Xiaomi: MiMo-V2-Flash

XiaomiID: xiaomi/mimo-v2-flash

MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config).

Pricing per 1M Tokens

Input (Prompt)$0.09
Output (Completion)$0.29
Cache Read$0.04
Cache WriteFree
ImageN/A

Specifications

Context Length262K
Max Output Tokens66K
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct TypeN/A
Top Provider Context262K
Top Provider Max Output66K
ModeratedNo

Compare this model

See how Xiaomi: MiMo-V2-Flash stacks up against other models.

vs Xiaomi: MiMo-V2-Omnivs Xiaomi: MiMo-V2-Pro

More from Xiaomi

Xiaomi: MiMo-V2-Omni
Input$0.40
Context262K
Xiaomi: MiMo-V2-Pro
Input$1.00
Context1.0M

Last updated: March 23, 2026

First tracked: March 23, 2026