RentGPU RentGPU
GPU finden →
by Xiaomi

Xiaomi: MiMo-V2.5.

multimodal open weights 1M ctx
Cheapest input
$0.105/M
on OpenRouter
Cheapest output
$0.28/M
on OpenRouter
Hosted equiv.
~$0.1/hr
@ 100 tok/s on OpenRouter

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..

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.105 $0.28 Launch ↗
DeepInfra hosted inference $0.4 $2.0 Launch ↗
FAQ

Frequently asked.

How do I run Xiaomi: MiMo-V2.5?
Xiaomi: MiMo-V2.5 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Xiaomi: MiMo-V2.5?
Xiaomi: MiMo-V2.5 is available via DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Xiaomi: MiMo-V2.5?
API pricing starts at $0.4/M input tokens and $2.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Xiaomi: MiMo-V2.5 open-source or proprietary?
Xiaomi: MiMo-V2.5 is open-weight under the license. You can download and self-host it.