← TPUs, AI chips & CPU endpoints
Hugging Face Inference Endpoints
HF Endpoints AWS Inferentia2
Dedicated Inferentia2 endpoint, 'starting at' price per hour, billed by the minute.
USD per accelerator- or instance-hour
$0.75
Verified Oct 6, 2026
#2 cheapest of 5 in TPUs, AI chips & CPU endpoints
Official pricing ↗Capabilities, explained
What this API can do, and what each capability means for your project.
Accelerator type
inferentia
The kind of hardware you are renting.
Memory
—
Memory per chip or instance. Sets the largest model you can load.
Frameworks
pytorch
Software stacks that run on this hardware.
Supports training
No
Can be used to train models, not only to serve them.
Per-minute billing
Yes
You pay by the minute instead of rounding up to a full hour.
Price history
Only one price recorded so far. The chart appears once the price changes.