RentGPU RentGPU
GPU finden →
by Xiaomi

MiMo-V2.6-Flash.

multimodal open weights datacenter 311B params 1M ctx
Cheapest input
$0.14/M
on DeepInfra
Cheapest output
$0.28/M
on DeepInfra
Smallest GPU
4× Nvidia Q RTX 8000
$1.08/hr

MiMo-V2.6-Flash is Xiaomi's MIT-licensed 309B mixture-of-experts model, 15B active, taking text, image, video and audio with a 1M-token context for agent work.

Smallest GPU to run it See all quantisations →

4× Nvidia Q RTX 8000 · $1.08/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 $0.14 $0.28 Launch ↗
OpenRouter api aggregator $0.14 $0.28 Launch ↗
Sources

Official references.

Hugging Face ↗
FAQ

Frequently asked.

How do I run MiMo-V2.6-Flash?
MiMo-V2.6-Flash 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-Flash?
MiMo-V2.6-Flash 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-Flash?
API pricing starts at $0.14/M input tokens and $0.28/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is MiMo-V2.6-Flash open-source or proprietary?
MiMo-V2.6-Flash is open-weight under the mit license. You can download and self-host it.