Hugging Face Inference Endpoints vs Lyceum
As of , Lyceum lists the lower on-demand rate on 5 of the 5 GPUs both offer on-demand. On the priciest shared card both list on-demand, NVIDIA B200: Hugging Face Inference Endpoints $9.25 (aws) vs Lyceum $6.49 per GPU-hour on-demand — Lyceum is $2.76 (30%) cheaper.
Cloud GPU rental prices of Hugging Face Inference Endpoints and Lyceum, 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 | Lyceum | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA B200 | $9.25 aws captured Deploy ↗ | $6.49 captured Deploy ↗ | $2.76 (30%) | Lyceum |
| NVIDIA H200 | $5.00 aws captured Deploy ↗ | $4.29 captured Deploy ↗ | $0.71 (14%) | Lyceum |
| NVIDIA H100 80GB (form factor not stated) | $4.50 aws captured Deploy ↗ | $2.79 captured Deploy ↗ | $1.71 (38%) | Lyceum |
| NVIDIA A100 80GB | $2.50 aws captured Deploy ↗ | $1.59 captured Deploy ↗ | $0.91 (36%) | Lyceum |
| NVIDIA L40S | $1.80 aws captured Deploy ↗ | $1.19 captured Deploy ↗ | $0.61 (34%) | Lyceum |
GPU by GPU
- NVIDIA B200: Hugging Face Inference Endpoints $9.25 (aws) vs Lyceum $6.49 per GPU-hour on-demand — Lyceum is $2.76 (30%) cheaper.
- NVIDIA H200: Hugging Face Inference Endpoints $5.00 (aws) vs Lyceum $4.29 per GPU-hour on-demand — Lyceum is $0.71 (14%) cheaper.
- NVIDIA H100 80GB (form factor not stated): Hugging Face Inference Endpoints $4.50 (aws) vs Lyceum $2.79 per GPU-hour on-demand — Lyceum is $1.71 (38%) cheaper.
- NVIDIA A100 80GB: Hugging Face Inference Endpoints $2.50 (aws) vs Lyceum $1.59 per GPU-hour on-demand — Lyceum is $0.91 (36%) cheaper.
- NVIDIA L40S: Hugging Face Inference Endpoints $1.80 (aws) vs Lyceum $1.19 per GPU-hour on-demand — Lyceum is $0.61 (34%) 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: