Xiaomi's omnimodal model that processes text, images, and video in a single forward pass, with a 1M token context window.
- Strengths
- Handles multimodal input across text, images, and video without separate encoders or routing logic.
- Best for
- Workflows that combine video, image, and text understanding in a single request, and applications requiring very long context windows.
- Limitations
- MiMo-V2.5 (released April 2026) is the newer standard release; MiMo-V2.5-Pro's specific positioning within the lineup is unclear.
Input / 1M
$0.435
Output / 1M
$0.87
Cached input / 1M
$0.0036
Context window
1.05M
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $0.435 | $0.87 | $0.0036 | Imported from OpenRouter | openrouter.ai |