AI Observatory / Model Radar
Xiaomi / xiaomi/mimo-v2.5
Xiaomi: MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
1,048,576
Context
131,072
Max output
$0.40 / 1M
Prompt price
2026-04-22
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Xiaomi | Input modalities | text, audio, image, video |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.40 / 1M |
| Completion price | $2.00 / 1M | Request price | N/A |
| Context length | 1,048,576 | Max completion tokens | 131,072 |
| Supported parameters | frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, response_format, stop, temperature, tool_choice, tools, top_p | ||
Best for
xiaomi/mimo-v2.5
Xiaomi: MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
Cross-modal work
Voice and audio
Long context
High-volume usage
new
vision
tool-capable
long-context
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.