Hugging Face services
Inference Endpoints and Hub services with published per-hour CPU and GPU instance rates.
Hugging Face Inference Endpoint CPU x1 (AWS)
$0.00055 / endpoint-minute (CPU x1)
Hugging Face
Inference Endpoints and Hub services with published per-hour CPU and GPU instance rates.
There is 1 published meter for Hugging Face. The published list unit price in this group is $0.00055. Billing units represented here: endpoint-minute (CPU x1). The most recent price check in this group is 2026-08-14.
Official Hugging Face pricing page
Hugging Face list rates
A cheap host rate is not the same kind of number as a per-GB or per-million-events rate. The source column is the page used for the check.
| Service | Unit price | Unit | Source | Verified |
|---|---|---|---|---|
| Hugging Face Inference Endpoint CPU x1 (AWS) | $0.00055 | endpoint-minute (CPU x1) | Hugging Face Inference Endpoints pricing |
Questions about Hugging Face rates
Do Hugging Face monthly plans show up in the calculator total?
When the source publishes a per-unit rate, the calculator uses that linear list rate. Included quotas, monthly minimums, annual packs, and volume discounts still live on the official docs.