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

Hugging Face Inference Endpoints vs packet.ai

As of , packet.ai lists the lower on-demand rate on 3 of the 3 GPUs both offer on-demand. 1 more shared GPU rests on community capacity or a marketplace floor and is not counted. On the priciest shared card both list on-demand, NVIDIA B200: Hugging Face Inference Endpoints $9.25 (aws) vs packet.ai $6.99 (Dedicated) per GPU-hour on-demand — packet.ai is $2.26 (24%) cheaper.

Cloud GPU rental prices of Hugging Face Inference Endpoints and packet.ai, 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.
GPUHugging Face Inference Endpointspacket.aiDifferenceCheaper
NVIDIA B200$9.25
aws
captured
Deploy ↗
$6.99
Dedicated
captured
Deploy ↗
$2.26 (24%)packet.ai
NVIDIA RTX PRO 6000 Blackwell$2.75
aws
captured
Deploy ↗
$0.66
Dynamic
captured
Deploy ↗
—not the same market
NVIDIA A100 80GB$2.50
aws
captured
Deploy ↗
$1.43
Dedicated
captured
Deploy ↗
$1.07 (43%)packet.ai
NVIDIA L40S$1.80
aws
captured
Deploy ↗
$0.92
Dedicated
captured
Deploy ↗
$0.88 (49%)packet.ai

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: