RentGPU RentGPU
GPU finden →
by Xiaomi

MiMo-V2.6-Pro.

multimodal open weights datacenter 1024B params 1M ctx
Cheapest input
$0.43/M
on DeepInfra
Cheapest output
$0.87/M
on DeepInfra
Smallest GPU
8× Nvidia A100 SXM4
$5.73/hr

MiMo-V2.6-Pro is Xiaomi's MIT-licensed mixture-of-experts model, 1.02T total and 42B active, with text, image, video and audio input and a 1M-token context for long agent runs.

Smallest GPU to run it See all quantisations →

8× Nvidia A100 SXM4 · $5.73/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.43 $0.87 Launch ↗
OpenRouter api aggregator $0.435 $0.87 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run MiMo-V2.6-Pro?
MiMo-V2.6-Pro 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 MiMo-V2.6-Pro?
MiMo-V2.6-Pro 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 MiMo-V2.6-Pro?
API pricing starts at $0.43/M input tokens and $0.87/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is MiMo-V2.6-Pro open-source or proprietary?
MiMo-V2.6-Pro is open-weight under the mit license. You can download and self-host it.