Does MiniMax M2.5 support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for MiniMax M2.5 is available on request via Opper Enterprise — contact hello@opper.ai.

Where is MiniMax M2.5 hosted?

MiniMax M2.5 runs on US hosting routes through the Opper gateway.

Is MiniMax M2.5 trained on prompts and outputs?

No. Every hosting route for MiniMax M2.5 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for MiniMax M2.5?

Yes. A GDPR Data Processing Agreement is available on at least one route serving MiniMax M2.5. Contact hello@opper.ai to receive it.

MiniMax M2.5

by MiniMax

MiniMax M2.5 is a 229-billion-parameter Mixture-of-Experts model offering production-grade capability in coding, tool use, and office productivity. It scores 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, with multi-turn function calling reaching 76.9% on BFCL. The model was trained across hundreds of thousands of real-world environments and more than 10 programming languages, letting it handle architecture-level code planning and multi-file editing. It uses roughly 20% fewer interaction rounds than its predecessor for efficient task decomposition and completes SWE-Bench evaluations about 37% faster than M2.1. M2.5 is strong at professional office work across Word, Excel, and PowerPoint, with a 59.0% average win rate against competing models on workplace scenarios. It supports extended chain-of-thought reasoning and agentic tool calling for real-world productivity.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

197K

Max output

—

Input price

$0.30 /1M

Output price

$1.20 /1M

US residency available
Zero data retention via Enterprise
No training by default
GDPR DPA available

Available routes

MiniMax M2.5 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
Fireworks	US	Enterprise	No	$0.30	$1.20

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

Data handling per route

Each route hosting MiniMax M2.5 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Fireworks — United States🇺🇸

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

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

Get started

Call MiniMax M2.5 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: "fireworks/minimax-m2p5",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);