MiMo-V2-Pro utilizes a 7:1 hybrid ratio (increased from 5:1 in the Flash version) to manage its massive 1M-token context window.
Xiaomi is continuing its steady push into large language models. After introducing MiMo-7B in May 2025 and following it up ...
Pro, Xiaomi’s agent focused LLM with 1M context, strong coding, efficient architecture, and lower API costs than premium rivals.
The MiMo-V2 lineup includes three models: MiMo-V2-Pro, MiMo-V2-Omni, and MiMo-V2-TTS.