← All models
Xiaomi · Video
Xiaomi: MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
ClosedIn: Text, Audio, Image, VideoOut: Text
Input / M
$0.40 / M
Output / M
$2.00 / M
Cache read / M
$0.08 / M
Context
1M
Released
Apr 22, 2026