AITOPAI热报

MiMo-V3

Xiaomi·China
ClosedPreviewMultimodalAudioVision

MiMo-V3 is a multimodal AI model developed by Xiaomi, specializing in visual and audio processing.

—context
—per 1M tokens (in / out)
—parameters
4stories in our feed

Specs

hover a value to see its source
Context window—
Max output—
Parameters—
Knowledge cutoff—
Licence—
Commercial useUnknown
Input—
Output—
Familymimo

API price

USD per 1M tokens

No public API price yet.

News timeline

from the AITOP feed, one story per event
2026-09-24
Xiaomi unveils HySparse2 architecture for MiMo-V3 agent inferenceIT之家
小米 MiMo 团队发布 HySparse2 注意力架构shao__meng
Xiaomi Details HySparse2 Sparse Attention for MiMo-V3pandaily
2026-09-23
Xiaomi MiMo-V3 to Adopt New Architecture with HySparse 2IT之家