$Proxlai
← Serverless GPU

Modal

Modal H100

Python-native serverless GPUs that scale to zero. Sample entry (hourly equivalent).

USD per GPU-hour (billed per second)

$3.95

Unverified sample

#4 cheapest of 5 in Serverless GPU

Official pricing ↗

Capabilities, explained

What this API can do, and what each capability means for your project.

GPU

H100 SXM

GPU type for this price.

VRAM

80 GB

Memory per GPU.

Typical cold start

5 s

Seconds from zero to ready.

Scales to zero

Yes

No cost when there is no traffic.

Price history

Only one price recorded so far. The chart appears once the price changes.