Mistral AI

Mistral AI: Mistral Medium 3.1

mistralai/mistral-medium-2508

Access Mistral Medium 3.1 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/mistral-medium-2508"
}).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-medium-2508"
        }).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/mistral-medium-2508",
    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/mistral-medium-2508",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Mistral Medium 3.1 is Mistral's frontier-class multimodal model released August 2025 with 128K context. It delivers near-frontier performance at $0.4/$2 per million tokens, excelling in reasoning, coding, and enterprise workflows.

Context Window 131K

tokens

Max Output 131K

tokens

Input Cost $0.4

per million tokens

Output Cost $2

per million tokens

Input text, image

modalities

Tool Use Yes

 

Knowledge Cutoff May 2025

 

Release Date Aug 12, 2025

 

Output Speed 89

tokens / sec

Latency 0.41s

time to first token

Model Playground

Try Mistral Medium 3.1 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat mistralai/mistral-medium-2508
Mistral AI
Chat with Mistral Medium 3.1
Powered by Puter.js

Benchmarks

How Mistral Medium 3.1 performs on standard evaluations.

Artificial Analysis
Intelligence Index
21.3
Better than 57% of tracked models
Artificial Analysis
Coding Index
18.3
Better than 51% of tracked models
Artificial Analysis
Math Index
38.3
Better than 39% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
58.8%
Humanity's Last Exam Cross-domain reasoning
4.4%
LiveCodeBench Recent coding problems
40.6%
SciCode Scientific programming
33.8%
AIME 2025 Advanced math exam
38.3%
IFBench Instruction following
39.8%
LCR Long-context reasoning
19.7%
Terminal-Bench Hard Agentic terminal tasks
10.6%
τ²-Bench Tool use / agents
40.6%

Scores sourced from Artificial Analysis.

Frequently Asked Questions

How do I use Mistral Medium 3.1?

You can access Mistral Medium 3.1 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 Mistral Medium 3.1 free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Mistral Medium 3.1 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 Mistral Medium 3.1?
Pricing for Mistral Medium 3.1 is based on the number of input and output tokens used per request.
Price per 1M tokens
Input$0.4
Output$2
Who created Mistral Medium 3.1?

Mistral Medium 3.1 was created by Mistral AI and released on Aug 12, 2025.

What is the context window of Mistral Medium 3.1?

Mistral Medium 3.1 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 Mistral Medium 3.1?

Mistral Medium 3.1 can generate up to 131K tokens in a single response.

What is the knowledge cutoff of Mistral Medium 3.1?

Mistral Medium 3.1 has a knowledge cutoff date of May 2025. This means the model was trained on data available up to that date.

What types of input can Mistral Medium 3.1 process?

Mistral Medium 3.1 accepts the following input types: text, image. It produces: text.

Does Mistral Medium 3.1 support tool use (function calling)?

Yes, Mistral Medium 3.1 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 Mistral Medium 3.1 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 Mistral Medium 3.1 to your app without worrying about API keys or setup.

Read the Docs View Tutorials