@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/edenai.js

@@ -0,0 +1,5 @@
+import { createProviderCatalog } from "../provider.js";
+
+export const data = {"alias_of":null,"base_url":"https://api.edenai.run/v3","catalog_only":true,"config_schema":null,"doc":"https://docs.edenai.co","env":["EDENAI_API_KEY"],"exclude_models":null,"extra":null,"id":"edenai","models":{"amazon/moonshot.kimi-k2-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"amazon/moonshot.kimi-k2-thinking","knowledge":"2024-08","last_updated":"2025-11-06","lifecycle":null,"limits":{"context":128000,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"amazon/moonshotai.kimi-k2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":false},"family":null,"id":"amazon/moonshotai.kimi-k2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"amazon/nvidia.nemotron-nano-9b-v2":{"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":0.06,"output":0.23},"deprecated":false,"extra":{"attachment":false,"description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"amazon/nvidia.nemotron-nano-9b-v2","knowledge":null,"last_updated":"2025-08-18","lifecycle":null,"limits":{"context":128000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Nano 9B v2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-18","retired":false,"tags":null},"amazon/nvidia.nemotron-nano-9b-v2@us":{"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":0.06,"output":0.23},"deprecated":false,"extra":{"attachment":false,"description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"amazon/nvidia.nemotron-nano-9b-v2@us","knowledge":null,"last_updated":"2025-08-18","lifecycle":null,"limits":{"context":128000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron Nano 9B v2 (US)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-18","retired":false,"tags":null},"amazon/zai.glm-4.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"amazon/zai.glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"amazon/zai.glm-4.7-flash@us":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"amazon/zai.glm-4.7-flash@us","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":200000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash (US)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"anthropic/claude-fable-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"anthropic/claude-fable-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1,"cache_write":12.5,"input":10,"output":50},"deprecated":false,"extra":{"attachment":true,"description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-fable-latest","knowledge":"2026-01-31","last_updated":"2026-06-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-09","retired":false,"tags":null},"anthropic/claude-opus-4-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4-5","knowledge":"2025-05","last_updated":"2025-11-24","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5 (latest)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-24","retired":false,"tags":null},"anthropic/claude-opus-4-5-20251101":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4-5-20251101","knowledge":"2025-05","last_updated":"2025-11-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-01","retired":false,"tags":null},"anthropic/claude-opus-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"anthropic/claude-opus-4-7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-4-7","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"anthropic/claude-opus-4-8":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"anthropic/claude-opus-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-opus-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-opus-latest","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"anthropic/claude-sonnet-4-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"anthropic/claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"anthropic/claude-sonnet-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"anthropic/claude-sonnet-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"anthropic/claude-sonnet-latest","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"azure/gpt-5.1-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"azure/gpt-5.1-codex","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":272000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"azure/gpt-5.1-codex-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"azure/gpt-5.1-codex-max","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":272000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex Max","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"azure/gpt-5.1-codex-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"azure/gpt-5.1-codex-mini","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":272000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1 Codex mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"azure/gpt-5.2-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"azure/gpt-5.2-codex","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":272000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"cerebras/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.35,"input":0.35,"output":0.75},"deprecated":false,"extra":{"attachment":false,"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":"cerebras/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.351,"output":0.555},"deprecated":false,"extra":{"attachment":false,"description":"Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following","family":"gemma","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","knowledge":null,"last_updated":"2025-09-23","lifecycle":null,"limits":{"context":128000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemma-SEA-LION-v4-27B-IT","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"cloudflare/@cf/deepseek-ai/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":0.014,"input":0.44,"output":1.32},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"cloudflare/@cf/meta/llama-guard-3-8b":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.484,"output":0.03},"deprecated":false,"extra":{"attachment":false,"description":"Llama 3.1-based safety classifier for moderating prompts and model responses","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"cloudflare/@cf/meta/llama-guard-3-8b","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-Guard-3-8B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"cloudflare/@cf/openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.35,"output":0.75},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"cloudflare/@cf/openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"cloudflare/@cf/openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.2,"output":0.3},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"cloudflare/@cf/openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.66,"output":1},"deprecated":false,"extra":{"attachment":false,"description":"Open coding-focused Qwen model for code generation, repair, and repository reasoning","family":"qwen","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","knowledge":null,"last_updated":"2024-11-12","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen2.5-Coder-32B-Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-11-12","retired":false,"tags":null},"cloudflare/@cf/zai-org/glm-4.