MiniMax·MiniMax family

MiniMax M3

proprietaryReleased Jun 2026

MiniMax's frontier open-weight model with 1M-token context window, native multimodality (text, image, video), and strong coding capabilities. Built on MiniMax Sparse Attention (MSA) architecture, achieving 59% on SWE-Bench Pro with significantly improved efficiency at long context.

Capabilities

chatcompletionfunction-callingcode-generationreasoningvision

Modalities

textimagevideocode

Context Window

1.0M tokens

Providers

available

Available from 3 providers

Cheapest

OpenRouter

$1.50/1M tokens

MiniMax, OpenRouter, SiliconFlow

Providers (3)

Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.

Provider	Pricing (per 1M)	Rate Limits	Regions	Health	Latency
OpenRouter	In: $0.30Out: $1.20	20 RPM / 1.0M TPM	us-east-1	Healthy	0ms
MiniMax	In: $0.60Out: $2.40	300 RPM / 1.0M TPM	us-east-1global	Healthy	0ms
SiliconFlow	In: $0.60Out: $2.40	300 RPM / 1.0M TPM	ap-east-1us-west-2global	Healthy	0ms

Quick Start

Use this model via OpenRouter with an OpenAI-compatible SDK.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "minimax/minimax-m3",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

console.log(response.choices[0].message.content);

Using OpenRouter API • OpenAI-compatible SDK