@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/venice.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":null,"config_schema":null,"doc":"https://docs.venice.ai","env":["VENICE_API_KEY"],"exclude_models":null,"extra":null,"id":"venice","models":{"aion-labs-aion-3-0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.9375,"input":3.75,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"aion-labs-aion-3-0","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Aion 3.0","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"aion-labs-aion-3-0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.225,"input":0.875,"output":1.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"aion-labs-aion-3-0-mini","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Aion 3.0 Mini","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"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}},"cost":{"cache_read":1.2,"cache_write":15,"input":12,"output":60},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-10","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-5","knowledge":"2025-05","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-06","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-7","knowledge":"2026-01-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-4-8-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.2,"cache_write":15,"input":12,"output":60},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8-fast","knowledge":"2026-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.8 Fast","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"claude-opus-5-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.2,"cache_write":15,"input":12,"output":60},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5-fast","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 5 Fast","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"claude-sonnet-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}},"cost":{"cache_read":0.375,"cache_write":4.69,"input":3.75,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"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}},"cost":{"cache_read":0.36,"cache_write":4.5,"input":3.6,"output":18},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"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}},"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-07-01","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-29","retired":false,"tags":null},"deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.16,"input":0.33,"output":0.48},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true},"family":null,"id":"deepseek-v3.2","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":160000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-04","retired":false,"tags":null},"deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.028,"input":0.138,"output":0.275},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0423","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.035,"input":0.175,"output":0.35},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.33,"input":1.65,"output":3.301},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"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}},"cost":{"cache_read":0.5,"cache_write":0.5,"input":2.5,"output":15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-1-pro-preview","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"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}},"cost":{"cache_read":0.155,"cache_write":0.086,"input":1.55,"output":9.45},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-5-flash","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-22","retired":false,"tags":null},"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}},"cost":{"cache_read":0.0375,"input":0.375,"output":3.125},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash-Lite","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"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}},"cost":{"cache_read":0.1875,"input":1.875,"output":9.375},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"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}},"cost":{"cache_read":0.07,"input":0.7,"output":3.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-19","retired":false,"tags":null},"gemma-4-uncensored":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1625,"output":0.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"structured_output":true},"family":null,"id":"gemma-4-uncensored","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 Uncensored","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-13","retired":false,"tags":null},"google-gemma-3-27b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.12,"output":0.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"structured_output":true},"family":null,"id":"google-gemma-3-27b-it","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google Gemma 3 27B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-11-04","retired":false,"tags":null},"google-gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"input":0.13,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google-gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Google Gemma 4 26B A4B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google-gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.09,"input":0.12,"output":0.36},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google-gemma-4-31b-it","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Google Gemma 4 31B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-03","retired":false,"tags":null},"grok-4-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.23,"input":1.42,"output":2.83},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true},"family":null,"id":"grok-4-20","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":2000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.20","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-12","retired":false,"tags":null},"grok-4-20-multi-agent":{"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}},"cost":{"cache_read":0.23,"input":1.42,"output":2.83},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true},"family":null,"id":"grok-4-20-multi-agent","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":2000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.20 Multi-Agent","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-12","retired":false,"tags":null},"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}},"cost":{"cache_read":0.23,"input":1.42,"output":2.83},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"grok-4-3","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-18","retired":false,"tags":null},"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}},"cost":{"cache_read":0.34,"input":2.27,"output":6.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-07","retired":false,"tags":null},"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}},"cost":{"cache_read":0.2,"input":1,"output":2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"grok-build-0-1","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"hermes-3-llama-3.1-405b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1.1,"output":3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"hermes","open_weights":true},"family":null,"id":"hermes-3-llama-3.1-405b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes 3 Llama 3.1 405b","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-09-25","retired":false,"tags":null},"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}},"cost":{"cache_read":0.2125,"input":1.25,"output":5.0625},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"inkling","knowledge":null,"last_updated":"2026-07-17","lifecycle":null,"limits":{"context":524288,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"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}},"cost":{"cache_read":0.22,"input":0.56,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2-5","knowledge":"2024-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"kimi-k2-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.16,"input":0.75,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2-6","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"kimi-k2-7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.16,"input":0.75,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2-7-code","knowledge":"2025-01","last_updated":"2026-06-16","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.375,"input":3.75,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-17","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"kimi-k3-fast-api":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.45,"input":4.5,"output":22.