Skip to main content
Providers

Venice AI

Use venice/<model> with VoltAgent's model router.

Quick start​

import { Agent } from "@voltagent/core";

const agent = new Agent({
  name: "venice-agent",
  instructions: "You are a helpful assistant",
  model: "venice/claude-opus-45",
});

Environment variables​

  • VENICE_API_KEY

Provider package​

@ai-sdk/openai-compatible

This provider uses the OpenAI-compatible adapter.

Default base URL​

https://api.venice.ai/api/v1

You can override the base URL by setting VENICE_BASE_URL.

Provider docs​

Models​

Show models (25)
  • claude-opus-45
  • claude-sonnet-45
  • deepseek-v3.2
  • gemini-3-flash-preview
  • gemini-3-pro-preview
  • google-gemma-3-27b-it
  • grok-41-fast
  • grok-code-fast-1
  • hermes-3-llama-3.1-405b
  • kimi-k2-thinking
  • llama-3.2-3b
  • llama-3.3-70b
  • minimax-m21
  • mistral-31-24b
  • openai-gpt-52
  • openai-gpt-52-codex
  • openai-gpt-oss-120b
  • qwen3-235b-a22b-instruct-2507
  • qwen3-235b-a22b-thinking-2507
  • qwen3-4b
  • qwen3-coder-480b-a35b-instruct
  • qwen3-next-80b
  • venice-uncensored
  • zai-org-glm-4.6v
  • zai-org-glm-4.7

Table of Contents