Mistral Small 4 Is Now Available in Puter.js

Puter.js now supports Mistral Small 4, the latest open-source model from Mistral AI that unifies instruction-following, reasoning, multimodal understanding, and agentic coding into a single deployment. Add it to your application for free without any API keys.

What is Mistral Small 4?

Mistral Small 4 is a 119B-parameter Mixture-of-Experts model with 128 experts and only 6B active parameters per token, released under the Apache 2.0 license. It consolidates the strengths of Magistral (reasoning), Devstral (coding), and Mistral Small (instruct) into one model. With a 256K context window, native image understanding, and configurable reasoning effort, it delivers 40% lower latency and 3x higher throughput compared to Mistral Small 3.

Examples

Basic Chat

puter.ai.chat("Explain the concept of quantum computing in simple terms",
    { model: "mistralai/mistral-small-2603" }
)

Image Analysis

puter.ai.chat("What do you see in this image?",
    "https://assets.puter.site/doge.jpeg",
    { model: "mistralai/mistral-small-2603" }
)

Reasoning

puter.ai.chat("A farmer has 17 sheep. All but 9 run away. How many sheep does the farmer have left? Explain your reasoning step by step.",
    { model: "mistralai/mistral-small-2603" }
)

Get Started Now

Just add one library to your project:

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

Or add one script tag to your HTML:

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

No API keys or infrastructure setup needed. Start building with Mistral Small 4 immediately.

Learn more:

• Free, Unlimited Mistral API
• Puter.js AI Documentation