Mistral AI: Mistral Small 3.2
mistralai/mistral-small-3.2-24b-instruct
Try Mistral Small 3.2 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: "mistralai/mistral-small-3.2-24b-instruct"
}).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: "mistralai/mistral-small-3.2-24b-instruct"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Mistral Small 3.2 improves on 3.1 with better instruction following (84.78% vs 82.75%), reduced infinite generations (1.29% vs 2.11%), and more robust function calling. It maintains the 24B/256K context architecture under Apache 2.0.
Context Window 256K
tokens
Max Output 16K
tokens
Input Cost $0.09
per million tokens
Output Cost $0.25
per million tokens
Input image, text
modalities
Tool Use Yes
Release Date Jun 20, 2025
Try Mistral Small 3.2 for free
Try Mistral Small 3.2 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Mistral Small 3.2 performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 50.5% |
| Humanity's Last Exam Cross-domain reasoning | 4.3% |
| LiveCodeBench Recent coding problems | 27.5% |
| SciCode Scientific programming | 28.6% |
| MATH-500 Competition math | 88.3% |
| AIME 2024 Advanced math exam | 32.3% |
| AIME 2025 Advanced math exam | 27.0% |
| IFBench Instruction following | 33.5% |
| LCR Long-context reasoning | 20.3% |
| Terminal-Bench Hard Agentic terminal tasks | 6.8% |
| τ²-Bench Tool use / agents | 29.5% |
Scores sourced from Artificial Analysis.
Find other Mistral AI models →
Mistral Large 4
Mistral Large 4 is a multimodal sparse mixture-of-experts model from Mistral AI with 1 trillion total parameters and 49 billion active. It accepts text and image input and produces text output, and it supports tool calling and structured responses through the API. Mistral positions it for coding, cybersecurity, finance, manufacturing, and visual grounding. In Mistral's preview results it scores 62% on DeepSWE v1.1, 67% on FinWorkBench, and 73% on DIOR-RSVG, and it solves 93% of the 40 Cybench exercises. It is suited to developers building coding agents, security analysis tools, and enterprise workflows that need long context (1M tokens) and image understanding. Open weights are planned for release after the API preview.
ChatMistral Medium 3.5
Mistral Medium 3.5 is a dense 128-billion-parameter multimodal model from Mistral AI that unifies instruction-following, reasoning, and coding into a single set of weights. It features a 256k-token context window, native function calling, structured JSON output, and vision capabilities via a custom-trained encoder that handles variable image sizes. A per-request reasoning_effort parameter lets you toggle between fast responses and deeper chain-of-thought processing, making the same model suitable for quick chat replies and complex agentic workflows. On benchmarks, it scores 77.6% on SWE-Bench Verified and 91.4% on τ³-Telecom. It replaces Mistral's previous Medium 3.1, Magistral, and Devstral 2 models. Priced at $1.50 per million input tokens and $7.50 per million output tokens, it's a strong fit for developers building tool-calling agents, long-horizon coding tasks, and multi-step automation pipelines.
ChatMistral Medium 3.5
Mistral Medium 3.5 is a dense 128-billion-parameter multimodal model from Mistral AI that unifies instruction-following, reasoning, and coding into a single set of weights. This entry is Mistral's own dated direct-integration id for the same release available as mistralai/mistral-medium-3-5 through OpenRouter. It features a 256k-token context window, native function calling, structured JSON output, and vision capabilities via a custom-trained encoder that handles variable image sizes. A per-request reasoning_effort parameter lets you toggle between fast responses and deeper chain-of-thought processing, making the same model suitable for quick chat replies and complex agentic workflows. On benchmarks, it scores 77.6% on SWE-Bench Verified and 91.4% on τ³-Telecom. It replaces Mistral's previous Medium 3.1, Magistral, and Devstral 2 models. Priced at $1.50 per million input tokens and $7.50 per million output tokens, it's a strong fit for developers building tool-calling agents, long-horizon coding tasks, and multi-step automation pipelines.
Frequently Asked Questions
You can access Mistral Small 3.2 by Mistral AI 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.
Mistral Small 3.2 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.
Mistral Small 3.2 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 | $0.09 |
| Output | $0.25 |
Mistral Small 3.2 was created by Mistral AI and released on Jun 20, 2025.
Mistral Small 3.2 supports a context window of 256K tokens. For reference, that is roughly equivalent to 512 pages of text.
Mistral Small 3.2 can generate up to 16K tokens in a single response.
Mistral Small 3.2 accepts the following input types: image, text. It produces: text.
Yes, Mistral Small 3.2 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Mistral Small 3.2 scores 7.0 on the Artificial Analysis Intelligence Index, outperforming 22% of tracked models. On coding, it scores 12.5 (outperforms 12% of models). On math, it scores 27.0 (outperforms 28% of models).
Yes — the Mistral Small 3.2 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 Mistral Small 3.2 to your app for free
Developers can integrate Mistral Small 3.2 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.