mp3","mp4","mpeg","mpga","m4a","ogg","wav","webm"],"temperature":true},"family":"whisper","id":"whisper-large-v3-turbo","knowledge":null,"last_updated":"2024-10-01","lifecycle":null,"limits":null,"modalities":{"input":["audio"],"output":["text"]},"model":null,"name":"Whisper Large V3 Turbo","pricing":{"components":[{"id":"audio.transcription","kind":"other","notes":"per hour of audio","per":1,"rate":0.04,"unit":"other"}],"currency":"USD","merge":"replace"},"provider":"groq","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":["stt","transcription"]}},"name":"Groq","pricing_defaults":null,"runtime":{"auth":{"env":["GROQ_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.groq.com/openai/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://groq.com/docs"}};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/hetzner.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "hetzner",
-  "Qwen/Qwen3.6-35B-A3B-FP8"
+  "DeepSeek-V4-Flash-0731" | "GLM-5.2-NVFP4" | "Kimi-K2.7-Code" | "Qwen/Qwen3.6-35B-A3B-FP8"
 >;
 export default provider;

package/dist/providers/hetzner.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://inference.hetzner.com/api/v1","catalog_only":true,"config_schema":null,"doc":"https://experiments.hetzner.com/docs/inference","env":["HETZNER_API_KEY"],"exclude_models":null,"extra":null,"id":"hetzner","models":{"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":{"cache_read":0,"input":0,"output":0},"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":[],"status":"beta","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":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"hetzner","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null}},"name":"Hetzner","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://inference.hetzner.com/api/v1","catalog_only":true,"config_schema":null,"doc":"https://experiments.hetzner.com/docs/inference","env":["HETZNER_API_KEY"],"exclude_models":null,"extra":null,"id":"hetzner","models":{"DeepSeek-V4-Flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0,"input":0,"output":0},"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":"effort","values":["none","low","high","max"]}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":512000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"hetzner","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"GLM-5.2-NVFP4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0,"input":0,"output":0},"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":"effort","values":["none","high","max"]}],"status":"beta","structured_output":true,"temperature":true},"family":null,"id":"GLM-5.2-NVFP4","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":512000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2 NVFP4","pricing":null,"provider":"hetzner","provider_model_id":null,"release_date":"2026-06-13","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,"input":0,"output":0},"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":[],"status":"beta","structured_output":true,"temperature":false},"family":null,"id":"Kimi-K2.7-Code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"hetzner","provider_model_id":null,"release_date":"2026-06-12","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":{"cache_read":0,"input":0,"output":0},"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":[],"status":"beta","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":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3.6 35B A3B FP8","pricing":null,"provider":"hetzner","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null}},"name":"Hetzner","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;

