/ Models

Language models

Xiaomi: MiMo-V2.5-Pro

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

Maker
Xiaomi
Context window
1.1M
Max output
131K
Input / 1M
$0.435
Output / 1M
$0.87
1M in + 1M out
$1.30

Everything else

Max output131K
Input / 1M$0.435
Output / 1M$0.87
Cache read / 1M$0.004
Cache write / 1M
1M in + 1M out$1.30
Takestext
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2026-04-22
Knowledge cutoff
Retires
Catalog idxiaomi/mimo-v2.5-pro

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