Does Mistral Small 3.1 24B support zero data retention?

Yes. Mistral Small 3.1 24B is available with zero data retention by default on Berget through the Opper gateway.

Where is Mistral Small 3.1 24B hosted?

Mistral Small 3.1 24B runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Mistral Small 3.1 24B trained on prompts and outputs?

No. Every hosting route for Mistral Small 3.1 24B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Mistral Small 3.1 24B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Mistral Small 3.1 24B. Contact hello@opper.ai to receive it.

Mistral Small 3.1 24B

by Mistral

Mistral Small 3.1 (March 2025) is a 24B open-weight model designed for versatile generative AI tasks including instruction following, conversational assistance, image understanding, and function calling. Released under Apache 2.0, it is described by Mistral as the first open model to surpass the performance of leading compact proprietary models, outperforming peers such as Gemma 3 and GPT-4o mini while delivering inference speeds of around 150 tokens per second. The model's 128K token context window supports document analysis, retrieval-augmented generation, and extended interactions. Its multimodal capabilities enable use cases such as document verification, visual inspection, quality checks, and image-based support. Small 3.1 can run on a single high-end consumer GPU or a Mac with 32GB of memory and serves as a strong base for domain-specific fine-tuning. Optimized for both lean and enterprise deployments, Mistral Small 3.1 pairs the capability of much larger models with the efficiency of open-weight alternatives, making it well suited to applications that must balance quality against resource constraints.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

128K

Max output

Input price

$0.35 /1M

Output price

$0.35 /1M

EU residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Mistral Small 3.1 24B runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Berget	EU	Zero data retention	No	$0.35	$0.35

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

Data handling per route

Each route hosting Mistral Small 3.1 24B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Berget — Sweden🇸🇪

Zero data retention is on by default on Pay-as-you-go — 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: None
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Mistral Small 3.1 24B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — 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 — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "berget/mistral-small-3.1-24b-instruct",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);