Free, Unlimited Xiaomi MiMo API

Reynaldi Chernando

Updated: September 23, 2026

On this page

In this tutorial, you will learn how to add Xiaomi MiMo models into your application for free using Puter.js. The MiMo family includes MiMo-V2.6-Pro, MiMo-V2.6-Pro-UltraSpeed, MiMo-V2.6-Flash, MiMo-V2.5, and MiMo-V2.5-Pro.

Puter.js uses the User-Pays model, where users of your application cover their own AI costs. This means you as a developer don't pay anything for your users' usage, making your app practically free to run. You can scale to unlimited users and pay nothing for the AI or server usage.

Getting Started

To use Puter.js, import our npm module in your project:

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

Or alternatively, add our script via CDN if you are working directly with HTML, simply add it to the <head> or <body> section of your code:

<script src="https://js.puter.com/v2/"></script>

That's it, you're ready to start integrating Xiaomi MiMo into your application.

Example 1: Code Generation

MiMo-V2.6-Flash is the cost-efficient model in the MiMo-V2.6 series, suited to everyday coding tasks where you want quick, inexpensive responses.

puter.ai.chat(
    "Write a TypeScript function that implements a rate limiter using the sliding window algorithm. Include type definitions and comments.",
    { model: "xiaomi/mimo-v2.6-flash" }
)
.then(response => {
    puter.print(response);
});

Full code example:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat(
            "Write a TypeScript function that implements a rate limiter using the sliding window algorithm. Include type definitions and comments.",
            { model: "xiaomi/mimo-v2.6-flash" }
        )
        .then(response => {
            puter.print(response);
        });
    </script>
</body>
</html>

Example 2: Agentic Reasoning with MiMo-V2.6-Pro

MiMo-V2.6-Pro is Xiaomi's flagship model, built for complex software engineering and long-horizon agentic workflows. The example below streams both its reasoning and its final answer.

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        async function streamResponse() {
            const response = await puter.ai.chat(
                `You are a senior backend engineer. I have a REST API with the following endpoints:
                - POST /users (create user)
                - GET /users/:id (get user)
                - PUT /users/:id (update user)
                - DELETE /users/:id (delete user)

                Design a comprehensive migration plan to convert this to GraphQL, including:
                1. Schema definitions with types, queries, and mutations
                2. A phased rollout strategy that maintains backward compatibility
                3. Resolver implementation patterns with DataLoader for N+1 prevention
                4. Testing and monitoring approach for each phase`,
                { model: "xiaomi/mimo-v2.6-pro", stream: true }
            );

            for await (const part of response) {
                if (part?.reasoning) puter.print(part?.reasoning);
                else puter.print(part?.text);
            }
        }

        streamResponse();
    </script>
</body>
</html>

Example 3: Image Analysis with MiMo-V2.6-Flash

MiMo-V2.6-Flash accepts text, image, video, and audio input in a single model, so you can pass an image URL alongside your prompt.

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <img src="https://assets.puter.site/doge.jpeg" id="image">
    <script>
        puter.ai.chat(
            "What do you see in this image? Describe it in detail.",
            "https://assets.puter.site/doge.jpeg",
            { model: 'xiaomi/mimo-v2.6-flash' }
        ).then(response => {
            puter.print(response);
        });
    </script>
</body>
</html>

Example 4: Low-Latency Chat with MiMo-V2.6-Pro-UltraSpeed

MiMo-V2.6-Pro-UltraSpeed runs the same model as MiMo-V2.6-Pro on a serving path tuned for output speed. Use it for interactive chat where response time matters more than cost per token.

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        async function fastChat() {
            const response = await puter.ai.chat(
                "Explain the difference between optimistic and pessimistic locking in databases in a few sentences.",
                { model: "xiaomi/mimo-v2.6-pro-ultraspeed", stream: true }
            );

            for await (const part of response) {
                puter.print(part?.text);
            }
        }

        fastChat();
    </script>
</body>
</html>

List of Xiaomi MiMo models

You can use the following Xiaomi MiMo models with Puter.js:

xiaomi/mimo-v2.6-pro-ultraspeed
xiaomi/mimo-v2.6-pro
xiaomi/mimo-v2.6-flash
xiaomi/mimo-v2.5
xiaomi/mimo-v2.5-pro

Conclusion

Using Puter.js, you can gain access to Xiaomi MiMo models without having to set up the AI server yourself. And thanks to the User-Pays model, your users cover their own AI usage, not you as the developer. This means you can build powerful applications without worrying about AI usage costs.

You can find all AI features supported by Puter.js in the documentation.

Ship a Full-Stack App with One Prompt

Give this to your AI Build an AI chat app using Puter.js

Try in

Coding manually? see the guide