Does Mistral-Small-3.2-24B-Instruct-2506 support zero data retention?

Yes. Mistral-Small-3.2-24B-Instruct-2506 is available with zero data retention by default on Berget, DeepInfra through the Opper gateway.

Where is Mistral-Small-3.2-24B-Instruct-2506 hosted?

Mistral-Small-3.2-24B-Instruct-2506 runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Mistral-Small-3.2-24B-Instruct-2506 trained on prompts and outputs?

No. Every hosting route for Mistral-Small-3.2-24B-Instruct-2506 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Mistral-Small-3.2-24B-Instruct-2506?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Mistral-Small-3.2-24B-Instruct-2506. Contact hello@opper.click to receive it.

Mistral-Small-3.2-24B-Instruct-2506

by Mistral

Mistral Small 3.2 24B Instruct is an open-weight instruction-tuned model released in June 2025 under Apache 2.0. As an incremental update to Mistral Small 3.1, it focuses on more reliable behavior: better adherence to precise instructions, far fewer repetitive or infinite generations, and more robust function calling. This configuration is optimized for text generation and tool execution, with a 128K token context window that supports document analysis, retrieval-augmented generation, and extended multi-turn interactions. Function calling lets it drive agentic workflows and structured automation. With a compact 24B footprint, Small 3.2 runs on modest hardware and serves as a dependable open-weight choice for virtual assistants, fine-tuning, and production deployments where consistent instruction following matters more than raw scale.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

—

Max output

—

Input price

$0.34 /1M

Output price

$0.34 /1M

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

Available routes

Mistral-Small-3.2-24B-Instruct-2506 runs on 2 different routes 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	$0.34	$0.34
DeepInfra	US	Enterprise	No	$0.07	$0.20

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

Data handling per route

Each route hosting Mistral-Small-3.2-24B-Instruct-2506 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

DeepInfra — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Limited debug logs
Third-party access: None disclosed
GDPR DPA: No DPA
Transfer mechanism: unknown

Get started

Call Mistral-Small-3.2-24B-Instruct-2506 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.click/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);