Baseten

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

Quick start

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

const agent = new Agent({
  name: "baseten-agent",
  instructions: "You are a helpful assistant",
  model: "baseten/Qwen/Qwen3-Coder-480B-A35B-Instruct",
});

Environment variables

• BASETEN_API_KEY

Provider package

@ai-sdk/openai-compatible

This provider uses the OpenAI-compatible adapter.

Default base URL

https://inference.baseten.co/v1

You can override the base URL by setting BASETEN_BASE_URL.

Provider docs

• https://docs.baseten.co/development/model-apis/overview

Models

Show models (6)

• Qwen/Qwen3-Coder-480B-A35B-Instruct
• deepseek-ai/DeepSeek-V3.2
• moonshotai/Kimi-K2-Instruct-0905
• moonshotai/Kimi-K2-Thinking
• zai-org/GLM-4.6
• zai-org/GLM-4.7