Mistral AI

Mistral AI: Devstral 2

mistralai/devstral-2512

Access Devstral 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/devstral-2512"
}).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/devstral-2512"
        }).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/devstral-2512",
    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/devstral-2512",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Devstral 2 is a 123B parameter dense transformer coding model achieving 72.2% on SWE-bench Verified with 256K context. Released under modified MIT license, it's the state-of-the-art open model for code agents, 7x more cost-efficient than Claude Sonnet.

Context Window 262K

tokens

Max Output 66K

tokens

Input Cost $0.4

per million tokens

Output Cost $2

per million tokens

Release Date Dec 1, 2025

 

Output Speed 79

tokens / sec

Latency 0.59s

time to first token

Model Playground

Try Devstral 2 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat mistralai/devstral-2512
Mistral AI
Chat with Devstral 2
Powered by Puter.js

Benchmarks

How Devstral 2 performs on standard evaluations.

Artificial Analysis
Intelligence Index
22.0
Better than 58% of tracked models
Artificial Analysis
Coding Index
23.7
Better than 62% of tracked models
Artificial Analysis
Math Index
36.7
Better than 36% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
59.4%
Humanity's Last Exam Cross-domain reasoning
3.6%
LiveCodeBench Recent coding problems
44.8%
SciCode Scientific programming
33.1%
AIME 2025 Advanced math exam
36.7%
IFBench Instruction following
38.1%
LCR Long-context reasoning
30.0%
Terminal-Bench Hard Agentic terminal tasks
18.9%
τ²-Bench Tool use / agents
24.9%

Scores sourced from Artificial Analysis.

Find other Mistral AI models →

Chat

Mistral 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.

 Chat

Mistral Small Creative

Mistral Small Creative is a specialized Labs model variant optimized for creative content generation. It builds on the Mistral Small architecture with adjustments for more imaginative and varied outputs in writing tasks.

 Chat

Ministral 14B

Ministral 14B is part of the Ministral 3 family, a 14B parameter multimodal model with vision capabilities under Apache 2.0. It offers advanced capabilities for local deployment with instruct, base, and reasoning variants achieving 85% on AIME'25.

Frequently Asked Questions

How do I use Devstral 2?

You can access Devstral 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 Devstral 2 free?

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

Devstral 2 was created by Mistral AI and released on Dec 1, 2025.

What is the context window of Devstral 2?

Devstral 2 supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.

What is the max output length of Devstral 2?

Devstral 2 can generate up to 66K tokens in a single response.

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

Yes — the Devstral 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 Devstral 2 to your app without worrying about API keys or setup.

Read the Docs View Tutorials