Hugging Face
CuratedActiveAI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inference
From
≈$24.09/mo
Detected on the provider's website
GPU from
$0.800/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
3
plans
Overview
Hugging Face, the largest hub for open models and datasets, rents GPU hardware for Spaces apps and dedicated autoscaling Inference Endpoints on major public clouds, and routes serverless calls to partner inference providers. GPU options range from T4 and L4 to A100, H100, H200 and B200.
Plans & prices
GPU instances3
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
Spaces hardware — 1× Nvidia L4 | 1× L4 | $0.800 | $0.800 | — | Verified 4 days ago | |
Spaces hardware — 1× Nvidia L40S | 1× L40S | $1.80 | $1.80 | — | Verified 4 days ago | |
Spaces hardware — 1× Nvidia A100 80GB (a100-large) | 1× A100 80GB | $2.50 | $2.50 | — | Verified 4 days ago |
GPU models
Similar providers
RunPodDeveloper GPU cloud with per-second Pods, serverless endpoints and community hosts
falGenerative media platform with pay-per-use model APIs and serverless GPUs
ModalPython-native serverless cloud with per-second GPUs from T4 to B300
DeepInfraLow-cost model inference API plus dedicated A100-to-B300 GPUs billed by the minute
Fireworks AIFast inference and fine-tuning platform with per-second on-demand GPU deployments
BasetenInference platform for dedicated model deployments and model APIs, billed per minute
BeamServerless GPUs, sandboxes and BYOC deployments billed by the millisecond
SaladSaladCloud runs containers on a distributed network of consumer RTX GPUs