Does Mistral Large 3 support zero data retention?

Yes. Mistral Large 3 is available with zero data retention by default on AWS Bedrock through the Opper gateway.

Where is Mistral Large 3 hosted?

Mistral Large 3 runs on US hosting routes through the Opper gateway.

Is Mistral Large 3 trained on prompts and outputs?

No. Every hosting route for Mistral Large 3 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Mistral Large 3?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Mistral Large 3. Contact hello@opper.ai to receive it.

Mistral Large 3

by Mistral

Mistral Large 3 is a frontier-class, open-weight model built on a granular mixture-of-experts architecture with 41 billion active and 675 billion total parameters, released December 2025 under the Apache 2.0 license. It supports native function calling and tool use, making it well suited to reasoning-heavy and agentic workflows. The model excels at production-grade assistants, retrieval-augmented systems, long document understanding, and complex enterprise tasks. It pairs frontier capability with the flexibility of open weights for self-hosted deployment.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

128K

Max output

Input price

$0.50 /1M

Output price

$1.50 /1M

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

Available routes

Mistral Large 3 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	US	Zero data retention	No	$0.50	$1.50

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

Data handling per route

Each route hosting Mistral Large 3 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

AWS Bedrock — United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; 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: SCCs

Benchmarks

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

Global rank#238 of 531 LLMs

TierEfficient

Output speed61 tok/s

First token0.67s

Intelligence Index16.2

Coding Index22.7

Math Index38.0

Reasoning & knowledge

MMLU-Pro

81%

GPQA Diamond

68%

Humanity's Last Exam

Long-context reasoning

35%

Coding

LiveCodeBench

47%

SciCode

36%

Agentic & tool use

Terminal-Bench Hard

16%

τ²-Bench Telecom

25%

Math & instruction following

AIME 2025

38%

IFBench

36%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Mistral Large 3 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/mistral-large-3",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);