Skip to main content
Providers

MiniMax

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

MiniMax provides an OpenAI-compatible API at https://api.minimax.io/v1. For users in China, use the minimax-cn provider which routes to https://api.minimaxi.com/v1.

Quick start​

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

const agent = new Agent({
  name: "minimax-agent",
  instructions: "You are a helpful assistant",
  model: "minimax/MiniMax-M3",
});

Environment variables​

  • MINIMAX_API_KEY

Provider package​

@ai-sdk/openai-compatible

Default base URL​

https://api.minimax.io/v1

You can override the base URL by setting MINIMAX_BASE_URL.

Provider docs​

Pricing​

ModelInputOutputCache readCache write
MiniMax-M3$0.60 / 1M tokens$2.40 / 1M tokens$0.12 / 1M tokensNot listed

Models​

ModelContextDescription
MiniMax-M31M tokensLatest flagship model
MiniMax-M2.71M tokensPrevious generation
MiniMax-M2.7-highspeed1M tokensOptimized for speed
MiniMax-M2.51M tokensPrevious generation
MiniMax-M2.5-highspeed204K tokensFast inference
MiniMax-M2.11M tokensLegacy
MiniMax-M21M tokensLegacy

Table of Contents