@agentjido/llmdb 2026.8.2

package/dist/providers/greenpt.js

@@ -0,0 +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};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/groq.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "groq",
+  "allam-2-7b" | "canopylabs/orpheus-arabic-saudi" | "canopylabs/orpheus-v1-english" | "groq/compound" | "groq/compound-mini" | "llama-3.1-8b-instant" | "llama-3.3-70b-versatile" | "meta-llama/llama-prompt-guard-2-22m" | "meta-llama/llama-prompt-guard-2-86m" | "openai/gpt-oss-120b" | "openai/gpt-oss-20b" | "openai/gpt-oss-safeguard-20b" | "qwen/qwen3.6-27b" | "whisper-large-v3" | "whisper-large-v3-turbo"
+>;
+export default provider;

package/dist/providers/groq.js

@@ -0,0 +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"}};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/helicone.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "helicone",
+  "chatgpt-4o-latest" | "claude-3-haiku-20240307" | "claude-3.5-haiku" | "claude-3.5-sonnet-v2" | "claude-3.7-sonnet" | "claude-4.5-haiku" | "claude-4.5-opus" | "claude-4.5-sonnet" | "claude-haiku-4-5-20251001" | "claude-opus-4" | "claude-opus-4-1" | "claude-opus-4-1-20250805" | "claude-sonnet-4" | "claude-sonnet-4-5-20250929" | "deepseek-r1-distill-llama-70b" | "deepseek-reasoner" | "deepseek-tng-r1t2-chimera" | "deepseek-v3" | "deepseek-v3.1-terminus" | "deepseek-v3.2" | "ernie-4.5-21b-a3b-thinking" | "gemini-2.5-flash" | "gemini-2.5-flash-lite" | "gemini-2.5-pro" | "gemini-3-pro-preview" | "gemma-3-12b-it" | "gemma2-9b-it" | "glm-4.6" | "gpt-4.1" | "gpt-4.1-mini" | "gpt-4.1-mini-2025-04-14" | "gpt-4.1-nano" | "gpt-4o" | "gpt-4o-mini" | "gpt-5" | "gpt-5-chat-latest" | "gpt-5-codex" | "gpt-5-mini" | "gpt-5-nano" | "gpt-5-pro" | "gpt-5.1" | "gpt-5.1-chat-latest" | "gpt-5.1-codex" | "gpt-5.1-codex-mini" | "gpt-oss-120b" | "gpt-oss-20b" | "grok-3" | "grok-3-mini" | "grok-4" | "grok-4-1-fast-non-reasoning" | "grok-4-1-fast-reasoning" | "grok-4-fast-non-reasoning" | "grok-4-fast-reasoning" | "grok-code-fast-1" | "hermes-2-pro-llama-3-8b" | "kimi-k2-0711" | "kimi-k2-0905" | "kimi-k2-thinking" | "llama-3.1-8b-instant" | "llama-3.1-8b-instruct" | "llama-3.1-8b-instruct-turbo" | "llama-3.3-70b-instruct" | "llama-3.3-70b-versatile" | "llama-4-maverick" | "llama-4-scout" | "llama-guard-4" | "llama-prompt-guard-2-22m" | "llama-prompt-guard-2-86m" | "mistral-large-2411" | "mistral-nemo" | "mistral-small" | "o1" | "o1-mini" | "o3" | "o3-mini" | "o3-pro" | "o4-mini" | "qwen2.5-coder-7b-fast" | "qwen3-235b-a22b-thinking" | "qwen3-30b-a3b" | "qwen3-32b" | "qwen3-coder" | "qwen3-coder-30b-a3b-instruct" | "qwen3-next-80b-a3b-instruct" | "qwen3-vl-235b-a22b-instruct" | "sonar" | "sonar-deep-research" | "sonar-pro" | "sonar-reasoning" | "sonar-reasoning-pro"
+>;
+export default provider;

package/dist/providers/helicone.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://ai-gateway.helicone.ai/v1","catalog_only":true,"config_schema":null,"doc":"https://helicone.ai/models","env":["HELICONE_API_KEY"],"exclude_models":null,"extra":null,"id":"helicone","models":{"chatgpt-4o-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":2.5,"input":5,"output":20},"deprecated":false,"extra":{"attachment":false,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"chatgpt-4o-latest","knowledge":"2024-08","last_updated":"2024-08-14","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI ChatGPT-4o","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-08-14","retired":false,"tags":null},"claude-3-haiku-20240307":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.3,"input":0.25,"output":1.25},"deprecated":false,"extra":{"attachment":false,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"claude-3-haiku-20240307","knowledge":"2024-03","last_updated":"2024-03-07","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude 3 Haiku","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-03-07","retired":false,"tags":null},"claude-3.5-haiku":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.08,"cache_write":1,"input":0.7999999999999999,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"claude-3.5-haiku","knowledge":"2024-10","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude 3.5 Haiku","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"claude-3.5-sonnet-v2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.30000000000000004,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"temperature":true},"family":null,"id":"claude-3.5-sonnet-v2","knowledge":"2024-10","last_updated":"2024-10-22","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude 3.5 Sonnet v2","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-10-22","retired":false,"tags":null},"claude-3.7-sonnet":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.30000000000000004,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"temperature":true},"family":null,"id":"claude-3.7-sonnet","knowledge":"2025-02","last_updated":"2025-02-19","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude 3.7 Sonnet","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-02-19","retired":false,"tags":null},"claude-4.5-haiku":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.09999999999999999,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"claude-4.5-haiku","knowledge":"2025-10","last_updated":"2025-10-01","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude 4.5 Haiku","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-10-01","retired":false,"tags":null},"claude-4.5-opus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":63999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-4.5-opus","knowledge":"2025-11","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.5","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"claude-4.5-sonnet":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.30000000000000004,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":63999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-4.5-sonnet","knowledge":"2025-09","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 