Modal
CuratedActivePython-native serverless cloud with per-second GPUs from T4 to B300
From
—
GPU from
$1.95/GPU-hr
Locations
0
countries
Data centers
0
sites
Networks (ASN)
0
ASNs
Plans & prices
6
plans
Overview
Modal runs Python functions, batch jobs, notebooks and web endpoints on autoscaling containers with GPUs from T4 to B300, billed by the second with scale-to-zero and a monthly free compute allowance. Capacity is pooled across several underlying clouds.
Plans & prices
GPU instances6
| Instance | Config | per GPU-hr | Total /hr | Spot | Locations | Source |
|---|---|---|---|---|---|---|
NVIDIA L40S — $0.000542/s per GPU (≈ hourly) | 1× L40S | $1.95 | $1.95 | — | Verified 3 days ago | |
NVIDIA A100 80GB — $0.000694/s per GPU (≈ hourly) | 1× A100 80GB | $2.50 | $2.50 | — | Verified 3 days ago | |
NVIDIA H100 SXM5 — $0.001097/s per GPU (≈ hourly) | 1× H100 SXM | $3.95 | $3.95 | — | Verified 3 days ago | |
NVIDIA H200 SXM — $0.001261/s per GPU (≈ hourly) | 1× H200 | $4.54 | $4.54 | — | Verified 3 days ago | |
NVIDIA B200 — $0.001736/s per GPU (≈ hourly) | 1× B200 | $6.25 | $6.25 | — | Verified 3 days ago | |
NVIDIA B300 — $0.001972/s per GPU (≈ hourly) | 1× B300 (Blackwell Ultra) | $7.10 | $7.10 | — | Verified 3 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
Hugging FaceAI model hub selling GPU Spaces, dedicated Inference Endpoints and routed inference
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