MiniMax M2

MiniMaxOpen-weight

197K context · — params · —

minimax/minimax-m2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Official Path Verified MiniMax International API Intl card

Cheapest blended: ¥0.4413 / 1M tokens on MiniMaxGet custom quote

Reachability & verification

Live reachability

Probing…

Target (MiniMax): https://api.minimax.io/v1

Overseas reference latency (est.)

Singapore 170 ms London 200 ms

Live reachability probe

Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.

Official Path Verified by ModelHub

Pricing across providers

Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.

Provider	Input /1M	Output /1M	Blended	Ctx	p50 latency	API	Verified
MiniMaxminimax-m2	¥0.255	¥1	¥0.4413	197K	—	OAI	119d ago

Works with

CursorClineAiderContinueOpenCodeOpen WebUI

Any OpenAI-compatible client works — point the base URL at the provider endpoint.

Capabilities

Code samplesExample usingMiniMax— the cheapest hosting for this model as of last verification. Swapbase_urlandmodelto use a different provider from the matrix above.PythoncURLNode.jsCopyfrom openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.minimax.io/v1", ) response = client.chat.completions.create( model="minimax-m2", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)code

Code samples

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.minimax.io/v1",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="minimax-m2",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

cURL

curl https://api.minimax.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.minimax.io/v1",
  apiKey: "YOUR_API_KEY",
});

const resp = await client.chat.completions.create({
  model: "minimax-m2",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Technical specs

Context

197K

Max output

197K

Parameters

—

Release

—

Training cutoff

—

License

—

Hugging Face

Similar models

MiniMax M1

MiniMax · 1M ctx · Open weight

MiniMax M2-her

MiniMax · 66K ctx · Open weight

MiniMax M2.1

MiniMax · 197K ctx · Open weight

MiniMax M2.5

MiniMax · 197K ctx · Open weight

MiniMax M2.5

MiniMax · — ctx

MiniMax M2.7

MiniMax · 197K ctx · Open weight

Frequently asked questions

How much does MiniMax M2 cost?

The cheapest tracked blended price is ¥0.4413 per 1M tokens on MiniMax. See the pricing matrix above for input/output splits per provider.

Can I use MiniMax M2 from outside China?

Availability depends on the hosting provider. Use our Path Planner on the MiniMax page to map a verified official-vs-brokered access path, including payment and KYC constraints.

Is MiniMax M2 open source?

Yes — MiniMax M2 is open-weight under the — license. You can self-host it or use any listed inference provider.

Is MiniMax M2 OpenAI-compatible?

Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.

What is the maximum context window?

MiniMax M2 supports up to 197K tokens of context with a maximum output of 197K tokens.

Need verified access to MiniMax M2?

We broker vetted intros to MiniMax — payment, KYC and endpoint verification handled.

Request a brokerage intro