4.5","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-haiku-4-5-20251001":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.09999999999999999,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"temperature":true},"family":null,"id":"claude-haiku-4-5-20251001","knowledge":"2025-10","last_updated":"2025-10-01","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude 4.5 Haiku (20251001)","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-10-01","retired":false,"tags":null},"claude-opus-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":31999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4","knowledge":"2025-05","last_updated":"2025-05-14","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-05-14","retired":false,"tags":null},"claude-opus-4-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":31999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-1","knowledge":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.1","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-1-20250805":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":31999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-1-20250805","knowledge":"2025-08","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude Opus 4.1 (20250805)","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-sonnet-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.30000000000000004,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":63999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4","knowledge":"2025-05","last_updated":"2025-05-14","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 4","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-05-14","retired":false,"tags":null},"claude-sonnet-4-5-20250929":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.30000000000000004,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":63999,"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-5-20250929","knowledge":"2025-09","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Anthropic: Claude Sonnet 4.5 (20250929)","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"deepseek-r1-distill-llama-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-r1-distill-llama-70b","knowledge":"2025-01","last_updated":"2025-01-20","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek R1 Distill Llama 70B","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek-reasoner":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.07,"input":0.56,"output":1.68},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":false,"temperature":true},"family":null,"id":"deepseek-reasoner","knowledge":"2025-01","last_updated":"2025-01-20","lifecycle":null,"limits":{"context":128000,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek Reasoner","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepseek-tng-r1t2-chimera":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","open_weights":false,"temperature":true},"family":null,"id":"deepseek-tng-r1t2-chimera","knowledge":"2025-07","last_updated":"2025-07-02","lifecycle":null,"limits":{"context":130000,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek TNG R1T2 Chimera","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-07-02","retired":false,"tags":null},"deepseek-v3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.56,"output":1.68},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"temperature":true},"family":null,"id":"deepseek-v3","knowledge":"2024-12","last_updated":"2024-12-26","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepseek-v3.1-terminus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.21600000000000003,"input":0.27,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"deepseek-v3.1-terminus","knowledge":"2025-09","last_updated":"2025-09-22","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.1 Terminus","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-22","retired":false,"tags":null},"deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.27,"output":0.41},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":false,"temperature":true},"family":null,"id":"deepseek-v3.2","knowledge":"2025-09","last_updated":"2025-09-22","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-22","retired":false,"tags":null},"ernie-4.5-21b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.07,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ernie","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"ernie-4.5-21b-a3b-thinking","knowledge":"2025-03","last_updated":"2025-03-16","lifecycle":null,"limits":{"context":128000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Baidu Ernie 4.5 21B A3B Thinking","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-03-16","retired":false,"tags":null},"gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.3,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-flash","knowledge":"2025-06","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google Gemini 2.5 Flash","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.024999999999999998,"cache_write":0.09999999999999999,"input":0.09999999999999999,"output":0.39999999999999997},"deprecated":false,"extra":{"attachment":false,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":512,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-flash-lite","knowledge":"2025-07","last_updated":"2025-07-22","lifecycle":null,"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google Gemini 2.5 Flash Lite","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3125,"cache_write":1.25,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-pro","knowledge":"2025-06","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google Gemini 2.5 