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.0605,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"cloudflare/@cf/zai-org/glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"cohere/command-a-03-2025":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-a-03-2025","knowledge":"2024-06-01","last_updated":"2025-03-13","lifecycle":null,"limits":{"context":288000,"output":8000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command A","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-03-13","retired":false,"tags":null},"cohere/command-r-08-2024":{"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":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-r-08-2024","knowledge":"2024-06-01","last_updated":"2024-08-30","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command R","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-08-30","retired":false,"tags":null},"cohere/command-r-plus-08-2024":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-r-plus-08-2024","knowledge":"2024-06-01","last_updated":"2024-08-30","lifecycle":null,"limits":{"context":128000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command R+","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-08-30","retired":false,"tags":null},"cohere/command-r7b-12-2024":{"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":0.0375,"output":0.15},"deprecated":false,"extra":{"attachment":false,"description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"cohere/command-r7b-12-2024","knowledge":"2024-06-01","last_updated":"2024-12-02","lifecycle":null,"limits":{"context":132000,"output":4000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Command R7B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-02","retired":false,"tags":null},"databricks/databricks-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":0.15001,"output":0.59997},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"databricks/databricks-gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"databricks/databricks-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":0.07,"output":0.30002},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"databricks/databricks-gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"deepinfra/ByteDance/Seed-2.0-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/ByteDance/Seed-2.0-code","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 2.0 Code","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"deepinfra/ByteDance/Seed-2.0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/ByteDance/Seed-2.0-mini","knowledge":null,"last_updated":"2026-02-14","lifecycle":null,"limits":{"context":256000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Seed 2.0 Mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-14","retired":false,"tags":null},"deepinfra/deepseek-ai/DeepSeek-R1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":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":0.7,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/deepseek-ai/DeepSeek-R1","knowledge":"2024-07","last_updated":"2025-05-29","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-R1","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-01-20","retired":false,"tags":null},"deepinfra/deepseek-ai/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":{"input":0.32,"output":0.89},"deprecated":false,"extra":{"attachment":false,"description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/deepseek-ai/DeepSeek-V3","knowledge":null,"last_updated":"2024-12-26","lifecycle":null,"limits":{"context":163840,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek-V3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-26","retired":false,"tags":null},"deepinfra/deepseek-ai/DeepSeek-V3-0324":{"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":0.135,"input":0.24,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/deepseek-ai/DeepSeek-V3-0324","knowledge":null,"last_updated":"2025-03-24","lifecycle":null,"limits":{"context":163840,"output":163840},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3 0324","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-03-24","retired":false,"tags":null},"deepinfra/deepseek-ai/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":0.016,"input":0.08,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1.3,"output":2.6},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.345,"output":0.345},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for image understanding, captioning, and visual QA","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","knowledge":"2023-12","last_updated":"2024-09-25","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama-3.2-11B-Vision-Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-09-25","retired":false,"tags":null},"deepinfra/meta-llama/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":0.1,"output":0.32},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"deepinfra/meta-llama/Llama-Guard-3-8B":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.055,"output":0.055},"deprecated":false,"extra":{"attachment":false,"description":"Llama 3.1-based safety classifier for moderating prompts and model responses","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/meta-llama/Llama-Guard-3-8B","knowledge":"2023-12","last_updated":"2024-07-23","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-Guard-3-8B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-07-23","retired":false,"tags":null},"deepinfra/meta-models/Muse-Glimmer-30B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/meta-models/Muse-Glimmer-30B","knowledge":"2026-01-04","last_updated":"2026-08-10","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Muse Glimmer 30B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-10","retired":false,"tags":null},"deepinfra/moonshotai/Kimi-K2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.07,"input":0.45,"output":2.25},"deprecated":false,"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"deepinfra/moonshotai/Kimi-K2.5","knowledge":"2025-01","last_updated":"2026-01","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-01","retired":false,"tags":null},"deepinfra/nemotron-3-ultra-550b-a55b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":262144,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra 550B A55B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"deepinfra/nvidia/Llama-3.1-Nemotron-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":0.6,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","knowledge":null,"last_updated":"2025-04-15","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.1 Nemotron 70B Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04-15","retired":false,"tags":null},"deepinfra/nvidia/Nemotron-3-Nano-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":{"cache_read":0.025,"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","knowledge":null,"last_updated":"2025-12-15","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Nano 30B A3B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-15","retired":false,"tags":null},"deepinfra/openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.037,"output":0.17},"deprecated":false,"extra":{"attachment":false,"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":"deepinfra/openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"deepinfra/openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.03,"output":0.14},"deprecated":false,"extra":{"attachment":false,"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":"deepinfra/openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"deepinfra/stepfun-ai/Step-3.5-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.09,"output":0.3},"deprecated":false,"extra":{"attachment":false,"description":"StepFun flash lane for quick multimodal reasoning and coding assistance","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/stepfun-ai/Step-3.5-Flash","knowledge":"2025-01","last_updated":"2026-02-13","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Step 3.5 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"deepinfra/stepfun-ai/Step-3.