Modal
Serverless GPUs defined entirely in Python, no Dockerfiles or YAML. Per-second billing, scale-to-zero and instant fan-out make it ideal for batch jobs, inference APIs and pipelines.
On-demand GPUs
| GPU | VRAM | $/hr | Type |
|---|---|---|---|
| H100 | 80 GB | $3.95 | Serverless |
| A100 80GB | 80 GB | $2.50 | Serverless |
| A100 40GB | 40 GB | $2.10 | Serverless |
| L40S | 48 GB | $1.95 | Serverless |
| A10G | 24 GB | $1.10 | Serverless |
On-demand prices are indicative snapshots for orientation only. Spot/community and committed-use rates are often 30 to 70% lower. Always confirm on the provider's pricing page before committing.