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3-fast-api","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3 Fast","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"llama-3.2-3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true},"family":null,"id":"llama-3.2-3b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2024-10-03","retired":false,"tags":null},"llama-3.3-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.7,"output":2.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true},"family":null,"id":"llama-3.3-70b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-06","retired":false,"tags":null},"mercury-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}},"cost":{"cache_read":0.03125,"input":0.3125,"output":0.9375},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true},"family":null,"id":"mercury-2","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":50000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mercury 2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-20","retired":false,"tags":null},"minimax-m25":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.27,"output":0.95},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m25","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax-m27":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.06875,"input":0.375,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m27","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.7","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax-m3-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}},"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","open_weights":true,"reasoning_options":[]},"family":null,"id":"minimax-m3-preview","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":524288,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax M3 Preview","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"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}},"cost":{"input":0.1875,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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-small-2603","knowledge":"2025-06","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"mistral-small-3-2-24b-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}},"cost":{"input":0.09375,"output":0.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"structured_output":true},"family":null,"id":"mistral-small-3-2-24b-instruct","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.2 24B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-15","retired":false,"tags":null},"nvidia-nemotron-3-nano-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nvidia-nemotron-3-nano-30b-a3b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3 Nano 30B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"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}},"cost":{"cache_read":0.1875,"input":0.625,"output":3.125},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia-nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3 Ultra","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"olafangensan-glm-4.7-flash-heretic":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.035,"input":0.07,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true},"family":null,"id":"olafangensan-glm-4.7-flash-heretic","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":24000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7 Flash Heretic","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-04","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}},"cost":{"input":3.125,"output":12.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-28","retired":false,"tags":null},"openai-gpt-4o-mini-2024-07-18":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.09375,"input":0.1875,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-4o-mini-2024-07-18","knowledge":"2023-09","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o Mini","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-28","retired":false,"tags":null},"openai-gpt-52":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.219,"input":2.19,"output":17.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-52","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-13","retired":false,"tags":null},"openai-gpt-52-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}},"cost":{"cache_read":0.219,"input":2.19,"output":17.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-52-codex","knowledge":"2025-08","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"openai-gpt-53-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}},"cost":{"cache_read":0.219,"input":2.19,"output":17.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-53-codex","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"openai-gpt-54":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.313,"input":3.13,"output":18.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-54","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai-gpt-54-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}},"cost":{"cache_read":0.09375,"input":0.9375,"output":5.625},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-54-mini","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 Mini","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-27","retired":false,"tags":null},"openai-gpt-54-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":37.5,"output":225},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-54-pro","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai-gpt-55":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.625,"input":6.25,"output":37.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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-55","knowledge":"2025-12-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai-gpt-55-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":37.5,"output":225},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-55-pro","knowledge":"2025-12-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.5 Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"openai-gpt-56-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}},"cost":{"cache_read":0.125,"cache_write":1.5625,"input":1.25,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","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-56-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-luna-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.125,"cache_write":1.5625,"input":1.25,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","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-56-luna-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-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}},"cost":{"cache_read":0.625,"cache_write":7.8125,"input":6.25,"output":37.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","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-56-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-sol-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.625,"cache_write":7.8125,"input":6.25,"output":37.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","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-56-sol-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-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}},"cost":{"cache_read":0.3125,"cache_write":3.90625,"input":3.125,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","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-56-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-terra-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3125,"cache_write":3.90625,"input":3.125,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal 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-56-terra-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.07,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-oss-120b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT OSS 120B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"qwen-3-6-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0625,"cache_write":0.78,"input":0.625,"output":3.