Mistral AI: Magistral Small
mistralai/magistral-small-latest
Access Magistral Small from Mistral AI using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "mistralai/magistral-small-latest"
}).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/magistral-small-latest"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="mistralai/magistral-small-latest",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "mistralai/magistral-small-latest",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Magistral Small is Mistral's small open-source reasoning model, built on Mistral Small 3.2 with added chain-of-thought training via supervised fine-tuning from Magistral Medium traces and reinforcement learning. It has 24B parameters and is released under Apache 2.0.
The "latest" alias currently resolves to the 1.2 (September 2025) generation. Compared to 1.1, Mistral reports about 15% gains on math and coding benchmarks including AIME 2024/2025 and LiveCodeBench, along with better tool use for web search and code interpreter, clearer non-English responses, and reduced repetition. It scores 70.7% on AIME2024 and 70.88% on LiveCodeBench v5.
It reasons step by step in English, French, Spanish, German, Italian, Arabic, Russian, and Chinese, and supports function calling and structured outputs. It suits math, coding, and logic tasks that need traceable reasoning, and can run locally on a single RTX 4090 GPU or a 32GB RAM Mac when quantized.
Context Window 131K
tokens
Max Output 131K
tokens
Input Cost $0.5
per million tokens
Output Cost $1.5
per million tokens
Input text
modalities
Tool Use Yes
Knowledge Cutoff Jun 2025
Release Date Sep 1, 2025
Model Playground
Try Magistral Small instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
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
You can access Magistral Small 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.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Magistral Small to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.5 |
| Output | $1.5 |
Magistral Small was created by Mistral AI and released on Sep 1, 2025.
Magistral Small supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
Magistral Small can generate up to 131K tokens in a single response.
Magistral Small has a knowledge cutoff date of Jun 2025. This means the model was trained on data available up to that date.
Magistral Small accepts the following input types: text. It produces: text.
Yes, Magistral Small supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Magistral Small 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 Magistral Small to your app without worrying about API keys or setup.
Read the Docs View Tutorials