Hugging Face Inference Endpoints vs Scaleway
As of , Hugging Face Inference Endpoints and Scaleway each list the lower on-demand rate on 1 of the 2 GPUs both offer on-demand. On the priciest shared card both list on-demand, NVIDIA L40S: Hugging Face Inference Endpoints $1.80 (aws) vs Scaleway $1.67 (fr-par-2) per GPU-hour on-demand — Scaleway is $0.13 (7%) cheaper.
Cloud GPU rental prices of Hugging Face Inference Endpoints and Scaleway, compared per GPU-hour on the GPUs both list. Where a provider has several tiers or regions, its cheapest on-demand rate is used and labelled. Community capacity (RunPod Community Cloud) and marketplace floors are shown only where a provider has nothing else, and never decide which is cheaper.
On-demand, per GPU-hour
| GPU | Hugging Face Inference Endpoints | Scaleway | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA L40S | $1.80 aws captured Deploy ↗ | $1.67 fr-par-2 captured Deploy ↗ | $0.13 (7%) | Scaleway |
| NVIDIA L4 | $0.80 aws captured Deploy ↗ | $0.89 fr-par-1 captured Deploy ↗ | $0.09 (11%) | Hugging Face Inference Endpoints |
GPU by GPU
- NVIDIA L40S: Hugging Face Inference Endpoints $1.80 (aws) vs Scaleway $1.67 (fr-par-2) per GPU-hour on-demand — Scaleway is $0.13 (7%) cheaper.
- NVIDIA L4: Hugging Face Inference Endpoints $0.80 (aws) vs Scaleway $0.89 (fr-par-1) per GPU-hour on-demand — Hugging Face Inference Endpoints is $0.09 (11%) cheaper.
Not compared: GPUs only one of the two lists, reserved/committed tiers, and anything either provider prices only on request. See each provider's page for its full list.
Data updated: