MiniMax: MiniMax M2
minimax/minimax-m2
Access MiniMax M2 from MiniMax using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "minimax/minimax-m2"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "minimax/minimax-m2"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="minimax/minimax-m2",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "minimax/minimax-m2",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
MiniMax-M2 is a compact MoE model (230B total, 10B active parameters) optimized for coding and agentic workflows with a 128K context window. It ranks #1 among open-source models for tool use and agent tasks, delivering elite performance in multi-step development workflows at 8% the cost of comparable models.
Context Window 205K
tokens
Max Output 197K
tokens
Input Cost $0.3
per million tokens
Output Cost $1.2
per million tokens
Input text
modalities
Tool Use Yes
Release Date Sep 1, 2025
Output Speed 115
tokens / sec
Latency 1.04s
time to first token
Model Playground
Try MiniMax M2 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How MiniMax M2 performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 77.7% |
| Humanity's Last Exam Cross-domain reasoning | 12.5% |
| LiveCodeBench Recent coding problems | 82.6% |
| SciCode Scientific programming | 36.1% |
| AIME 2025 Advanced math exam | 78.3% |
| IFBench Instruction following | 72.3% |
| LCR Long-context reasoning | 61.0% |
| Terminal-Bench Hard Agentic terminal tasks | 25.8% |
| τ²-Bench Tool use / agents | 86.8% |
Scores sourced from Artificial Analysis.
Find other MiniMax models →
MiniMax M3
MiniMax M3 is a frontier-level multimodal language model built for long-horizon coding, agentic workflows, and complex reasoning. It introduces MiniMax Sparse Attention (MSA), which delivers 15x faster decoding and 9x faster prefill at 1M-token context compared to the prior generation. M3 scores 59.0% on SWE-Bench Pro — surpassing GPT-5.5 and Gemini 3.1 Pro — and achieves the highest score on Claw-Eval (74.5%) for autonomous agent tasks. It accepts text, image, and video inputs natively and supports tool calling through standard MCP scaffolding. Ideal for developers building coding agents, long-document pipelines, and multi-step automation that require sustained, multi-hour autonomous execution.
ChatMiniMax M2.7
MiniMax M2.7 is a proprietary reasoning LLM from Chinese AI startup MiniMax, released on March 18, 2026, notable for being one of the first commercial models to actively participate in its own training through autonomous self-evolution loops. It excels at agentic coding workflows with a 56.2% score on SWE-Pro and strong performance in office productivity tasks, scoring the highest ELO (1495) on GDPval-AA among open-source-tier models. It targets developers building complex agent systems and automated workflows.
ChatMiniMax M2.7 Highspeed
MiniMax M2.7 Highspeed is a high-throughput, inference-optimized variant of MiniMax M2.7, delivering approximately 100 tokens per second — roughly 66% faster than the standard version. It shares the same model weights and MoE architecture as M2.7, so output quality and reasoning capability are identical; the speed advantage comes entirely from inference-layer routing and batching optimizations. It supports text and image inputs with a 204K context window and features automatic prompt caching and parallel tool calling. Best suited for live coding assistants, autonomous agent pipelines, and interactive workflows where low latency and high throughput matter.
Frequently Asked Questions
You can access MiniMax M2 by MiniMax through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add MiniMax M2 to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.3 |
| Output | $1.2 |
MiniMax M2 was created by MiniMax and released on Sep 1, 2025.
MiniMax M2 supports a context window of 205K tokens. For reference, that is roughly equivalent to 410 pages of text.
MiniMax M2 can generate up to 197K tokens in a single response.
MiniMax M2 accepts the following input types: text. It produces: text.
Yes, MiniMax M2 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
MiniMax M2 scores 36.1 on the Artificial Analysis Intelligence Index, outperforming 78% of tracked models. On coding, it scores 29.2 (outperforms 67% of models). On math, it scores 78.3 (outperforms 72% of models).
Yes — the MiniMax M2 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add MiniMax M2 to your app without worrying about API keys or setup.
Read the Docs View Tutorials