Pro","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-3-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19999999999999998,"input":2,"output":12},"deprecated":false,"extra":{"attachment":false,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","high"]}],"temperature":true},"family":null,"id":"gemini-3-pro-preview","knowledge":"2025-11","last_updated":"2025-11-18","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Google Gemini 3 Pro Preview","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-11-18","retired":false,"tags":null},"gemma-3-12b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.049999999999999996,"output":0.09999999999999999},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":false,"temperature":true},"family":null,"id":"gemma-3-12b-it","knowledge":"2024-12","last_updated":"2024-12-01","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google Gemma 3 12B","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-12-01","retired":false,"tags":null},"gemma2-9b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0.03},"deprecated":false,"extra":{"attachment":false,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":false,"temperature":true},"family":null,"id":"gemma2-9b-it","knowledge":"2024-06","last_updated":"2024-06-25","lifecycle":null,"limits":{"context":8192,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Google Gemma 2","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-25","retired":false,"tags":null},"glm-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.44999999999999996,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"glm-4.6","knowledge":"2024-07","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Zai GLM-4.6","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"gpt-4.1","knowledge":"2025-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4.1","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.09999999999999999,"input":0.39999999999999997,"output":1.5999999999999999},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"temperature":true},"family":null,"id":"gpt-4.1-mini","knowledge":"2025-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4.1 Mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-mini-2025-04-14":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.09999999999999999,"input":0.39999999999999997,"output":1.5999999999999999},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"temperature":true},"family":null,"id":"gpt-4.1-mini-2025-04-14","knowledge":"2025-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4.1 Mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.024999999999999998,"input":0.09999999999999999,"output":0.39999999999999997},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"temperature":true},"family":null,"id":"gpt-4.1-nano","knowledge":"2025-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4.1 Nano","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"temperature":true},"family":null,"id":"gpt-4o","knowledge":"2024-05","last_updated":"2024-05-13","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4o","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"temperature":true},"family":null,"id":"gpt-4o-mini","knowledge":"2024-07","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-4o-mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12500000000000003,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"temperature":false},"family":null,"id":"gpt-5","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12500000000000003,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","open_weights":false,"temperature":false},"family":null,"id":"gpt-5-chat-latest","knowledge":"2024-09","last_updated":"2024-09-30","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5 Chat Latest","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-09-30","retired":false,"tags":null},"gpt-5-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12500000000000003,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"temperature":false},"family":null,"id":"gpt-5-codex","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5 Codex","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.024999999999999998,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","open_weights":false,"temperature":false},"family":null,"id":"gpt-5-mini","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5 Mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.049999999999999996,"output":0.39999999999999997},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","open_weights":false,"temperature":false},"family":null,"id":"gpt-5-nano","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI GPT-5 Nano","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":15,"output":120},"deprecated":false,"extra":{"attachment":false,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","open_weights":false,"temperature":false},"family":null,"id":"gpt-5-pro","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: GPT-5 Pro","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12500000000000003,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","open_weights":false,"temperature":false},"family":null,"id":"gpt-5.1","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"OpenAI GPT-5.1","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5.1-chat-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12500000000000003,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","open_weights":false,"temperature":false},"family":null,"id":"gpt-5.1-chat-latest","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"OpenAI GPT-5.1 Chat","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.12500000000000003,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","open_weights":false,"temperature":false},"family":null,"id":"gpt-5.1-codex","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"OpenAI: GPT-5.1 Codex","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"gpt-5.1-codex-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.024999999999999998,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","open_weights":false,"temperature":false},"family":null,"id":"gpt-5.1-codex-mini","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"OpenAI: GPT-5.1 Codex Mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","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":0.04,"output":0.16},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"gpt-oss-120b","knowledge":"2024-06","last_updated":"2024-06-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT-OSS 120b","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.049999999999999996,"output":0.19999999999999998},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"gpt-oss-20b","knowledge":"2024-06","last_updated":"2024-06-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT-OSS 20b","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"grok-3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-3","knowledge":"2024-06","last_updated":"2024-06-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"xAI Grok 3","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"grok-3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.3,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-3-mini","knowledge":"2024-06","last_updated":"2024-06-01","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"xAI Grok 3 Mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"grok-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-4","knowledge":"2024-07","last_updated":"2024-07-09","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"xAI Grok 4","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-09","retired":false,"tags":null},"grok-4-1-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.049999999999999996,"input":0.19999999999999998,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-4-1-fast-non-reasoning","knowledge":"2025-11","last_updated":"2025-11-17","lifecycle":null,"limits":{"context":2000000,"output":30000},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"xAI Grok 4.1 Fast Non-Reasoning","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-11-17","retired":false,"tags":null},"grok-4-1-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.049999999999999996,"input":0.19999999999999998,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"grok-4-1-fast-reasoning","knowledge":"2025-11","last_updated":"2025-11-17","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"xAI Grok 4.1 Fast Reasoning","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-11-17","retired":false,"tags":null},"grok-4-fast-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.049999999999999996,"input":0.19999999999999998,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-4-fast-non-reasoning","knowledge":"2025-09","last_updated":"2025-09-19","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"xAI Grok 4 Fast Non-Reasoning","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-19","retired":false,"tags":null},"grok-4-fast-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.049999999999999996,"input":0.19999999999999998,"output":0.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"grok-4-fast-reasoning","knowledge":"2025-09","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":2000000,"output":2000000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"xAI: Grok 4 Fast Reasoning","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-01","retired":false,"tags":null},"grok-code-fast-1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.19999999999999998,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","open_weights":false,"temperature":true},"family":null,"id":"grok-code-fast-1","knowledge":"2024-08","last_updated":"2024-08-25","lifecycle":null,"limits":{"context":256000,"output":10000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"xAI Grok Code Fast 1","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-08-25","retired":false,"tags":null},"hermes-2-pro-llama-3-8b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":0.14},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"hermes-2-pro-llama-3-8b","knowledge":"2024-05","last_updated":"2024-05-27","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes 2 Pro Llama 3 8B","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-05-27","retired":false,"tags":null},"kimi-k2-0711":{"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":0.5700000000000001,"output":2.3},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":false,"temperature":true},"family":null,"id":"kimi-k2-0711","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 (07/11)","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"kimi-k2-0905":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.39999999999999997,"input":0.5,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","open_weights":false,"temperature":true},"family":null,"id":"kimi-k2-0905","knowledge":"2025-09","last_updated":"2025-09-05","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 (09/05)","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-05","retired":false,"tags":null},"kimi-k2-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.48,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","open_weights":false,"temperature":true},"family":null,"id":"kimi-k2-thinking","knowledge":"2025-11","last_updated":"2025-11-06","lifecycle":null,"limits":{"context":256000,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-11-06","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}},"catalog_only":true,"cost":{"input":0.049999999999999996,"output":0.08},"deprecated":false,"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.1-8b-instant","knowledge":"2024-07","last_updated":"2024-07-01","lifecycle":null,"limits":{"context":131072,"output":32678},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta Llama 3.1 8B