MiniMax: MiniMax M2-her
minimax/minimax-m2-her
Try MiniMax M2-her for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "minimax/minimax-m2-her"
}).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-her"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. It stays consistent in tone and personality across conversations and supports rich message roles to learn from example dialogue. This makes it well-suited for storytelling, AI companions, and conversational experiences where natural flow matters.
Context Window 66K
tokens
Max Output 2K
tokens
Input Cost $0.3
per million tokens
Output Cost $1.2
per million tokens
Release Date Jan 23, 2026
Output Speed 57
tokens / sec
Latency 1.76s
time to first token
Try MiniMax M2-her for free
Try MiniMax M2-her instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How MiniMax M2-her performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 77.7% |
| Humanity's Last Exam Cross-domain reasoning | 13.7% |
| LiveCodeBench Recent coding problems | 82.6% |
| AIME 2025 Advanced math exam | 78.3% |
| IFBench Instruction following | 72.3% |
| LCR Long-context reasoning | 64.3% |
| 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 M3.1 Flash
MiniMax M3.1 Flash is a multimodal coding model from MiniMax, released on October 19, 2026. MiniMax describes it as a frontier multimodal coding model with a 1M-token context window and tunable thinking depth, built for agentic reasoning, tool use, coding, and structured tasks. It accepts text, image, and video input and returns text. Thinking is always on, with five effort levels (low, medium, high, xhigh, max) where max is the default. Lowering the effort level reduces latency, and requests that disable thinking return an error. MiniMax positions it for everyday development work such as bug fixes, small features, and regression testing. MiniMax reports 73.7% on DeepSWE v1.1 and 61.7 on OSWorld V2. It suits API developers building coding agents and tool-calling workflows that need long context and image or video input.
ChatMiniMax 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.
Frequently Asked Questions
You can access MiniMax M2-her 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.
MiniMax M2-her is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
MiniMax M2-her is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.3 |
| Output | $1.2 |
MiniMax M2-her was created by MiniMax and released on Jan 23, 2026.
MiniMax M2-her supports a context window of 66K tokens. For reference, that is roughly equivalent to 131 pages of text.
MiniMax M2-her can generate up to 2K tokens in a single response.
Yes — the MiniMax M2-her 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.
Add MiniMax M2-her to your app for free
Developers can integrate MiniMax M2-her for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.