Magistral Small

by Mistral

Magistral Small is Mistral's 24B-parameter open-source reasoning model, released under the Apache 2.0 license and available for self-deployment. It delivers strong mathematical and logical reasoning in a lightweight package that runs well on local hardware. Designed for transparent, step-by-step reasoning, Magistral Small works through multi-step problems across professional domains and exposes interpretable thought processes in the user's language. It reasons across multiple languages including English, French, Spanish, German, Italian, Arabic, Russian, and Simplified Chinese. As an open-weight model with a 128k token context window, Magistral Small balances capability and efficiency. Developers can inspect, modify, and build on it freely while keeping reasoning quality competitive with larger models.

Key info

Input
Output
Features
Context window
128K
Max output
8K
Input price
$0.54 /1M
Output price
$2.16 /1M
  • EU residency available
  • Zero data retention on pay-as-you-go
  • No training by default
  • GDPR DPA available

Available routes

Magistral Small runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
EvrocEUZero data retentionNo$0.54$2.16

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Magistral Small has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Evroc β€” SwedenπŸ‡ΈπŸ‡ͺ

Zero data retention is on by default on Pay-as-you-go β€” no action required. No training on customer data. EU; DPA available.

Zero data retention
On by default on Pay-as-you-go.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
Not applicable β€” data stays in EU

Benchmarks

Independent benchmark scores β€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#307 of 531 LLMs
TierEfficient
Output speed0 tok/s
First token0.00s
Intelligence Index10.7
Coding Index11.1
Math Index41.3
Reasoning & knowledge
MMLU-Pro
75%
GPQA Diamond
64%
Humanity's Last Exam
7%
Long-context reasoning
0%
Coding
LiveCodeBench
51%
SciCode
24%
Agentic & tool use
Terminal-Bench Hard
5%
τ²-Bench Telecom
27%
Math & instruction following
AIME 2025
41%
IFBench
25%

Get started

Call Magistral Small through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β€” Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent β€” Claude Code, Cursor, Codex, and more β€” and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "evroc/magistral-small",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Magistral Small with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Mistral

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Magistral Small by Mistral β€” pricing, benchmarks, ZDR, EU hosting | Opper AI