Instant","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-01","retired":false,"tags":null},"llama-3.1-8b-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":0.02,"output":0.049999999999999996},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.1-8b-instruct","knowledge":"2024-07","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":16384,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta Llama 3.1 8B Instruct","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"llama-3.1-8b-instruct-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.02,"output":0.03},"deprecated":false,"extra":{"attachment":false,"description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.1-8b-instruct-turbo","knowledge":"2024-07","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta Llama 3.1 8B Instruct Turbo","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"llama-3.3-70b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.39},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.3-70b-instruct","knowledge":"2024-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":16400},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta Llama 3.3 70B Instruct","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-12-06","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}},"catalog_only":true,"cost":{"input":0.59,"output":0.7899999999999999},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-3.3-70b-versatile","knowledge":"2024-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":32678},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta Llama 3.3 70B Versatile","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"llama-4-maverick":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-4-maverick","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Meta Llama 4 Maverick 17B 128E","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"llama-4-scout":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.08,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-4-scout","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Meta Llama 4 Scout 17B 16E","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"llama-guard-4":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.21,"output":0.21},"deprecated":false,"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-guard-4","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":131072,"output":1024},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Meta Llama Guard 4 12B","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"llama-prompt-guard-2-22m":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0.01},"deprecated":false,"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-prompt-guard-2-22m","knowledge":"2024-10","last_updated":"2024-10-01","lifecycle":null,"limits":{"context":512,"output":2},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta Llama Prompt Guard 2 22M","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"llama-prompt-guard-2-86m":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.01,"output":0.01},"deprecated":false,"extra":{"attachment":false,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","open_weights":false,"temperature":true},"family":null,"id":"llama-prompt-guard-2-86m","knowledge":"2024-10","last_updated":"2024-10-01","lifecycle":null,"limits":{"context":512,"output":2},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Meta Llama Prompt Guard 2 86M","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-10-01","retired":false,"tags":null},"mistral-large-2411":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":false,"temperature":true},"family":null,"id":"mistral-large-2411","knowledge":"2024-07","last_updated":"2024-07-24","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral-Large","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-24","retired":false,"tags":null},"mistral-nemo":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":20,"output":40},"deprecated":false,"extra":{"attachment":false,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","open_weights":false,"temperature":true},"family":null,"id":"mistral-nemo","knowledge":"2024-07","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16400},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Nemo","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"mistral-small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.075,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"temperature":true},"family":null,"id":"mistral-small","knowledge":"2025-03","last_updated":"2025-06-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 3.2","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-06-20","retired":false,"tags":null},"o1":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":7.5,"input":15,"output":60},"deprecated":false,"extra":{"attachment":false,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"temperature":false},"family":null,"id":"o1","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: o1","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"o1-mini":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"temperature":false},"family":null,"id":"o1-mini","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":128000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI: o1-mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"temperature":false},"family":null,"id":"o3","knowledge":"2024-06","last_updated":"2024-06-01","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI o3","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"temperature":false},"family":null,"id":"o3-mini","knowledge":"2023-10","last_updated":"2023-10-01","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI o3 Mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2023-10-01","retired":false,"tags":null},"o3-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":20,"output":80},"deprecated":false,"extra":{"attachment":false,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","open_weights":false,"temperature":false},"family":null,"id":"o3-pro","knowledge":"2024-06","last_updated":"2024-06-01","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI