Mistral AI: Mistral Small 3.2 (24B Instruct 2506)
This model is no longer available.Add AI to your application with Puter.js.
Explore Other ModelsModel Card
Mistral Small 3.2 (24B Instruct 2506) is a 24-billion-parameter multimodal model from Mistral AI, accepting both text and image input and released under the Apache 2.0 license in June 2025.
It is an instruction-following update to Mistral Small 3.1, with the same architecture. Mistral AI reports internal instruction-following accuracy rising from 82.75% to 84.78%, infinite/repetitive generations dropping from 2.11% to 1.29%, and gains on WildBench v2 (55.6% to 65.33%) and Arena Hard v2 (19.56% to 43.1%). It also improves on coding benchmarks (HumanEval Plus 88.99% to 92.90%) and supports function/tool calling with an updated template.
With a 128,000-token context window and open licensing, it suits developers needing document QA, chart/image understanding, structured output, and tool-calling agents.
Context Window 128K
tokens
Max Output 128K
tokens
Input Cost $0.08
per million tokens
Output Cost $0.2
per million tokens
Input text, image
modalities
Tool Use Yes
Release Date Jun 20, 2025
Code Example
Add AI to your app with the Puter.js AI API, no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").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").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From Mistral AI
Find other Mistral AI models →
Mistral 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.
ChatMistral Small 4
Mistral Small 4 is a 119B-parameter open-source Mixture-of-Experts model (6B active per token) released under Apache 2.0, unifying instruction-following, reasoning, multimodal (text + image), and agentic coding into a single deployment. It features 128 experts, a 256k context window, and configurable reasoning effort that lets developers toggle between fast responses and deep step-by-step reasoning per request. Compared to its predecessor Mistral Small 3, it delivers 40% lower latency and 3x higher throughput while matching or surpassing GPT-OSS 120B on key benchmarks.
Frequently Asked Questions
Mistral Small 3.2 (24B Instruct 2506) is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.08 |
| Output | $0.2 |
Mistral Small 3.2 (24B Instruct 2506) was created by Mistral AI and released on Jun 20, 2025.
Mistral Small 3.2 (24B Instruct 2506) supports a context window of 128K tokens. For reference, that is roughly equivalent to 256 pages of text.
Mistral Small 3.2 (24B Instruct 2506) can generate up to 128K tokens in a single response.
Mistral Small 3.2 (24B Instruct 2506) accepts the following input types: text, image. It produces: text.
Yes, Mistral Small 3.2 (24B Instruct 2506) supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Mistral Small 3.2 (24B Instruct 2506) 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.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials