MiniMax

MiniMax API

Add AI to your application with MiniMax.
Access MiniMax AI models through a single API with Puter.js.

Get Started View Tutorial

AI Chat API

Massive Context Windows

Up to 1,000,000 tokens in context, letting you process entire books, large codebases, or lengthy conversation histories without chunking.

Cost-Effective Performance

Pricing is roughly 8% of comparable high-end models, with reduced token consumption lowering operational costs by up to 30%.

Optimized for Coding

Strong code understanding, multi-turn dialogue, and reasoning. Excels at code optimization, review, and instruction following across multiple languages.

Fast Inference Speed

Inference throughput around 100 tokens per second, fast enough for real-time applications like chat interfaces and interactive coding assistants.

Strong General Reasoning

High general intelligence across math, science, open-domain Q&A, and logical reasoning, ranking #1 among open-source models globally.

Excellent Multilingual Support

Exceptional multilingual capabilities with strong performance in languages like Chinese, English, and more—ideal for global applications.

MiniMax Models

Access all MiniMax models through a single API.

MiniMax M2.1

Latest flagship model with advanced reasoning and coding capabilities.

minimax/minimax-m2.1

MiniMax M2

Previous generation model with strong general performance.

minimax/minimax-m2

MiniMax M1

Optimized for long context processing up to 1M tokens.

minimax/minimax-m1

MiniMax 01

First generation model for general-purpose AI tasks.

minimax/minimax-01

Add AI Chat in Seconds

Add MiniMax AI to your app with just a few lines of code.
No API keys, no backend, no configuration required.

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum entanglement in simple terms", {
            model: "minimax/minimax-m2.1"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →