When was MiniMax M3.1 Flash released?

MiniMax released MiniMax M3.1 Flash on 19 Oct 2026. It is available through the Opper gateway.

Does MiniMax M3.1 Flash support zero data retention?

Yes. MiniMax M3.1 Flash is available with zero data retention on Fireworks, Infercom, Novita, TensorX through the Opper gateway. Other routes carry zero data retention with abuse monitoring; see each route's window in the data-handling section.

Where is MiniMax M3.1 Flash hosted?

MiniMax M3.1 Flash runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is MiniMax M3.1 Flash trained on prompts and outputs?

No. Every hosting route for MiniMax M3.1 Flash is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for MiniMax M3.1 Flash?

Yes. A GDPR Data Processing Agreement is available on at least one route serving MiniMax M3.1 Flash. Contact hello@opper.ai to receive it.

MiniMax M3.1 Flash

by MiniMax

Released 80 days after MiniMax H3 · Announcement · All MiniMax releases

MiniMax M3.1 Flash is an open-weight multimodal mixture-of-experts model with approximately 428 billion total parameters and 23 billion active per token. It accepts text, images and video, produces text, and supports a context window of up to one million tokens. MiniMax designed it for coding, agentic workflows and computer use. The release extends MiniMax Sparse Attention throughout the model and adds quantization-aware training and DSpark speculative decoding. MiniMax reports 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 82.2 on CyberGym and 29.6 on Agents' Last Exam. These are MiniMax's reported evaluation results. The weights are published under the minimax-community license.

Call MiniMax M3.1 Flash on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

Input price

$0.15 /1M$0.01 cache read

Output price

$0.60 /1M

Released

19 Oct 2026

Web search

Via Opper

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

Available routes

MiniMax M3.1 Flash runs on 7 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by TensorX. See every model hosted in the EU.

Provider	Region	Training	Input	Output	Cache read
DigitalOcean	US	No	$0.15	$0.60	$0.01
Fireworks	Multi	No	$0.15	$0.60	$0.01
Infercom	Multi	No	$0.34	$1.35	$0.03
MiniMax	Multi	No	$0.15	$0.60	$0.01
Nebius	Multi	No	$0.15	$0.60	$0.01
Novita	US	No	$0.15	$0.60	$0.01
TensorX	EU	No	$0.30	$1.20	$0.07

Live routes and prices as JSON: api.opper.ai/v3/models?q=minimax-m3.1-flash

Uptime and availability

MiniMax M3.1 Flash runs on 4 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 98.27% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

4 monitored providers serve MiniMax M3.1 Flash.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 3 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting MiniMax M3.1 Flash has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DigitalOcean — United States🇺🇸

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. US; dpf sccs; DPA available.

Zero data retention: With abuse monitoring, flagged content held.
Training: No training on customer data.
Logging: None
Abuse monitoring: Always on, holds flagged content, stored in United States
Caching: Content cached for replay
Subprocessor access: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: dpf sccs

Fireworks — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
Subprocessor access: Subprocessors may read content
GDPR DPA: DPA available
Transfer mechanism: SCCs

Infercom — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; dpf sccs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Subprocessor access: Subprocessors may read content
GDPR DPA: DPA available
Transfer mechanism: dpf sccs

MiniMax — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: With abuse monitoring, window not stated.
Training: No training on customer data.
Logging: Abuse monitoring
Abuse monitoring: On by default, holds flagged content
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: SCCs

Nebius — Multi-region

Content is retained: provider logging. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: Retained: provider logging.
Training: No training on customer data.
Logging: Other
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: SCCs

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
GDPR DPA: DPA available
Transfer mechanism: SCCs

TensorX — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Best for

Where MiniMax M3.1 Flash ranks among the models on Opper with a score for each use case.

Agents#15 of 8749.2

Terminal-Bench 4.0 and AutomationBenchSee the Agents ranking →Coding#21 of 4422.8

FrontierCode 2.0 and Terminal-Bench 4.0See the Coding ranking →Finance#22 of 4639.1

Finance and accountingSee the Finance ranking →Healthcare36.8

Healthcare and medicalSee the Healthcare ranking →Legal33.0

Legal tasks and reasoningSee the Legal ranking →

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#29 of 511 LLMs

TierEfficient

Output speed166 tok/s

Intelligence Index29.1

Coding

FrontierCode 2.0

21%

Terminal-Bench 4.0

26%

SciCode

53%

Agentic & knowledge work

AutomationBench

73%

GDPval

48%

GDP.pdf

21%

Briefcase (Elo)1474

Science & reasoning

Terminal-Bench Science

CritPt (hard)

33%

HLE Diamond

28%

Humanity's Last Exam

48%

Long-context reasoning

80%

Knowledge

Omniscience-6.4

MMMU-Pro

79%

By domain

Finance & accounting

39.1

Legal

33.0

Healthcare & medical

36.8

Engineering

34.3

Economics

37.4

Strategy & operations

50.8

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

Get started

Call MiniMax M3.1 Flash through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

MiniMax M3.1 Flash is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex 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: "minimax-m3.1-flash",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);