/ Models

Language models

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...

Maker
Xiaomi
Context window
1.1M
Max output
131K
Input / 1M
$0.14
Output / 1M
$0.28
1M in + 1M out
$0.42

Everything else

Max output131K
Input / 1M$0.14
Output / 1M$0.28
Cache read / 1M$0.003
Cache write / 1M
1M in + 1M out$0.42
Takestext, audio, image, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2026-04-22
Knowledge cutoff
Retires
Catalog idxiaomi/mimo-v2.5

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models