MiniMax · Single modalityReleased 2025-10-27

minimax-m2

minimax/minimax-m2 id

MiniMax-M2 redefines efficiency for agents. It is a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence.

ReasoningTool use
Type
Use minimax-m2
# Drop-in OpenAI-compatible client
$ import { generateText } from 'ai'
$
$ const { text } = await generateText({
$ model: 'minimax/minimax-m2',
$ baseURL: 'https://synapse.garden/api/v1',
$ apiKey: process.env.MG_KEY,
$ prompt: 'Why is the sky blue?',
$ })
205K
CONTEXT WINDOW
205K
MAX OUTPUT
$0.330/M
INPUT · PER M
$1.32/M
OUTPUT · PER M
PRICING

List prices, every modality.

RatePer million tokens · USD
Input$0.330/M
Output$1.32/M
Cache read$0.033/M
Cache write$0.413/M
Honest list pricesHow we calculate prices
MORE FROM MINIMAX

Other MiniMax models

See all 7
FAQ · MINIMAX-M2

Frequently asked

01 / 04

How do I call minimax-m2 from my code?

Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘minimax/minimax-m2 and supply your Synapse Garden API key. No code changes beyond the base URL.

02 / 04

How much does minimax-m2 cost?

Input: $0.330/M per million tokens. Output: $1.32/M per million tokens. The free tier includes a million tokens every month at no cost.

03 / 04

What's the context window for minimax-m2?

minimax-m2 supports a context window of 205K tokens, with a maximum output of 205K tokens.

04 / 04

Do I need a separate Anthropic or OpenAI account?

No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.

READY

Try minimax-m2 in three minutes.

Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.