When was MiMo V2.6 Pro released?

Xiaomi released MiMo V2.6 Pro on 21 Sep 2026. It is available through the Opper gateway.

Does MiMo V2.6 Pro support zero data retention?

Yes. MiMo V2.6 Pro is available with zero data retention on DeepInfra, EmpirioLabs, Tencent Cloud through the Opper gateway.

Where is MiMo V2.6 Pro hosted?

MiMo V2.6 Pro runs on US hosting routes through the Opper gateway.

Is MiMo V2.6 Pro trained on prompts and outputs?

No. Every hosting route for MiMo V2.6 Pro is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for MiMo V2.6 Pro?

Yes. A GDPR Data Processing Agreement is available on at least one route serving MiMo V2.6 Pro. Contact hello@opper.ai to receive it.

MiMo V2.6 Pro

by Xiaomi

Released 152 days after MiMo V2.5 Pro · All Xiaomi releases

Xiaomi MiMo V2.6 Pro is a 1.02T parameter sparse MoE (42B active) omnimodal reasoning model for long-horizon coding and multi-tool agents, with a 1M token context.

Call MiMo V2.6 Pro 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

131K

Input price

$0.43 /1M$0.0036 cache read

Output price

$0.87 /1M

Released

21 Sep 2026

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

Available routes

MiMo V2.6 Pro runs on 3 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.

Provider	Region	Training	Input	Output	Cache read
DeepInfra	US	No	$0.43	$0.87	$0.0036
EmpirioLabs	Multi	No	$2.17	$4.35	$2.17
Tencent Cloud	Multi	No	$0.43	$0.87	$0.0036

Live routes and prices as JSON: api.opper.ai/v3/models?q=mimo-v2.6-pro

Uptime and availability

One of MiMo V2.6 Pro's 3 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

100%route uptime, last 30 days

Its other routes aren't measured here yet.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 2 further routes are not on the board yet. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting MiMo V2.6 Pro has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

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

EmpirioLabs — 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: No subprocessor reads content
GDPR DPA: DPA available
Transfer mechanism: SCCs

Tencent Cloud — 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
Caching: Content cached for replay
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#32 of 689 LLMs

TierStrong

Output speed37 tok/s

First token2.65s

Intelligence Index46.3

Reasoning & knowledge

Humanity's Last Exam

49%

Long-context reasoning

86%

Coding

SciCode

61%

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

Get started

Call MiMo V2.6 Pro through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

MiMo V2.6 Pro 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: "mimo-v2.6-pro",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);