Skip to content
RankShark

MiMo-V2.6-Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.

ModelOpen sourceby Xiaomisince 2026
49.6

SharkScore

#44 in Models

Why it scores 49.6

MiMo-V2.6-Flash has a SharkScore of 49.6/100, ranked #44 of 608 in Models (updated 2026-11-19).

Each part compares MiMo-V2.6-Flash with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
10 · 30%
User reviews
no data · 25%
Maintenance
86 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of MiMo-V2.6-Flash

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, MiMo-V2.6-Flash accepts text, image, video, and audio and returns text; OpenRouter lists it at $0.14 per million input tokens and $0.28 per million output tokens. [E2]

Xiaomi's MiMo-V2.6-Flash is a foundation model with a 309B-parameter sparse Mixture-of-Experts architecture and 15B activated parameters. Xiaomi's model page describes the Flash-RL checkpoint as supporting text, image, video, and audio input; OpenRouter lists text output. [E1][E2]

Best for

  • Developers building applications that process text, images, video, or audio and return text. · OpenRouter
  • Long-context tasks: Xiaomi lists a 1M-token context length, and RankShark measured 1,050,000 tokens on OpenRouter. · model card, OpenRouter
  • Coding and agent tasks, which Xiaomi includes in its evaluation results. · model card

Not for

  • Applications that need the model to generate image, video, or audio outputs; OpenRouter lists text as its output modality. · OpenRouter

Key features

  • Multimodal input. The vendor says the model handles text, image, video, and audio. OpenRouter lists text as the output modality. · model card, OpenRouter
  • Long context. The vendor says the model has a 1M-token context length. RankShark measured 1,050,000 tokens on the OpenRouter listing. · model card, OpenRouter
  • Sparse MoE architecture. The vendor says the model has 309B total parameters and 15B activated parameters. · model card
  • Coding and agent evaluations. The vendor publishes results for coding, general agent, cybersecurity, and visual agent benchmarks. · model card
  • Self-hosting and hosted options. The vendor documents SGLang and vLLM deployment and lists AI Studio, MiMo Code, Xiaomi MiMo Desktop, Xiaomi MiMo Open Platform API, and OpenRouter as availability options. · model card

Pros

  • Supports text, image, video, and audio inputs. · model card, OpenRouter
  • Has a long context window; the OpenRouter listing measured 1,050,000 tokens. · model card, OpenRouter
  • The vendor provides deployment instructions for SGLang and vLLM, as well as hosted availability options. · model card

Cons

  • OpenRouter lists text as the only output modality. · OpenRouter
  • The vendor notes that stable vLLM may lag and points to a pre-built image and an earlier-version recipe. · model card
  • No free plan or free trial stated on the pages we checked.
  • Whether customer data is used for model training is not stated on the pages we checked.

Pricing

PlanPriceLimits
OpenRouter API$0.14 per million input tokens; $0.28 per million output tokensRankShark measured a 1,050,000-token context window on the OpenRouter listing.

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
Not stated (checked 18 Nov 2026)
Data retention
Not stated (checked 18 Nov 2026)
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
MiMo-V2.6-Flash (Hugging Face checkpoint: MiMo-V2.6-Flash-RL) · model card, OpenRouter
API
OpenRouter lists chat completions, completions, messages, and responses endpoints. Xiaomi also lists its MiMo Open Platform API. · model card, OpenRouter
SDKs
Not stated (checked 18 Nov 2026)
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
OpenRouter, Xiaomi MiMo Open Platform API, AI Studio, MiMo Code, Xiaomi MiMo Desktop, Hugging Face, and ModelScope. · model card, OpenRouter
Security claims
No security certification stated (checked 18 Nov 2026)

What we measured

Context window (OpenRouter listing) · now
1,050,000 tokens
Price per million tokens (OpenRouter listing) · now
$0.14 in, $0.28 out
Package downloads · 30 days
41,838
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.
  • 18 Nov 2026: Plans or prices changed on the pricing page.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to MiMo-V2.6-Flash

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source