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen-3-6-plus","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.6 Plus Uncensored","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-06","retired":false,"tags":null},"qwen-3-7-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.27,"cache_write":3.35,"input":2.7,"output":8.05},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen-3-7-max","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.7 Max","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-22","retired":false,"tags":null},"qwen-3-7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"cache_write":0.625,"input":0.5,"output":2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen-3-7-plus","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.7 Plus","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"qwen-3-8-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}},"cost":{"cache_read":0.3125,"cache_write":3.125,"input":2.5,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen-3-8-max","knowledge":null,"last_updated":"2026-07-19","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.8 Max","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-22","retired":false,"tags":null},"qwen3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.15,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true},"family":null,"id":"qwen3-235b-a22b-instruct-2507","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 235B A22B Instruct 2507","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen3-235b-a22b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.45,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"qwen3-235b-a22b-thinking-2507","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 235B A22B Thinking 2507","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen3-5-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.15625,"input":0.3125,"output":1.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-35b-a3b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 35B A3B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"qwen3-5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.75,"output":4.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-397b-a17b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 397B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"qwen3-5-9b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-9b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 3.5 9B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"qwen3-6-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.325,"output":3.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-27b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.6 27B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"qwen3-6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-35b-a3b","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 3.6 35B A3B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"qwen3-coder-480b-a35b-instruct-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.04,"input":0.35,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true},"family":null,"id":"qwen3-coder-480b-a35b-instruct-turbo","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Coder 480B Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"qwen3-next-80b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.35,"output":1.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true},"family":null,"id":"qwen3-next-80b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Next 80b","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen3-vl-235b-a22b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.21,"output":1.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","open_weights":true,"structured_output":true},"family":null,"id":"qwen3-vl-235b-a22b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-16","retired":false,"tags":null},"seed-2-1-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.125,"input":0.625,"output":3.125},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[],"structured_output":true},"family":null,"id":"seed-2-1-turbo","knowledge":null,"last_updated":"2026-07-24","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Seed 2.1 Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-28","retired":false,"tags":null},"venice-uncensored-1-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.2,"output":0.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","open_weights":true,"structured_output":true},"family":null,"id":"venice-uncensored-1-2","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Venice Uncensored 1.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"venice-uncensored-role-play":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.5,"output":2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","open_weights":true,"structured_output":true},"family":null,"id":"venice-uncensored-role-play","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Venice Role Play Uncensored","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-20","retired":false,"tags":null},"xiaomi-mimo-v2-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"input":0.14,"output":0.28},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xiaomi-mimo-v2-5","knowledge":"2024-12","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-11","retired":false,"tags":null},"z-ai-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}},"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai-glm-5-turbo","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5 Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"z-ai-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}},"cost":{"cache_read":0.3,"input":1.5,"output":5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai-glm-5v-turbo","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GLM 5V Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.08,"input":0.43,"output":1.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-4.6","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2024-04-01","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.11,"input":0.55,"output":2.65},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-4.7","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-24","retired":false,"tags":null},"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}},"cost":{"cache_read":0.01,"input":0.06,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7 Flash","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.2,"input":1,"output":3.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-5","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.286,"input":1.54,"output":4.84},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-5-1","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org-glm-5-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-5-2","knowledge":null,"last_updated":"2026-06-16","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null}},"name":"Venice AI","pricing_defaults":null,"runtime":{"auth":{"env":["VENICE_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.venice.ai/api/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://docs.venice.ai"}};