package/dist/providers/huggingface.d.ts

@@ -6,6 +6,6 @@ import type {
 export declare const data: Provider;
 declare const provider: ProviderCatalog<
   "huggingface",
-  "MiniMaxAI/MiniMax-M2" | "MiniMaxAI/MiniMax-M2.1" | "MiniMaxAI/MiniMax-M2.5" | "MiniMaxAI/MiniMax-M2.7" | "MiniMaxAI/MiniMax-M3" | "Qwen/Qwen3-235B-A22B" | "Qwen/Qwen3-235B-A22B-Thinking-2507" | "Qwen/Qwen3-32B" | "Qwen/Qwen3-Coder-30B-A3B-Instruct" | "Qwen/Qwen3-Coder-480B-A35B-Instruct" | "Qwen/Qwen3-Coder-Next" | "Qwen/Qwen3-Embedding-4B" | "Qwen/Qwen3-Embedding-8B" | "Qwen/Qwen3-Next-80B-A3B-Instruct" | "Qwen/Qwen3-Next-80B-A3B-Thinking" | "Qwen/Qwen3.5-122B-A10B" | "Qwen/Qwen3.5-27B" | "Qwen/Qwen3.5-35B-A3B" | "Qwen/Qwen3.5-397B-A17B" | "Qwen/Qwen3.5-9B" | "Qwen/Qwen3.6-27B" | "Qwen/Qwen3.6-35B-A3B" | "XiaomiMiMo/MiMo-V2-Flash" | "XiaomiMiMo/MiMo-V2.5" | "XiaomiMiMo/MiMo-V2.5-Pro" | "deepseek-ai/DeepSeek-R1" | "deepseek-ai/DeepSeek-R1-0528" | "deepseek-ai/DeepSeek-V3.2" | "deepseek-ai/DeepSeek-V4-Flash" | "deepseek-ai/DeepSeek-V4-Flash-0731" | "deepseek-ai/DeepSeek-V4-Pro" | "google/gemma-4-26B-A4B-it" | "google/gemma-4-31B-it" | "meta-llama/Llama-3.3-70B-Instruct" | "moonshotai/Kimi-K2-Instruct" | "moonshotai/Kimi-K2-Instruct-0905" | "moonshotai/Kimi-K2-Thinking" | "moonshotai/Kimi-K2.5" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K2.7-Code" | "moonshotai/Kimi-K3" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "stepfun-ai/Step-3.5-Flash" | "stepfun-ai/Step-3.7-Flash" | "tencent/Hy3" | "thinkingmachines/Inkling" | "thinkingmachines/Inkling-Small" | "zai-org/GLM-4.5" | "zai-org/GLM-4.5-Air" | "zai-org/GLM-4.5V" | "zai-org/GLM-4.6" | "zai-org/GLM-4.7" | "zai-org/GLM-4.7-Flash" | "zai-org/GLM-5" | "zai-org/GLM-5.1" | "zai-org/GLM-5.2"
+  "MiniMaxAI/MiniMax-M2" | "MiniMaxAI/MiniMax-M2.1" | "MiniMaxAI/MiniMax-M2.5" | "MiniMaxAI/MiniMax-M2.7" | "MiniMaxAI/MiniMax-M3" | "Qwen/Qwen2.5-Coder-32B-Instruct" | "Qwen/Qwen3-235B-A22B" | "Qwen/Qwen3-235B-A22B-Instruct-2507" | "Qwen/Qwen3-235B-A22B-Thinking-2507" | "Qwen/Qwen3-30B-A3B" | "Qwen/Qwen3-32B" | "Qwen/Qwen3-Coder-30B-A3B-Instruct" | "Qwen/Qwen3-Coder-480B-A35B-Instruct" | "Qwen/Qwen3-Coder-Next" | "Qwen/Qwen3-Embedding-4B" | "Qwen/Qwen3-Embedding-8B" | "Qwen/Qwen3-Next-80B-A3B-Instruct" | "Qwen/Qwen3-Next-80B-A3B-Thinking" | "Qwen/Qwen3.5-122B-A10B" | "Qwen/Qwen3.5-27B" | "Qwen/Qwen3.5-35B-A3B" | "Qwen/Qwen3.5-397B-A17B" | "Qwen/Qwen3.5-9B" | "Qwen/Qwen3.6-27B" | "Qwen/Qwen3.6-35B-A3B" | "Qwen/Qwen3.8-2.4T-A95B" | "XiaomiMiMo/MiMo-V2-Flash" | "XiaomiMiMo/MiMo-V2.5" | "XiaomiMiMo/MiMo-V2.5-Pro" | "deepseek-ai/DeepSeek-R1" | "deepseek-ai/DeepSeek-R1-0528" | "deepseek-ai/DeepSeek-V3" | "deepseek-ai/DeepSeek-V3-0324" | "deepseek-ai/DeepSeek-V3.1" | "deepseek-ai/DeepSeek-V3.2" | "deepseek-ai/DeepSeek-V4-Flash" | "deepseek-ai/DeepSeek-V4-Flash-0731" | "deepseek-ai/DeepSeek-V4-Pro" | "deepseek-ai/DeepSeek-V4-Pro-0813" | "google/gemma-4-26B-A4B-it" | "google/gemma-4-31B-it" | "meta-llama/Llama-3.1-8B-Instruct" | "meta-llama/Llama-3.3-70B-Instruct" | "moonshotai/Kimi-K2-Instruct" | "moonshotai/Kimi-K2-Instruct-0905" | "moonshotai/Kimi-K2-Thinking" | "moonshotai/Kimi-K2.5" | "moonshotai/Kimi-K2.6" | "moonshotai/Kimi-K2.7-Code" | "moonshotai/Kimi-K3" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "stepfun-ai/Step-3.5-Flash" | "stepfun-ai/Step-3.7-Flash" | "tencent/Hy3" | "thinkingmachines/Inkling" | "thinkingmachines/Inkling-Small" | "zai-org/GLM-4.5" | "zai-org/GLM-4.5-Air" | "zai-org/GLM-4.5V" | "zai-org/GLM-4.6" | "zai-org/GLM-4.7" | "zai-org/GLM-4.7-Flash" | "zai-org/GLM-5" | "zai-org/GLM-5.1" | "zai-org/GLM-5.2"
 >;
 export default provider;