MiMo V2 Omni
MiMo V2 Omni combined text, visual and speech understanding with tool calls and computer interaction. It preceded the V2.5 multimodal release and was offered through Xiaomi's API.
Retired
Perception and action were trained together
Xiaomi described native audio-video input, visual grounding and graphical-interface operation. Its release demonstrations covered browser interaction and office documents. These demonstrations are provider examples; they do not establish reliable completion for every application.Original MiMo V2 Omni announcement
The original API name has retired
The original API name expired on 30 June 2026 at 00:00 UTC+8. Xiaomi listed V2.5 as its replacement.MiMo model retirement and replacement schedule
Practical guidance. This page records the original release. A request routed to a successor does not establish that the original model is still being served. Use the current model list when choosing an API.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Retired |
| Launch date | |
| Access | API |
| Model identifiers | mimo-v2-omni |
| Input coverage | Text, images, video and audio.Original MiMo V2 Omni announcement |
| Model design | One architecture combines multimodal perception and agent actions.Original MiMo V2 Omni announcement |
Related models
- MiMo V2.6 Flash
Xiaomi · MiMo V2.6
A multimodal agent model that accepts text, images, video and audio and returns text.
Launch date not confirmedAPI · Downloadable · Provider product A multimodal model combining the V2 Flash language backbone with vision and audio encoders.
Launch date not confirmedDownloadable