+export const data = {"alias_of":null,"base_url":null,"config_schema":null,"doc":"https://docs.venice.ai","env":["VENICE_API_KEY"],"exclude_models":null,"extra":null,"id":"venice","models":{"aion-labs-aion-3-0":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.9375,"input":3.75,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"aion-labs-aion-3-0","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Aion 3.0","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"aion-labs-aion-3-0-mini":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.225,"input":0.875,"output":1.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient model for low-latency assistance, extraction, and routine automation","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"aion-labs-aion-3-0-mini","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Aion 3.0 Mini","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-08","retired":false,"tags":null},"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}},"cost":{"cache_read":1.2,"cache_write":15,"input":12,"output":60},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"claude-fable-5","knowledge":"2026-01-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Fable 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-10","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-5","knowledge":"2025-05","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-06","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-opus-4-6","knowledge":"2025-05-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-7","knowledge":"2026-01-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8","knowledge":"2026-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-4-8-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.2,"cache_write":15,"input":12,"output":60},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-4-8-fast","knowledge":"2026-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 4.8 Fast","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"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}},"cost":{"cache_read":0.6,"cache_write":7.5,"input":6,"output":30},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"claude-opus-5-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":1.2,"cache_write":15,"input":12,"output":60},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-opus-5-fast","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Opus 5 Fast","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-23","retired":false,"tags":null},"claude-sonnet-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}},"cost":{"cache_read":0.375,"cache_write":4.69,"input":3.75,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-5","knowledge":"2025-07-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"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}},"cost":{"cache_read":0.36,"cache_write":4.5,"input":3.6,"output":18},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"claude-sonnet-4-6","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"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}},"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"claude-sonnet-5","knowledge":"2026-01-31","last_updated":"2026-07-01","lifecycle":null,"limits":{"context":1000000,"output":64000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-29","retired":false,"tags":null},"deepseek-v3.2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.16,"input":0.33,"output":0.48},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v3.2","knowledge":"2024-07","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":160000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-04","retired":false,"tags":null},"deepseek-v4-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.028,"input":0.138,"output":0.275},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash","knowledge":"2025-05","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0423","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-v4-flash-0731":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.035,"input":0.175,"output":0.35},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731","knowledge":"2025-05","last_updated":"2026-08-01","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-31","retired":false,"tags":null},"deepseek-v4-flash-0731-fast":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0875,"input":0.35,"output":0.7},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-flash-0731-fast","knowledge":"2025-05","last_updated":"2026-08-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Flash 0731 Fast","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-09","retired":false,"tags":null},"deepseek-v4-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.33,"input":1.65,"output":3.301},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro","knowledge":"2025-05","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"deepseek-v4-pro-0813":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.33,"input":1.73,"output":4.95},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"deepseek-v4-pro-0813","knowledge":null,"last_updated":"2026-08-14","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"DeepSeek V4 Pro 0813","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-14","retired":false,"tags":null},"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}},"cost":{"cache_read":0.5,"cache_write":0.5,"input":2.5,"output":15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-1-pro-preview","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"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}},"cost":{"cache_read":0.155,"cache_write":0.086,"input":1.55,"output":9.45},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-5-flash","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-22","retired":false,"tags":null},"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}},"cost":{"cache_read":0.0375,"input":0.375,"output":3.125},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash-Lite","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"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}},"cost":{"cache_read":0.1875,"input":1.875,"output":9.375},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"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}},"cost":{"cache_read":0.1875,"input":1.875,"output":9.375},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-7-flash","knowledge":"2026-03","last_updated":"2026-08-14","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-14","retired":false,"tags":null},"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}},"cost":{"cache_read":0.07,"input":0.7,"output":3.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-19","retired":false,"tags":null},"gemma-4-uncensored":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1625,"output":0.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"structured_output":true},"family":null,"id":"gemma-4-uncensored","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Gemma 4 Uncensored","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-13","retired":false,"tags":null},"google-gemma-3-27b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.12,"output":0.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"structured_output":true},"family":null,"id":"google-gemma-3-27b-it","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Google Gemma 3 27B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-11-04","retired":false,"tags":null},"google-gemma-4-26b-a4b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"input":0.13,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google-gemma-4-26b-a4b-it","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Google Gemma 4 26B A4B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-02","retired":false,"tags":null},"google-gemma-4-31b-it":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.09,"input":0.12,"output":0.36},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"google-gemma-4-31b-it","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":8192},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Google Gemma 4 31B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-03","retired":false,"tags":null},"grok-4-20":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.23,"input":1.42,"output":2.83},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true},"family":null,"id":"grok-4-20","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":2000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.20","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-12","retired":false,"tags":null},"grok-4-20-multi-agent":{"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}},"cost":{"cache_read":0.23,"input":1.42,"output":2.83},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[],"structured_output":true},"family":null,"id":"grok-4-20-multi-agent","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":2000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.20 Multi-Agent","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-12","retired":false,"tags":null},"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}},"cost":{"cache_read":0.23,"input":1.42,"output":2.83},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"grok-4-3","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.3","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-18","retired":false,"tags":null},"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}},"cost":{"cache_read":0.34,"input":2.27,"output":6.