Xiaomi MiMo v2 Flash Is Now Available in Puter.js

Puter.js now supports MiMo v2 Flash, Xiaomi's latest open-source reasoning model.

What is Xiaomi MiMo v2 Flash?

MiMo v2 Flash is a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, featuring a 256K context window. It ranks #1 among open-source models on SWE-Bench Verified with a score of 73.4%, excelling at reasoning, coding, and agentic scenarios.

On the AIME 2025 benchmark, MiMo v2 Flash achieved 94.1%, approaching the performance of proprietary models like GPT-5 High. Released under the MIT license, it offers high-speed inference at up to 150 tokens per second.

Examples

Code Generation

puter.ai.chat("Write a function that implements binary search with error handling", {
    model: "xiaomi/mimo-v2-flash"
})

Complex Reasoning

puter.ai.chat("If a train travels 120km in 2 hours, then speeds up by 50% for the next 3 hours, what's the total distance covered?",
    { model: "xiaomi/mimo-v2-flash", stream: true }
)

Streaming Response

const response = await puter.ai.chat(
    "Explain how garbage collection works in JavaScript",
    { model: "xiaomi/mimo-v2-flash", stream: true }
);

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

Get Started Now

Just add one script tag to your HTML:

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

No API keys required. Start building with MiMo v2 Flash immediately.

Learn more:

• Free, Unlimited Xiaomi MiMo API
• Puter.js AI Documentation