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.2,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"deepinfra/stepfun-ai/Step-3.7-Flash","knowledge":"2026-03-01","last_updated":"2026-05-29","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Step 3.7 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-29","retired":false,"tags":null},"deepinfra/tencent/Hy3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.035,"input":0.14,"output":0.58},"deprecated":false,"extra":{"attachment":false,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/tencent/Hy3","knowledge":null,"last_updated":"2026-07-06","lifecycle":null,"limits":{"context":262144,"output":64000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hy3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-06","retired":false,"tags":null},"deepinfra/thinkingmachines/Inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.16,"input":0.95,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/thinkingmachines/Inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"deepinfra/thinkingmachines/Inkling-Small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.45,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/thinkingmachines/Inkling-Small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"deepinfra/zai-org/GLM-4.7-Flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.06,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepinfra/zai-org/GLM-4.7-Flash","knowledge":"2025-04","last_updated":"2026-01-19","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7-Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-01-19","retired":false,"tags":null},"deepseek/deepseek-chat":{"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":0.028,"input":0.28,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-chat","knowledge":"2025-09","last_updated":"2026-02-28","lifecycle":null,"limits":{"context":131072,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek Chat","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-reasoner":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.28,"output":0.42},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-reasoner","knowledge":"2025-09","last_updated":"2026-02-28","lifecycle":null,"limits":{"context":131072,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek Reasoner","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-01","retired":false,"tags":null},"deepseek/deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.007,"input":0.22,"output":0.66},"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","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek/deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.022,"input":0.66,"output":1.98},"deprecated":false,"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek/deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-04-24","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.028,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.044,"input":1.32,"output":3.96},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"fireworks_ai/accounts/fireworks/models/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"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":"fireworks_ai/accounts/fireworks/models/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"fireworks_ai/accounts/fireworks/models/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.035,"input":0.07,"output":0.3},"deprecated":false,"extra":{"attachment":false,"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":"fireworks_ai/accounts/fireworks/models/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"fireworks_ai/accounts/fireworks/models/muse-glimmer-30b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.35,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"fireworks_ai/accounts/fireworks/models/muse-glimmer-30b","knowledge":"2026-01-04","last_updated":"2026-08-10","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Muse Glimmer 30B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-10","retired":false,"tags":null},"fireworks_ai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.014,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"fireworks_ai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"fireworks_ai/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":{"cache_read":0.035,"input":0.07,"output":0.3},"deprecated":false,"extra":{"attachment":false,"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":"fireworks_ai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"flexai/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.08,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"flexai/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":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"flexai/Muse-Glimmer-30B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":false,"temperature":true},"family":null,"id":"flexai/Muse-Glimmer-30B","knowledge":"2026-01-04","last_updated":"2026-08-10","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Muse Glimmer 30B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-10","retired":false,"tags":null},"flexai/Nemotron-3-Super-120B-A12B":{"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":0.085,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"structured_output":false,"temperature":true},"family":null,"id":"flexai/Nemotron-3-Super-120B-A12B","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B A12B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"flexai/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.08,"output":0.18},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"flexai/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":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"flexai/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.039,"output":0.1},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"flexai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"flexai/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.03,"output":0.13},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"flexai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"google/gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"input_audio":1,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["audio","image","text","video"],"output":["text","image"]},"model":null,"name":"Nano Banana","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"google/gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0.083333,"input":0.5,"input_audio":1,"output":3,"reasoning":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"google/gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"google/gemini-3-pro-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3-pro-image-preview","knowledge":"2025-01","last_updated":"2025-11-20","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-20","retired":false,"tags":null},"google/gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["image","text"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"google/gemini-3.1-flash-image-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-image-preview","knowledge":"2025-01","last_updated":"2026-02-26","lifecycle":null,"limits":{"context":65536,"output":65536},"modalities":{"input":["image","text"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-26","retired":false,"tags":null},"google/gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"cache_write":0.083333,"input":0.25,"input_audio":0.5,"output":1.5,"reasoning":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"google/gemini-3.1-flash-lite-image":{"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":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-image","knowledge":"2025-01","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":65536,"output":4096},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana 2 Lite","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"google/gemini-3.1-flash-lite-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":0.025,"cache_write":0.083333,"input":0.25,"input_audio":0.5,"output":1.5,"reasoning":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-flash-lite-preview","knowledge":"2025-01","last_updated":"2026-03-03","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"google/gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.1-pro-preview-customtools":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.1-pro-preview-customtools","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview Custom Tools","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":0.083333,"input":1.5,"input_audio":3,"output":9,"reasoning":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"google/gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"input_audio":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"google/gemini-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-3.7-flash","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"google/gemini-flash-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-flash-latest","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"google/gemini-pro-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google/gemini-pro-latest","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"google/lyria-3-clip-preview":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0,"output":0},"deprecated":false,"extra":{"attachment":true,"description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","family":"lyria","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"google/lyria-3-clip-preview","knowledge":null,"last_updated":"2026-03-25","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image"],"output":["text","audio"]},"model":null,"name":"Lyria 3 Clip Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-25","retired":false,"tags":null},"groq/openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"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":"groq/openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"groq/openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.0375,"input":0.075,"output":0.3},"deprecated":false,"extra":{"attachment":false,"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":"groq/openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"ionos/meta-llama/Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.751855,"output":0.751855},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"ionos/meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"ionos/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.173505,"output":0.751855},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"ionos/openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"minimax/MiniMax-M2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"minimax/MiniMax-M2","knowledge":null,"last_updated":"2025-10-27","lifecycle":null,"limits":{"context":204800,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-10-27","retired":false,"tags":null},"minimax/MiniMax-M2.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/MiniMax-M2.1","knowledge":null,"last_updated":"2025-12-23","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.1","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-23","retired":false,"tags":null},"minimax/MiniMax-M2.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/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":"edenai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax/MiniMax-M2.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/MiniMax-M2.7","knowledge":null,"last_updated":"2026-03-18","lifecycle":null,"limits":{"context":204800,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax-M2.7","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax/MiniMax-M3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"minimax/MiniMax-M3","knowledge":null,"last_updated":"2026-06-01","lifecycle":null,"limits":{"context":524288,"output":128000},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax-M3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-01","retired":false,"tags":null},"mistral/codestral-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral/codestral-latest","knowledge":"2024-10","last_updated":"2025-01-04","lifecycle":null,"limits":{"context":256000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Codestral (latest)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-05-29","retired":false,"tags":null},"mistral/devstral-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral/devstral-2512","knowledge":"2025-12","last_updated":"2025-12-09","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"Devstral 2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-09","retired":false,"tags":null},"mistral/devstral-medium-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":false,"description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral/devstral-medium-latest","knowledge":"2025-12","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Devstral 2 (latest)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-02","retired":false,"tags":null},"mistral/magistral-medium-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":2,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"mistral/magistral-medium-latest","knowledge":"2025-06","last_updated":"2025-03-20","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Magistral Medium (latest)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-03-17","retired":false,"tags":null},"mistral/mistral-large-2512":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral/mistral-large-2512","knowledge":"2024-11","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Mistral Large 3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"mistral/mistral-large-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"mistral/mistral-large-latest","knowledge":"2024-11","last_updated":"2025-12-02","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Mistral Large (latest)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-11-01","retired":false,"tags":null},"mistral/mistral-medium-2505":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.4,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"mistral/mistral-medium-2505","knowledge":"2025-05","last_updated":"2025-05-07","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-05-07","retired":false,"tags":null},"mistral/mistral-medium-2604":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.5,"output":7.5},"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/mistral-medium-2604","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium 3.5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistral/mistral-medium-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1.5,"output":7.5},"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/mistral-medium-latest","knowledge":null,"last_updated":"2026-04-29","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Medium (latest)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-29","retired":false,"tags":null},"mistral/mistral-small-2603":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.015,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistral/mistral-small-2603","knowledge":"2025-06","last_updated":"2026-03-16","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"mistral/mistral-small-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.06,"output":0.18},"deprecated":false,"extra":{"attachment":true,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"mistral/mistral-small-latest","knowledge":"2025-06","last_updated":"2026-03-16","lifecycle":null,"limits":{"context":262144,"output":256000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small (latest)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"moonshot/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":0.16,"input":0.95,"output":4},"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":[],"structured_output":true,"temperature":true},"family":null,"id":"moonshot/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":"edenai","provider_model_id":null,"release_date":"2026-04-21","retired":false,"tags":null},"moonshot/kimi-k2.7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.19,"input":0.95,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"moonshot/kimi-k2.7-code","knowledge":"2025-01","last_updated":"2026-06-12","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"moonshot/kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"moonshot/kimi-k3","knowledge":null,"last_updated":"2026-07-16","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"nebius/meta-llama/Llama-3.3-70B-Instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.13,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nebius/meta-llama/Llama-3.3-70B-Instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":131072,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"nebius/nvidia/Nemotron-3-Ultra-550b-a55b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":1,"output":3},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"nebius/nvidia/Nemotron-3-Ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":8000,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra 550B A55B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"nebius/nvidia/nemotron-3-super-120b-a12b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":false,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"structured_output":true,"temperature":true},"family":null,"id":"nebius/nvidia/nemotron-3-super-120b-a12b","knowledge":null,"last_updated":"2026-03-11","lifecycle":null,"limits":{"context":8000,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Super 120B A12B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-11","retired":false,"tags":null},"nebius/openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open 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":"nebius/openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-3.5-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":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-3.5-turbo","knowledge":"2021-09-01","last_updated":"2023-11-06","lifecycle":null,"limits":{"context":16385,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-3.5-turbo","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2023-03-01","retired":false,"tags":null},"openai/gpt-4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":30,"output":60},"deprecated":false,"extra":{"attachment":false,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4","knowledge":"2023-11","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":8191,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-4","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/gpt-4-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":10,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4-turbo","knowledge":"2023-12","last_updated":"2024-04-09","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4 Turbo","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2023-11-06","retired":false,"tags":null},"openai/gpt-4.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.4,"output":1.6},"deprecated":false,"extra":{"attachment":true,"description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1-mini","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1 mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4.1-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.1,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4.1-nano","knowledge":"2024-04","last_updated":"2025-04-14","lifecycle":null,"limits":{"context":1047576,"output":32768},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-4.1 nano","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04-14","retired":false,"tags":null},"openai/gpt-4o":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-05-13","retired":false,"tags":null},"openai/gpt-4o-2024-08-06":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-08-06","knowledge":"2023-09","last_updated":"2024-08-06","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o (2024-08-06)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-08-06","retired":false,"tags":null},"openai/gpt-4o-2024-11-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.25,"input":2.5,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-2024-11-20","knowledge":"2023-09","last_updated":"2024-11-20","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o (2024-11-20)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-11-20","retired":false,"tags":null},"openai/gpt-4o-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai/gpt-4o-mini","knowledge":"2023-09","last_updated":"2024-07-18","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-4o mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-07-18","retired":false,"tags":null},"openai/gpt-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5","knowledge":"2024-09-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-mini","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5 Mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.005,"input":0.05,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-nano","knowledge":"2024-05-30","last_updated":"2025-08-07","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5 Nano","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-07","retired":false,"tags":null},"openai/gpt-5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":15,"output":120},"deprecated":false,"extra":{"attachment":true,"description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5-pro","knowledge":"2024-09-30","last_updated":"2025-10-06","lifecycle":null,"limits":{"context":400000,"output":272000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-5 Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-10-06","retired":false,"tags":null},"openai/gpt-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.1","knowledge":"2024-09-30","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-5.1","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-5.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.2-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":21,"output":168},"deprecated":false,"extra":{"attachment":true,"description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.2-pro","knowledge":"2025-08-31","last_updated":"2025-12-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"GPT-5.2 Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-11","retired":false,"tags":null},"openai/gpt-5.3-codex":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.175,"input":1.75,"output":14},"deprecated":false,"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.3-codex","knowledge":"2025-08-31","last_updated":"2026-02-05","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"openai/gpt-5.4":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"input":2.5,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-mini","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-nano":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"input":0.2,"output":1.25},"deprecated":false,"extra":{"attachment":true,"description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-nano","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"GPT-5.4 nano","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-5.4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":3,"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.4-pro","knowledge":"2025-08-31","last_updated":"2026-03-05","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.4 Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai/gpt-5.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.5","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/gpt-5.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":3,"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.5-pro","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5 Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/gpt-5.6-luna":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.02,"cache_write":0.25,"input":0.2,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-sol":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-5.6-terra":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-5.6-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-latest","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai/gpt-mini-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"output":4.5},"deprecated":false,"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-mini-latest","knowledge":"2025-08-31","last_updated":"2026-03-17","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["pdf","image","text"],"output":["text"]},"model":null,"name":"GPT-5.4 mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-17","retired":false,"tags":null},"openai/gpt-pro-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":3,"input":30,"output":180},"deprecated":false,"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/gpt-pro-latest","knowledge":"2025-12-01","last_updated":"2026-04-23","lifecycle":null,"limits":{"context":1050000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"GPT-5.5 Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai/o1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":7.5,"input":15,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o1","knowledge":"2023-09","last_updated":"2024-12-05","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o1","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-05","retired":false,"tags":null},"openai/o1-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":150,"output":600},"deprecated":false,"extra":{"attachment":true,"description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o1-pro","knowledge":"2023-09","last_updated":"2025-03-19","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o1-pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-03-19","retired":false,"tags":null},"openai/o3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"o3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"openai/o3-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.55,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3-mini","knowledge":"2024-05","last_updated":"2025-01-29","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"o3-mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-20","retired":false,"tags":null},"openai/o3-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":20,"output":80},"deprecated":false,"extra":{"attachment":true,"description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o3-pro","knowledge":"2024-05","last_updated":"2025-06-10","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["text","pdf","image"],"output":["text"]},"model":null,"name":"o3-pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-06-10","retired":false,"tags":null},"openai/o4-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.275,"input":1.1,"output":4.4},"deprecated":false,"extra":{"attachment":true,"description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai/o4-mini","knowledge":"2024-05","last_updated":"2025-04-16","lifecycle":null,"limits":{"context":200000,"output":100000},"modalities":{"input":["image","text","pdf"],"output":["text"]},"model":null,"name":"o4-mini","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04-16","retired":false,"tags":null},"ovhcloud/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.09,"output":0.47},"deprecated":false,"extra":{"attachment":false,"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":"ovhcloud/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"ovhcloud/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":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.05,"output":0.18},"deprecated":false,"extra":{"attachment":false,"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":"ovhcloud/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"perplexityai/sonar":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":1},"deprecated":false,"extra":{"attachment":true,"description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"perplexityai/sonar","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":127072,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"perplexityai/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,"reasoning":3},"deprecated":false,"extra":{"attachment":false,"description":"Sonar search model for autonomous research and citation-backed long-form reports","family":"sonar","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":false,"temperature":false},"family":null,"id":"perplexityai/sonar-deep-research","knowledge":"2025-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Sonar Deep Research","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-02-01","retired":false,"tags":null},"perplexityai/sonar-pro":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"perplexityai/sonar-pro","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":200000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"perplexityai/sonar-reasoning-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":8},"deprecated":false,"extra":{"attachment":true,"description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":false,"temperature":true},"family":null,"id":"perplexityai/sonar-reasoning-pro","knowledge":"2025-09-01","last_updated":"2025-09-01","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Sonar Reasoning Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-01-01","retired":false,"tags":null},"qwen/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":0.04,"input":0.2,"output":0.4},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"qwen/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":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"qwen/qwen-max":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.32,"input":1.6,"output":6.4},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-max","knowledge":"2024-04","last_updated":"2025-01-25","lifecycle":null,"limits":{"context":32768,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen Max","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-04-03","retired":false,"tags":null},"qwen/qwen-vl-max":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.16,"input":0.8,"output":3.2},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen-vl-max","knowledge":"2024-04","last_updated":"2025-08-13","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen-VL Max","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-04-08","retired":false,"tags":null},"qwen/qwen-vl-plus":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"cache_read":0.042,"input":0.21,"output":0.63},"deprecated":false,"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen-vl-plus","knowledge":"2024-04","last_updated":"2025-08-15","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen-VL Plus","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-01-25","retired":false,"tags":null},"qwen/qwen3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.23,"output":0.92},"deprecated":false,"extra":{"attachment":false,"description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-instruct-2507","knowledge":null,"last_updated":"2025-07-21","lifecycle":null,"limits":{"context":131072,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B-A22B Instruct 2507","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-07-21","retired":false,"tags":null},"qwen/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":0.45,"output":2.25},"deprecated":false,"extra":{"attachment":false,"description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-30b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 30B-A3B Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen/qwen3-coder-480b-a35b-instruct":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":false,"description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwen3-coder-480b-a35b-instruct","knowledge":"2025-04","last_updated":"2025-04","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Coder 