o3 Pro","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","open_weights":false,"temperature":false},"family":null,"id":"o4-mini","knowledge":"2024-06","last_updated":"2024-06-01","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"OpenAI o4 Mini","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-06-01","retired":false,"tags":null},"qwen2.5-coder-7b-fast":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.03,"output":0.09},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen2.5-coder-7b-fast","knowledge":"2024-09","last_updated":"2024-09-15","lifecycle":null,"limits":{"context":32000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5 Coder 7B fast","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2024-09-15","retired":false,"tags":null},"qwen3-235b-a22b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.3,"output":2.9000000000000004},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-235b-a22b-thinking","knowledge":"2025-07","last_updated":"2025-07-25","lifecycle":null,"limits":{"context":262144,"output":81920},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Thinking","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-07-25","retired":false,"tags":null},"qwen3-30b-a3b":{"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":0.08,"output":0.29},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-30b-a3b","knowledge":"2025-06","last_updated":"2025-06-01","lifecycle":null,"limits":{"context":41000,"output":41000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 30B A3B","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-06-01","retired":false,"tags":null},"qwen3-32b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.29,"output":0.59},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen3-32b","knowledge":"2025-04","last_updated":"2025-04-28","lifecycle":null,"limits":{"context":131072,"output":40960},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 32B","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-04-28","retired":false,"tags":null},"qwen3-coder":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.22,"output":0.95},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-coder","knowledge":"2025-07","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Qwen3 Coder 480B A35B Instruct Turbo","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-07-23","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":0.09999999999999999,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-coder-30b-a3b-instruct","knowledge":"2025-07","last_updated":"2025-07-31","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder 30B A3B Instruct","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-07-31","retired":false,"tags":null},"qwen3-next-80b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.14,"output":1.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-next-80b-a3b-instruct","knowledge":"2025-01","last_updated":"2025-01-01","lifecycle":null,"limits":{"context":262000,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3 Next 80B A3B Instruct","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-01","retired":false,"tags":null},"qwen3-vl-235b-a22b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"temperature":true},"family":null,"id":"qwen3-vl-235b-a22b-instruct","knowledge":"2025-09","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B A22B Instruct","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"sonar":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","open_weights":false,"temperature":true},"family":null,"id":"sonar","knowledge":"2025-01","last_updated":"2025-01-27","lifecycle":null,"limits":{"context":127000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity Sonar","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null},"sonar-deep-research":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"sonar-deep-research","knowledge":"2025-01","last_updated":"2025-01-27","lifecycle":null,"limits":{"context":127000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity Sonar Deep Research","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null},"sonar-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":false,"description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","open_weights":false,"temperature":true},"family":null,"id":"sonar-pro","knowledge":"2025-01","last_updated":"2025-01-27","lifecycle":null,"limits":{"context":200000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity Sonar Pro","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null},"sonar-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":1,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"sonar-reasoning","knowledge":"2025-01","last_updated":"2025-01-27","lifecycle":null,"limits":{"context":127000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity Sonar Reasoning","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null},"sonar-reasoning-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":8},"deprecated":false,"extra":{"attachment":false,"description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"sonar-reasoning-pro","knowledge":"2025-01","last_updated":"2025-01-27","lifecycle":null,"limits":{"context":127000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Perplexity Sonar Reasoning Pro","pricing":null,"provider":"helicone","provider_model_id":null,"release_date":"2025-01-27","retired":false,"tags":null}},"name":"Helicone","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;

package/dist/providers/hetzner.d.ts

@@ -0,0 +1,11 @@
+import type {
+  Provider,
+  ProviderCatalog,
+} from "../types.js";
+
+export declare const data: Provider;
+declare const provider: ProviderCatalog<
+  "hetzner",
+  "Qwen/Qwen3.6-35B-A3B-FP8"
+>;
+export default provider;

package/dist/providers/hetzner.js

@@ -0,0 +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};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;