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-5","knowledge":null,"last_updated":"2026-07-08","lifecycle":null,"limits":{"context":500000,"output":32000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-07","retired":false,"tags":null},"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}},"cost":{"cache_read":0.57,"input":2.27,"output":6.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"structured_output":true,"temperature":true},"family":null,"id":"grok-4-6","knowledge":"2026-02-01","last_updated":"2026-08-12","lifecycle":null,"limits":{"context":500000,"output":200000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok 4.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-10","retired":false,"tags":null},"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}},"cost":{"cache_read":0.2,"input":1,"output":2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"grok-build-0-1","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Grok Build 0.1","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-21","retired":false,"tags":null},"hermes-3-llama-3.1-405b":{"aliases":[],"base_url":null,"capabilities":null,"cost":{"input":1.1,"output":3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"hermes","open_weights":true},"family":null,"id":"hermes-3-llama-3.1-405b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Hermes 3 Llama 3.1 405b","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-09-25","retired":false,"tags":null},"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}},"cost":{"cache_read":0.2125,"input":1.25,"output":5.0625},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"inkling","knowledge":null,"last_updated":"2026-07-17","lifecycle":null,"limits":{"context":524288,"output":65536},"modalities":{"input":["text","image","audio"],"output":["text"]},"model":null,"name":"Inkling","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"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}},"cost":{"cache_read":0.22,"input":0.56,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2-5","knowledge":"2024-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"kimi-k2-6":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.16,"input":0.75,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"kimi-k2-6","knowledge":"2025-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-20","retired":false,"tags":null},"kimi-k2-7-code":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.16,"input":0.75,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k2-7-code","knowledge":"2025-01","last_updated":"2026-06-16","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K2.7 Code","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-13","retired":false,"tags":null},"kimi-k3":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.375,"input":3.75,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3","knowledge":null,"last_updated":"2026-07-17","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-16","retired":false,"tags":null},"kimi-k3-fast-api":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.45,"input":4.5,"output":22.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":false},"family":null,"id":"kimi-k3-fast-api","knowledge":null,"last_updated":"2026-08-03","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Kimi K3 Fast","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-03","retired":false,"tags":null},"llama-3.2-3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.15,"output":0.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"temperature":true},"family":null,"id":"llama-3.2-3b","knowledge":"2023-12","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.2 3B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2024-10-03","retired":false,"tags":null},"llama-3.3-70b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.7,"output":2.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true},"family":null,"id":"llama-3.3-70b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-06","retired":false,"tags":null},"mercury-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}},"cost":{"cache_read":0.03125,"input":0.3125,"output":0.9375},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true},"family":null,"id":"mercury-2","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":50000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mercury 2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-20","retired":false,"tags":null},"minimax-m25":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.03,"input":0.27,"output":0.95},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m25","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-12","retired":false,"tags":null},"minimax-m27":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.06875,"input":0.375,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"temperature":true},"family":null,"id":"minimax-m27","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"MiniMax M2.7","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-18","retired":false,"tags":null},"minimax-m3-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}},"cost":{"cache_read":0.06,"input":0.3,"output":1.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","open_weights":true,"reasoning_options":[]},"family":null,"id":"minimax-m3-preview","knowledge":null,"last_updated":"2026-06-13","lifecycle":null,"limits":{"context":524288,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"MiniMax M3 Preview","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-12","retired":false,"tags":null},"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}},"cost":{"input":0.1875,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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-small-2603","knowledge":"2025-06","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Mistral Small 4","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-16","retired":false,"tags":null},"mistral-small-3-2-24b-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}},"cost":{"input":0.09375,"output":0.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","open_weights":true,"structured_output":true},"family":null,"id":"mistral-small-3-2-24b-instruct","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Mistral Small 3.2 24B Instruct","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-15","retired":false,"tags":null},"nvidia-nemotron-3-5-lightning-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}},"cost":{"input":0.1,"output":0.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","open_weights":true,"reasoning_options":[],"structured_output":true},"family":null,"id":"nvidia-nemotron-3-5-lightning-30b-a3b","knowledge":null,"last_updated":"2026-08-12","lifecycle":null,"limits":{"context":1000000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3.5 Lightning 30B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"nvidia-nemotron-3-nano-30b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.075,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"nvidia-nemotron-3-nano-30b-a3b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3 Nano 30B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"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}},"cost":{"cache_read":0.1875,"input":0.625,"output":3.125},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"nvidia-nemotron-3-ultra-550b-a55b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"NVIDIA Nemotron 3 Ultra","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-04","retired":false,"tags":null},"olafangensan-glm-4.7-flash-heretic":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.035,"input":0.07,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true},"family":null,"id":"olafangensan-glm-4.7-flash-heretic","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":24000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7 Flash Heretic","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-04","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}},"cost":{"input":3.125,"output":12.