480B-A35B Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-04","retired":false,"tags":null},"qwen/qwen3-coder-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.06,"cache_write":0.375,"input":0.3,"output":1.5},"deprecated":false,"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-flash","knowledge":"2025-04","last_updated":"2025-07-28","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-07-28","retired":false,"tags":null},"qwen/qwen3-coder-next":{"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":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-next","knowledge":"2025-09","last_updated":"2026-02-03","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Next","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-03","retired":false,"tags":null},"qwen/qwen3-coder-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":false,"description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-coder-plus","knowledge":"2025-04","last_updated":"2025-07-23","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Coder Plus","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-07-23","retired":false,"tags":null},"qwen/qwen3-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"cache_write":1.5,"input":1.2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-max","knowledge":"2025-04","last_updated":"2025-09-23","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 Max","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-09-23","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-instruct":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-instruct","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next 80B-A3B Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"qwen/qwen3-next-80b-a3b-thinking":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":1.2},"deprecated":false,"extra":{"attachment":false,"description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-next-80b-a3b-thinking","knowledge":"2025-04","last_updated":"2025-09","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3-Next 80B-A3B (Thinking)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-09","retired":false,"tags":null},"qwen/qwen3.8-2.4t-a95b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.8-2.4t-a95b","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3.8 2.4T A95B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"qwen/qwen3.8-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.25,"cache_write":2.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3.8-max","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen3.8 Max","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"qwen/qwq-plus":{"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":0.8,"output":2.4},"deprecated":false,"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"qwen/qwq-plus","knowledge":"2024-04","last_updated":"2025-03-05","lifecycle":null,"limits":{"context":131072,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"QwQ Plus","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-03-05","retired":false,"tags":null},"scaleway/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":{"input":0.46268,"output":0.92536},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"scaleway/deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":256000,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"scaleway/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":0.173505,"output":0.69402},"deprecated":false,"extra":{"attachment":false,"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":false,"temperature":true},"family":null,"id":"scaleway/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"scaleway/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":1.04103,"output":1.04103},"deprecated":false,"extra":{"attachment":false,"description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","open_weights":true,"structured_output":false,"temperature":true},"family":null,"id":"scaleway/llama-3.3-70b-instruct","knowledge":"2023-12","last_updated":"2024-12-06","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama-3.3-70B-Instruct","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2024-12-06","retired":false,"tags":null},"together_ai/deepseek-ai/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":0.03,"input":0.14,"output":0.28},"deprecated":false,"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","knowledge":"2025-05","last_updated":"2026-07-31","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.13,"input":1.32,"output":3.96},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1048576,"output":384000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"together_ai/meta-models/Muse-Glimmer-30B":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.04,"input":0.35,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"together_ai/meta-models/Muse-Glimmer-30B","knowledge":"2026-01-04","last_updated":"2026-08-10","lifecycle":null,"limits":{"context":131072,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Muse Glimmer 30B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-10","retired":false,"tags":null},"together_ai/nvidia/nemotron-3-ultra-550b-a55b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":0.6,"output":3.6},"deprecated":false,"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"together_ai/nvidia/nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-04","lifecycle":null,"limits":{"context":512288,"output":128000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Nemotron 3 Ultra 550B A55B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"together_ai/openai/gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.15,"output":0.6},"deprecated":false,"extra":{"attachment":false,"description":"Open 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":"together_ai/openai/gpt-oss-120b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"together_ai/openai/gpt-oss-20b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.05,"output":0.2},"deprecated":false,"extra":{"attachment":false,"description":"Open 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":"together_ai/openai/gpt-oss-20b","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"together_ai/thinkingmachines/Inkling":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.17,"input":1,"output":4.05},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"together_ai/thinkingmachines/Inkling","knowledge":null,"last_updated":"2026-07-15","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-15","retired":false,"tags":null},"together_ai/thinkingmachines/Inkling-Small":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":0.5,"output":1.2},"deprecated":false,"extra":{"attachment":true,"description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"structured_output":false,"temperature":true},"family":null,"id":"together_ai/thinkingmachines/Inkling-Small","knowledge":null,"last_updated":"2026-07-30","lifecycle":null,"limits":{"context":524288,"output":1048576},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling Small","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-30","retired":false,"tags":null},"vertex/gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"input_audio":1,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"vertex/gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"cache_write":0.083333,"input":0.5,"input_audio":1,"output":3,"reasoning":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"vertex/gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"vertex/gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["image","text"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"vertex/gemini-3.1-flash-lite-image":{"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":0.25,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.1-flash-lite-image","knowledge":"2025-01","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":65536,"output":4096},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana 2 Lite","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"vertex/gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"vertex/gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":0.083333,"input":1.5,"input_audio":3,"output":9,"reasoning":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"vertex/gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"input_audio":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"vertex/gemini-3.5-flash-lite@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"input_audio":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.5-flash-lite@eu","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite (EU)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"vertex/gemini-3.5-flash-lite@us":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"cache_write":0.083333,"input":0.3,"input_audio":0.3,"output":2.5,"reasoning":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.5-flash-lite@us","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite (US)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"vertex/gemini-3.5-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":0.083333,"input":1.5,"input_audio":3,"output":9,"reasoning":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.5-flash@eu","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash (EU)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"vertex/gemini-3.5-flash@us":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"cache_write":0.083333,"input":1.5,"input_audio":3,"output":9,"reasoning":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.5-flash@us","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash (US)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"vertex/gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"vertex/gemini-3.6-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.6-flash@eu","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash (EU)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"vertex/gemini-3.6-flash@us":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.6-flash@us","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash (US)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"vertex/gemini-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.7-flash","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"vertex/gemini-3.7-flash@eu":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.7-flash@eu","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash (EU)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"vertex/gemini-3.7-flash@us":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":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":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-3.7-flash@us","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash (US)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"vertex/gemini-flash-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.041667,"input":0.75,"input_audio":0.75,"output":3.75,"reasoning":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-flash-latest","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"vertex/gemini-pro-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":0.375,"input":2,"input_audio":2,"output":12,"reasoning":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"vertex/gemini-pro-latest","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"xai/grok-4.20-0309-non-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.20-0309-non-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.20 (Non-Reasoning)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"xai/grok-4.20-0309-reasoning":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.20-0309-reasoning","knowledge":null,"last_updated":"2026-03-09","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.20 (Reasoning)","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-09","retired":false,"tags":null},"xai/grok-4.3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1.25,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.3","knowledge":null,"last_updated":"2026-04-17","lifecycle":null,"limits":{"context":1000000,"output":30000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-17","retired":false,"tags":null},"xai/grok-4.5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"xai/grok-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-4.6","knowledge":"2026-02-01","last_updated":"2026-08-12","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.6","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"xai/grok-build-0.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":2},"deprecated":false,"extra":{"attachment":true,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-build-0.1","knowledge":null,"last_updated":"2026-04-16","lifecycle":null,"limits":{"context":256000,"output":256000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"xai/grok-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"input":2,"output":6},"deprecated":false,"extra":{"attachment":true,"description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"xai/grok-latest","knowledge":"2026-02-01","last_updated":"2026-08-12","lifecycle":null,"limits":{"context":500000,"output":500000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Grok 4.6","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"zai/glm-4.6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"zai/glm-4.6","knowledge":"2025-04","last_updated":"2025-09-30","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.6","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"zai/glm-4.6v":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.3,"output":0.9},"deprecated":false,"extra":{"attachment":true,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"zai/glm-4.6v","knowledge":"2025-04","last_updated":"2025-12-08","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"GLM-4.6V","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-08","retired":false,"tags":null},"zai/glm-4.7":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.11,"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-4.7","knowledge":"2025-04","last_updated":"2025-12-22","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2025-12-22","retired":false,"tags":null},"zai/glm-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":false,"temperature":true},"family":null,"id":"zai/glm-5","knowledge":null,"last_updated":"2026-02-12","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"zai/glm-5-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":false,"description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5-turbo","knowledge":null,"last_updated":"2026-03-16","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5-Turbo","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"zai/glm-5.1":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5.1","knowledge":null,"last_updated":"2026-04-07","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.1","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai/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":0.26,"input":1.4,"output":4.4},"deprecated":false,"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5.2","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":1048576,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5.2","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"zai/glm-5v-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"extra":{"attachment":true,"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"zai/glm-5v-turbo","knowledge":null,"last_updated":"2026-04-01","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["image","text","video"],"output":["text"]},"model":null,"name":"GLM-5V-Turbo","pricing":null,"provider":"edenai","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null}},"name":"Eden AI","pricing_defaults":null};
+const provider = /* @__PURE__ */ createProviderCatalog(data);
+export default provider;