Xiaomi MiMo
Xiaomi's family of large AI models for agent tasks, multimodal input, and speech
Introduction
Xiaomi MiMo is a suite of large AI models from Xiaomi. The lineup includes MiMo-V2-Pro for agent tasks, MiMo-V2-Omni for multimodal perception, MiMo-V2-TTS for speech synthesis, and MiMo-V2-Flash for fast responses. You can try the models in a web demo, and developers can integrate them through an API portal.
- Added on
- Nov 2, 2026
- Website
- mimo.xiaomi.com
Product information
What is Xiaomi MiMo?
A suite of Xiaomi's large AI models covering agents, multimodal perception, and voice.
How to use Xiaomi MiMo?
Try the models in the web demo on the site, or use the API portal to add them to your own applications.
Core features of Xiaomi MiMo
- Agent capabilities with MiMo-V2-Pro
- Multimodal perception with MiMo-V2-Omni
- Text-to-speech with MiMo-V2-TTS
- Fast responses with MiMo-V2-Flash
- Developer API access
Use cases of Xiaomi MiMo
- 1Building agents that carry out tasks automatically
- 2Apps that need visual and audio awareness
- 3Natural voices for AI assistants
Frequently asked questions about Xiaomi MiMo
What models are included in Xiaomi MiMo?+
The suite includes MiMo-V2-Pro for agent tasks, MiMo-V2-Omni for multimodal input, MiMo-V2-TTS for voice, and MiMo-V2-Flash for speed.
How can developers use Xiaomi MiMo?+
Developers can use the MiMo API portal to add language, multimodal, and voice capabilities to their products.
Can I try Xiaomi MiMo without writing code?+
Yes. The site provides a web demo where you can interact with the AI directly.
Which category is Xiaomi MiMo in?+
Xiaomi MiMo is listed under AI Agents.