Xiaomi

MiMo V2.6 Flash

Xiaomi's efficient reasoning model. Close to V2.6 Pro on agent benchmarks at a third of the price.

MiMo V2.6Text + visiontext + image inputtext output

Replaces MiMo M2.5: same input and output price, context 1.1M → 1M, max output 131K → 131K.

Run this model

xiaomi/mimo-v2.6-flash

Use an endpoint supported by this model.

Get a key for this setup →
const response = await fetch('https://api.minirouter.sh/v1/chat/completions', {  method: 'POST',  headers: {    Authorization: `Bearer ${process.env.MINIROUTER_KEY}`,    'Content-Type': 'application/json',  },  body: JSON.stringify({    model: 'xiaomi/mimo-v2.6-flash',    messages: [{ role: 'user', content: 'Why is the sky blue?' }],    max_tokens: 1024,  }),}) const data = await response.json()console.log(data.choices[0].message.content)
Read docs →

Use Chat Completions with an explicit max_tokens. Text and image input are enabled; audio and video are not yet.

Model overview

Input / 1M
$0.147
All-in MiniRouter rate
Output / 1M
$0.294
All-in MiniRouter rate
Context
1M
1,048,576 tokens
Max output
131K
tokens
DeepSWE v1.1
67.9%
Pro scores 71.9%
Architecture
309B MoE
15B active, MIT weights
Announced
22 Sept 2026
publisher release

Publisher evidence

Most of Pro, for less.

Xiaomi's own harness and settings. Compare within this table, not against other publishers' numbers.

Xiaomi-reported

Coding, agents and tools

  • MiMo V2.6 Flash
  • Comparison models

Coding agent

DeepSWE v1.1

  • MiMo V2.6 Pro71.9%
  • MiMo V2.6 Flash67.9%
  • MiMo V2.5 Pro19.0%
  • Claude Opus 574.0%
  • GPT-5.6 Sol73.0%

0 to 100%

General agent

AutomationBench v1.0.6

  • MiMo V2.6 Pro53.1%
  • MiMo V2.6 Flash52.3%
  • MiMo V2.5 Pro16.0%
  • Claude Opus 550.3%
  • GPT-5.6 Sol45.8%

0 to 100%

Tool use

Toolathlon-Verified

  • MiMo V2.6 Pro76.9%
  • MiMo V2.6 Flash73.6%
  • MiMo V2.5 Pro49.1%
  • Claude Opus 580.6%
  • GPT-5.6 Sol74.9%

0 to 100%

Terminal

Terminal Bench 2.1

  • MiMo V2.6 Pro89.9%
  • MiMo V2.6 Flash87.6%
  • MiMo V2.5 Pro65.2%
  • Claude Opus 589.1%
  • GPT-5.6 Sol88.8%

0 to 100%

Xiaomi MiMo-V2.6 model card ↗, September 22, 2026.
View chart data
Values from Xiaomi's MiMo-V2.6 model card
BenchmarkMiMo V2.6 ProMiMo V2.6 FlashMiMo V2.5 ProClaude Opus 5GPT-5.6 Sol
DeepSWE v1.171.9%67.9%19.0%74.0%73.0%
AutomationBench v1.0.653.1%52.3%16.0%50.3%45.8%
Toolathlon-Verified76.9%73.6%49.1%80.6%74.9%
Terminal Bench 2.189.9%87.6%65.2%89.1%88.8%

When to step up

Start on Flash, escalate to Pro.

The gap widens on terminal and security tasks. Measure on your own work before you switch.

MiMo V2.6 Pro
  1. 01

    High-volume agents

    Tool calls, JSON output and long context at the lowest MiMo price.

  2. 02

    Harder terminal work

    Terminal Bench 4.0: 28.8% on Flash, 34.9% on Pro.

One route, standard clients.

Authenticate with a MiniRouter bearer key. Caller-provided upstream credentials are not used on this route.

Read model setup docs →
Base URLhttps://api.minirouter.sh/v1
Model IDxiaomi/mimo-v2.6-flash
Endpoints
/v1/chat/completions/v1/messages/v1/responses
Parameters

max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning

Structured output

Not enforced; a requested format is dropped and the answer is plain text.

Configured provider

Priority follows the live catalog order.

Input: text, image · Output: text

ProviderPriorityInput / 1MOutput / 1MParametersAccess
vercel
1$0.147$0.294max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoningMiniRouter balance