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-28","retired":false,"tags":null},"openai-gpt-4o-mini-2024-07-18":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.09375,"input":0.1875,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt","open_weights":false,"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-4o-mini-2024-07-18","knowledge":"2023-09","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-4o Mini","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-28","retired":false,"tags":null},"openai-gpt-52":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.219,"input":2.19,"output":17.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-52","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT-5.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-13","retired":false,"tags":null},"openai-gpt-52-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}},"cost":{"cache_read":0.219,"input":2.19,"output":17.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-52-codex","knowledge":"2025-08","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.2 Codex","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-01-15","retired":false,"tags":null},"openai-gpt-53-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}},"cost":{"cache_read":0.219,"input":2.19,"output":17.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-53-codex","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.3 Codex","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-24","retired":false,"tags":null},"openai-gpt-54":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.313,"input":3.13,"output":18.8},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-54","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai-gpt-54-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}},"cost":{"cache_read":0.09375,"input":0.9375,"output":5.625},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-54-mini","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":400000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 Mini","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-27","retired":false,"tags":null},"openai-gpt-54-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":37.5,"output":225},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-54-pro","knowledge":"2025-08-31","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.4 Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"openai-gpt-55":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.625,"input":6.25,"output":37.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"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-55","knowledge":"2025-12-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-23","retired":false,"tags":null},"openai-gpt-55-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":37.5,"output":225},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt","open_weights":false,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"structured_output":true,"temperature":false},"family":null,"id":"openai-gpt-55-pro","knowledge":"2025-12-01","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.5 Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"openai-gpt-56-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}},"cost":{"cache_read":0.02666667,"cache_write":0.33333334,"input":0.26666667,"output":1.6},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","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-56-luna","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-luna-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.125,"cache_write":1.5625,"input":1.25,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","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-56-luna-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Luna Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-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}},"cost":{"cache_read":0.625,"cache_write":7.8125,"input":6.25,"output":37.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","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-56-sol","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-sol-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.625,"cache_write":7.8125,"input":6.25,"output":37.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal work","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-56-sol-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Sol Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-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}},"cost":{"cache_read":0.3125,"cache_write":3.90625,"input":3.125,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","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-56-terra","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-56-terra-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.3125,"cache_write":3.90625,"input":3.125,"output":18.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Frontier GPT model for professional reasoning, coding, and multimodal 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-56-terra-pro","knowledge":"2026-02-16","last_updated":"2026-07-09","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GPT-5.6 Terra Pro","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-09","retired":false,"tags":null},"openai-gpt-oss-120b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.07,"output":0.3},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"openai-gpt-oss-120b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"OpenAI GPT OSS 120B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-11-06","retired":false,"tags":null},"qwen-3-6-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.0625,"cache_write":0.78,"input":0.625,"output":3.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen-3-6-plus","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.6 Plus Uncensored","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-06","retired":false,"tags":null},"qwen-3-7-max":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.27,"cache_write":3.35,"input":2.7,"output":8.05},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen-3-7-max","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.7 Max","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-05-22","retired":false,"tags":null},"qwen-3-7-plus":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.05,"cache_write":0.625,"input":0.5,"output":2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen-3-7-plus","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.7 Plus","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-02","retired":false,"tags":null},"qwen-3-8-2-4t-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}},"cost":{"cache_read":0.3125,"input":2.5,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen-3-8-2-4t-a95b","knowledge":null,"last_updated":"2026-08-13","lifecycle":null,"limits":{"context":262144,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3.8 2.4T","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-08-12","retired":false,"tags":null},"qwen-3-8-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}},"cost":{"cache_read":0.3125,"cache_write":3.125,"input":2.5,"output":7.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"qwen-3-8-max","knowledge":null,"last_updated":"2026-07-19","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.8 Max","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-22","retired":false,"tags":null},"qwen3-235b-a22b-instruct-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.15,"output":0.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true,"temperature":true},"family":null,"id":"qwen3-235b-a22b-instruct-2507","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 235B A22B Instruct 2507","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen3-235b-a22b-thinking-2507":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.45,"output":3.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true},"family":null,"id":"qwen3-235b-a22b-thinking-2507","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 235B A22B Thinking 2507","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen3-5-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.15625,"input":0.3125,"output":1.