MiMo-V2-Omni
Xiaomi🇨🇳 China
Xiaomi's omni-modal model that processes image, video and audio input in one architecture, with agentic tool use.
Context window262K tokens
Input / 1M tokens$0.4
Output / 1M tokens$2
Pricing source: Xiaomi announcement.
Version History
launchmajor
MiMo-V2-Omni released. Xiaomi's omni-modal model that processes image, video and audio input in one architecture, with agentic tool use.