Modal GPU Pricing
8 GPU instances across 1 regions.6 GPU models available — from $0.59/hr.
Serverless GPU platform for running Python functions in the cloud. Modal bills per second with zero idle costs — deploy inference endpoints or run batch jobs without managing infrastructure.
- Per-second billing — zero idle costs
- Serverless — no infrastructure to manage
- Fast cold starts for GPU containers
- SOC 2 compliant
- Excellent developer experience and docs
- Not suitable for long-running training jobs
- No persistent local storage
- Serverless model requires code adaptation
Modal currently lists 8 GPU instances across 6 GPU models and 1 regions. Pricing starts at $0.59/hr, while the median listing price is $3.55/hr. Compare by model, commitment type, and region before treating the cheapest row as the best choice.
All Modal GPU Instances
8 results| GPU Model | Instance | Count | VRAM | Region | Type | Price/hr | $/GPU/hr | |
|---|---|---|---|---|---|---|---|---|
| T4 | 1x-T4-US-East | 1× | 16GB | US-East | Serverless | $0.5900 | — | Rent |
| L4 | 1x-L4-US-East | 1× | 24GB | US-East | Serverless | $0.8000 | — | Rent |
| A10G | 1x-A10G-US-East | 1× | 24GB | US-East | Serverless | $1.1000 | — | Rent |
| A100 40GB | 1x-A100-40GB-US-East | 1× | 40GB | US-East | Serverless | $2.7800 | — | Rent |
| A100 80GB | 1x-A100-80GB-US-East | 1× | 80GB | US-East | Serverless | $3.5500 | — | Rent |
| H100 | 1x-H100-80GB-US-East | 1× | 80GB | US-East | Serverless | $4.3000 | — | Rent |
| A100 80GB | 2x-A100-80GB-US-East | 2× | 160GB | US-East | Serverless | $7.1000 | $3.5500 | Rent |
| H100 | 8x-H100-80GB-US-East | 8× | 640GB | US-East | Serverless | $34.4000 | $4.3000 | Rent |
Compare Other Providers
Modal vs … (Head-to-Head)
Modal GPU Cloud — FAQ
Modal GPU instances start from $0.59/hr. The average price is $6.83/hr. Prices depend on GPU model, region, and commitment type (on-demand vs spot).
Modal offers 6 GPU models: T4, L4, A10G, A100 40GB, A100 80GB, H100. Browse the full list above to compare prices per model.
GPU Tracker’s pricing comparisons are paired with true cost and risk signals. Read the methodology page for how refresh cadence, cost assumptions, and reliability indicators are defined.