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-35b-a3b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 35B A3B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-25","retired":false,"tags":null},"qwen3-5-397b-a17b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.75,"output":4.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-397b-a17b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":32768},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.5 397B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-16","retired":false,"tags":null},"qwen3-5-9b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":0.15},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-5-9b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 3.5 9B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-05","retired":false,"tags":null},"qwen3-6-27b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.325,"output":3.25},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-27b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Qwen 3.6 27B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-24","retired":false,"tags":null},"qwen3-6-35b-a3b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.1,"output":1},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"qwen3-6-35b-a3b","knowledge":null,"last_updated":"2026-07-22","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen 3.6 35B A3B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-07-20","retired":false,"tags":null},"qwen3-coder-480b-a35b-instruct-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.04,"input":0.35,"output":1.5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","open_weights":true,"structured_output":true},"family":null,"id":"qwen3-coder-480b-a35b-instruct-turbo","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Coder 480B Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-27","retired":false,"tags":null},"qwen3-next-80b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.35,"output":1.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"structured_output":true},"family":null,"id":"qwen3-next-80b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":256000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen 3 Next 80b","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"qwen3-vl-235b-a22b":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.1,"input":0.21,"output":1.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","open_weights":true,"structured_output":true},"family":null,"id":"qwen3-vl-235b-a22b","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Qwen3 VL 235B","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-16","retired":false,"tags":null},"seed-2-1-turbo":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.125,"input":0.625,"output":3.125},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","open_weights":false,"reasoning_options":[],"structured_output":true,"temperature":true},"family":null,"id":"seed-2-1-turbo","knowledge":null,"last_updated":"2026-07-24","lifecycle":null,"limits":{"context":256000,"output":65536},"modalities":{"input":["text","image","video"],"output":["text"]},"model":null,"name":"Seed 2.1 Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-28","retired":false,"tags":null},"venice-uncensored-1-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.2,"output":0.9},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","open_weights":true,"structured_output":true},"family":null,"id":"venice-uncensored-1-2","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Venice Uncensored 1.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"venice-uncensored-role-play":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"input":0.5,"output":2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","open_weights":true,"structured_output":true},"family":null,"id":"venice-uncensored-role-play","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":4096},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Venice Role Play Uncensored","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-20","retired":false,"tags":null},"xiaomi-mimo-v2-5":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.08,"input":0.4,"output":2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"xiaomi-mimo-v2-5","knowledge":"2024-12","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":1000000,"output":65536},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"model":null,"name":"MiMo-V2.5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-11","retired":false,"tags":null},"z-ai-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}},"cost":{"cache_read":0.24,"input":1.2,"output":4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai-glm-5-turbo","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5 Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-03-15","retired":false,"tags":null},"z-ai-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}},"cost":{"cache_read":0.3,"input":1.5,"output":5},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":true,"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","open_weights":false,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"z-ai-glm-5v-turbo","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":32768},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"GLM 5V Turbo","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-01","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.08,"input":0.43,"output":1.75},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-4.6","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.6","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2024-04-01","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.11,"input":0.55,"output":2.65},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-4.7","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2025-12-24","retired":false,"tags":null},"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}},"cost":{"cache_read":0.01,"input":0.06,"output":0.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-4.7-flash","knowledge":"2025-04","last_updated":"2026-06-11","lifecycle":null,"limits":{"context":128000,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 4.7 Flash","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-01-29","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.2,"input":1,"output":3.2},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-5","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":198000,"output":32000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null},"zai-org-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}},"cost":{"cache_read":0.286,"input":1.54,"output":4.84},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-5-1","knowledge":null,"last_updated":"2026-06-11","lifecycle":null,"limits":{"context":200000,"output":80000},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.1","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-04-07","retired":false,"tags":null},"zai-org-glm-5-2":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"cost":{"cache_read":0.26,"input":1.4,"output":4.4},"deprecated":false,"execution":{"object":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"},"text":{"family":"openai_chat_compatible","path":"/chat/completions","supported":true,"wire_protocol":"openai_chat"}},"extra":{"attachment":false,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","open_weights":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"structured_output":true,"temperature":true},"family":null,"id":"zai-org-glm-5-2","knowledge":null,"last_updated":"2026-06-16","lifecycle":null,"limits":{"context":1000000,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM 5.2","pricing":null,"provider":"venice","provider_model_id":null,"release_date":"2026-06-16","retired":false,"tags":null}},"name":"Venice AI","pricing_defaults":null,"runtime":{"auth":{"env":["VENICE_API_KEY"],"headers":[],"type":"bearer"},"base_url":"https://api.venice.ai/api/v1","config_schema":null,"default_headers":{},"default_query":{},"doc_url":"https://docs.venice.ai"}};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;