RentGPU RentGPU
寻找 GPU →
by Google DeepMind

gemma-4-31B-it-Ultra.

multimodal open weights 131K ctx
Cheapest input
$0.27/M
on DeepInfra
Cheapest output
$0.76/M
on DeepInfra
Hosted equiv.
~$0.27/hr
@ 100 tok/s on DeepInfra

Ultra speed version of gemma-4-31B-it

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.27 $0.76 Launch ↗
FAQ

Frequently asked.

How do I run gemma-4-31B-it-Ultra?
gemma-4-31B-it-Ultra 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 gemma-4-31B-it-Ultra?
gemma-4-31B-it-Ultra is available via DeepInfra. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run gemma-4-31B-it-Ultra?
API pricing starts at $0.27/M input tokens and $0.76/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is gemma-4-31B-it-Ultra open-source or proprietary?
gemma-4-31B-it-Ultra is open-weight under the license. You can download and self-host it.