GPU EconomyCloud GPU prices, read every hour
updated
H100 index$3.5426 providersWidestV10015.9×Mover, 7dB300−1.4%Coverage709 quotes63 providersReads, 24 h17,43726 runs

Cerebrium vs Hugging Face Inference Endpoints

As of , Cerebrium lists the lower on-demand rate on 6 of the 8 GPUs both offer on-demand; Hugging Face Inference Endpoints wins on 2. On the priciest shared card both list on-demand, NVIDIA B200: Cerebrium $6.01 vs Hugging Face Inference Endpoints $9.25 (aws) per GPU-hour on-demand — Cerebrium is $3.24 (35%) cheaper.

Cloud GPU rental prices of Cerebrium and Hugging Face Inference Endpoints, 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

Each price links to the pricing page it was read from and says when it was read.
GPUCerebriumHugging Face Inference EndpointsDifferenceCheaper
NVIDIA B200$6.01
GPU only
captured
Deploy ↗
$9.25
aws
captured
Deploy ↗
$3.24 (35%)Cerebrium
NVIDIA H200$4.20
GPU only
captured
Deploy ↗
$5.00
aws
captured
Deploy ↗
$0.80 (16%)Cerebrium
NVIDIA H100 80GB (form factor not stated)$3.40
GPU only
captured
Deploy ↗
$4.50
aws
captured
Deploy ↗
$1.10 (24%)Cerebrium
NVIDIA RTX PRO 6000 Blackwell$2.50
GPU only
captured
Deploy ↗
$2.75
aws
captured
Deploy ↗
$0.25 (9%)Cerebrium
NVIDIA A100 80GB$2.10
GPU only
captured
Deploy ↗
$2.50
aws
captured
Deploy ↗
$0.40 (16%)Cerebrium
NVIDIA L40S$1.95
GPU only
captured
Deploy ↗
$1.80
aws
captured
Deploy ↗
$0.15 (8%)Hugging Face Inference Endpoints
NVIDIA L4$0.80
GPU only
captured
Deploy ↗
$0.80
aws
captured
Deploy ↗
$0.00 (0%)Cerebrium
NVIDIA T4$0.59
GPU only
captured
Deploy ↗
$0.50
aws
captured
Deploy ↗
$0.09 (15%)Hugging Face Inference Endpoints

GPU by GPU

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: