Does Pixtral Large support zero data retention?

Yes. Pixtral Large is available with zero data retention by default on AWS Bedrock through the Opper gateway.

Where is Pixtral Large hosted?

Pixtral Large runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Pixtral Large trained on prompts and outputs?

No. Every hosting route for Pixtral Large is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Pixtral Large?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Pixtral Large. Contact hello@opper.ai to receive it.

Pixtral Large

by Mistral

Pixtral Large is a 124B open-weights multimodal model built on Mistral Large 2, designed for frontier-level image and document understanding. It combines a 1B-parameter vision encoder with a 123B text backbone, supporting a 128K token context window that fits a minimum of 30 high-resolution images in a single request. The model excels at understanding documents, charts, and natural images while retaining strong text-only comprehension. On the MathVista visual reasoning benchmark it scores 69.4%, leading the models Mistral tested, and it achieves leading results on document and chart understanding benchmarks such as DocVQA and ChartQA. Pixtral Large is suited to document-heavy retrieval-augmented generation, agentic workflows, and knowledge exploration. It is available under the Mistral Research License and the Mistral Commercial License. It has since been marked as deprecated in favor of newer Mistral vision models, but remains a capable choice for document and reasoning-intensive visual tasks.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

128K

Max output

Input price

$2.00 /1M

Output price

$6.00 /1M

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

Available routes

Pixtral Large 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
AWS Bedrock	EU	Zero data retention	No	$2.00	$6.00

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

Data handling per route

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

AWS Bedrock — 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 Pixtral Large 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: "aws/pixtral-large-2502-eu",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);