Mistral AI

Mistral AI: Mistral Medium 3.5

mistralai/mistral-medium-3-5

Access Mistral Medium 3.5 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-3-5"
}).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-3-5"
        }).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-3-5",
    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-3-5",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

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.

Context Window 262K

tokens

Max Output N/A

tokens

Input Cost $1.5

per million tokens

Output Cost $7.5

per million tokens

Release Date Apr 30, 2026

 

Output Speed 163

tokens / sec

Latency 0.56s

time to first token

Model Playground

Try Mistral Medium 3.5 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat mistralai/mistral-medium-3-5
Mistral AI
Chat with Mistral Medium 3.5
Powered by Puter.js

Benchmarks

How Mistral Medium 3.5 performs on standard evaluations.

Artificial Analysis
Intelligence Index
39.2
Better than 84% of tracked models
Artificial Analysis
Coding Index
35.4
Better than 81% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
74.8%
Humanity's Last Exam Cross-domain reasoning
12.8%
SciCode Scientific programming
39.6%
IFBench Instruction following
68.8%
LCR Long-context reasoning
61.0%
Terminal-Bench Hard Agentic terminal tasks
33.3%
τ²-Bench Tool use / agents
94.2%

Scores sourced from Artificial Analysis.

Frequently Asked Questions

How do I use Mistral Medium 3.5?

You can access Mistral Medium 3.5 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 3.5 free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Mistral Medium 3.5 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 3.5?
Mistral Medium 3.5 costs $1.5 per 1M input tokens and $7.5 per 1M output tokens.
Price per 1M tokens
Input$1.5
Output$7.5
Who created Mistral Medium 3.5?

Mistral Medium 3.5 was created by Mistral AI and released on Apr 30, 2026.

What is the context window of Mistral Medium 3.5?

Mistral Medium 3.5 supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.

How does Mistral Medium 3.5 perform on benchmarks?

Mistral Medium 3.5 scores 39.2 on the Artificial Analysis Intelligence Index, outperforming 84% of tracked models. On coding, it scores 35.4 (outperforms 81% of models).

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

Yes — the Mistral Medium 3.5 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 3.5 to your app without worrying about API keys or setup.

Read the Docs View Tutorials