Mistral AI

Mistral AI: Magistral Medium 1.2

mistralai/magistral-medium-2509

Access Magistral Medium 1.2 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-medium-2509"
}).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-medium-2509"
        }).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-medium-2509",
    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-medium-2509",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Magistral Medium is Mistral's enterprise reasoning model with chain-of-thought capabilities, scoring 73.6% on AIME2024 (90% with majority voting). It excels in multilingual step-by-step reasoning for legal, financial, and scientific applications.

Context Window 131K

tokens

Max Output 131K

tokens

Input Cost $2

per million tokens

Output Cost $5

per million tokens

Input text

modalities

Tool Use Yes

 

Knowledge Cutoff Jun 2025

 

Release Date Mar 17, 2025

 

Output Speed 99

tokens / sec

Latency 0.44s

time to first token

Model Playground

Try Magistral Medium 1.2 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat mistralai/magistral-medium-2509
Mistral AI
Chat with Magistral Medium 1.2
Powered by Puter.js

Benchmarks

How Magistral Medium 1.2 performs on standard evaluations.

Artificial Analysis
Intelligence Index
27.1
Better than 69% of tracked models
Artificial Analysis
Coding Index
21.7
Better than 58% of tracked models
Artificial Analysis
Math Index
82.0
Better than 77% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
73.9%
Humanity's Last Exam Cross-domain reasoning
9.6%
LiveCodeBench Recent coding problems
75.0%
SciCode Scientific programming
39.2%
AIME 2025 Advanced math exam
82.0%
IFBench Instruction following
43.0%
LCR Long-context reasoning
51.3%
Terminal-Bench Hard Agentic terminal tasks
12.9%
τ²-Bench Tool use / agents
52.0%

Scores sourced from Artificial Analysis.

Frequently Asked Questions

How do I use Magistral Medium 1.2?

You can access Magistral Medium 1.2 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.

Is Magistral Medium 1.2 free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Magistral Medium 1.2 to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Magistral Medium 1.2?
Pricing for Magistral Medium 1.2 is based on the number of input and output tokens used per request.
Price per 1M tokens
Input$2
Output$5
Who created Magistral Medium 1.2?

Magistral Medium 1.2 was created by Mistral AI and released on Mar 17, 2025.

What is the context window of Magistral Medium 1.2?

Magistral Medium 1.2 supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of Magistral Medium 1.2?

Magistral Medium 1.2 can generate up to 131K tokens in a single response.

What is the knowledge cutoff of Magistral Medium 1.2?

Magistral Medium 1.2 has a knowledge cutoff date of Jun 2025. This means the model was trained on data available up to that date.

What types of input can Magistral Medium 1.2 process?

Magistral Medium 1.2 accepts the following input types: text. It produces: text.

Does Magistral Medium 1.2 support tool use (function calling)?

Yes, Magistral Medium 1.2 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Magistral Medium 1.2 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.

Get started with Puter.js

Add Magistral Medium 1.2 to your app without worrying about API keys or setup.

Read the Docs View Tutorials