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 USD prices are indicative snapshots from June 2026 for orientation only — they are not live. Spot/community and committed-use rates are often 30–70% lower. Always confirm on the provider's pricing page before committing.
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 |