CrossModel
MiMo V2.6 Flash
xiaomi/mimo-v2.6-flash
Back to model catalog

Xiaomi · Model guide

MiMo V2.6 Flash

Compare
xiaomi/mimo-v2.6-flashReleased Sep 22, 2026

The efficiency-balanced MiMo V2.6 model: an open-weight sparse MoE with 309B total and 15B active parameters, a 1M-token context and native understanding of text, images, audio and video. It shares the Pro model's reinforcement-learning recipe, and Xiaomi reports it outperforming MiMo V2.5 Pro across its agent benchmarks; Xiaomi recommends it for high-frequency calls and large-scale professional workloads.

Modalities
TextImageAudioVideoText
Context
1M
Max output
131K
Price / 1M tokens
$ 0.16in$ 0.32out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorA full-modality, high-intelligence reasoning model: the best balance for high-frequency calls and large-scale tasks in professional workflows.source

Best for

  • High-frequency professional workloads · Xiaomi's selection guide recommends it for frequent calls and large-scale tasks in professional office scenarios.(vendor claim)source

  • Coding agents · Scores 67.9 on DeepSWE v1.1 and 87.6 on Terminal-Bench 2.1 in Xiaomi's own evaluation, ahead of MiMo V2.5 Pro on both.(vendor claim)source

  • Omni-modal understanding · Takes text, images, audio and video in one model through the same vision and audio encoders as Pro.(vendor claim)source

Neighbouring models
  • xiaomi/mimo-v2.6-prostronger —Choose Pro for the hardest long-horizon agent, cybersecurity and research tasks.
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 0.16
Output$ 0.32
Cache read$ 0.0040
Cache write$ 0.16
Estimate a request
$ 0.0022
Estimated cost per request
10.0K × $ 0.16
+ 2.0K × $ 0.32
≈ $ 2.24 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
131.1K tokens
Input / output modalities
Text + Image + Audio + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
Reasoning effort
none · low · medium · high
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specshuggingface.co 1mimo.mi.com 2mimo.mi.com 3Capabilitiesmimo.mi.com 1mimo.mi.com 2mimo.mi.com 3mimo.mi.com 4mimo.mi.com 5mimo.mi.com 6

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 2.1
    pass_rate·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。

    87.6%
  • Terminal-Bench 4.0
    pass_rate·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。

    28.8%
Agentic work
  • AutomationBench v1.0.6
    score·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。

    52.3%
Coding
  • DeepSWE 1.1
    resolved_rate·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。发布博文正文另给出 6 天 Live RL 结束时的数字（Pro 72.6 / Flash 65.7），与最终表不同，此处取最终表。

    67.9%
  • ProgramBench
    score·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。

    26%
Computer use
  • OSWorld-Verified
    success_rate·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。

    80.8%
Cybersecurity
  • CyberGym
    score·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。技术报告脚注：Xiaomi 按报告 4.2.4 节的方法修正了有缺陷的评测环境，与其它厂商的 CyberGym 成绩不可直接比较。

    95.1%
  • ExploitBench
    score·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。

    25.3%
Tool use
  • Toolathlon Verified
    pass_rate·Xiaomi MiMo · 2026-09-22setup not fully disclosed

    厂商自测（技术报告 Table 3，与模型卡同表）；未披露本模型的推理档位、harness 与采样设置。

    73.6%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is MiMo V2.6 Flash?
MiMo V2.6 Flash is available on CrossModel as xiaomi/mimo-v2.6-flash. It has a 1M-token context window and can return up to 131K tokens per request.
How much does MiMo V2.6 Flash cost?
Currently $ 0.16 per 1M input tokens and $ 0.32 per 1M output tokens. Cached input is billed at $ 0.0040 per 1M.
Does MiMo V2.6 Flash support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.