Modal vs RunPod
- GPUs
- 11 43
- Cheapest GPU
- $0.59/hr $0.13/hr
- Price wins
- 3/9 6/9
RunPod is cheaper on 6 of the 9 GPUs both rent, Modal on 3. RunPod carries 32 more GPUs.
Serverless GPU platform where code runs as functions for inference, batch jobs and training, billed per second with no commitments.
Best for: Serverless inference and batch jobs
GPU cloud that rents pods billed per second and runs serverless endpoints, with community and secure hosting tiers.
Best for: Serverless inference and cheap GPU pods
Price by GPU
The 9 GPUs both rent. Cheapest live rate per GPU-hour, most powerful first. The cheaper side is in purple.
| GPU | Modal | RunPod | Gap |
|---|---|---|---|
| NVIDIA B200 SXM 180GB | $6.25/hr | $6.79/hr | 9% |
| NVIDIA B300 SXM 262GB | $7.10/hr | $7.89/hr | 11% |
| NVIDIA H100 SXM5 80GB | $3.95/hr | $3.49/hr | 13% |
| NVIDIA H200 SXM 141GB | $4.54/hr | $4.59/hr | 1% |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | $3.03/hr | $2.19/hr | 38% |
| NVIDIA L40S 48GB | $1.95/hr | $1.09/hr | 79% |
| NVIDIA A100 SXM4 80GB | $2.50/hr | $1.59/hr | 57% |
| NVIDIA A100 SXM4 40GB | $2.10/hr | $1.00/hr community | 110% |
| NVIDIA L4 24GB | $0.80/hr | $0.49/hr | 63% |
Prices last checked: Modal 1 Oct 2026, RunPod 1 Oct 2026.
Only on one side
Only on Modal 2
Only on RunPod 34
- AMD Instinct MI300X 192GB $2.39
- NVIDIA H100 NVL 94GB $3.19
- NVIDIA H200 NVL 141GB $3.79
- NVIDIA H100 PCIe 80GB $2.89
- NVIDIA RTX PRO 6000 Blackwell Server Edition $0.59
- NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition $0.50
- NVIDIA GeForce RTX 5090 32GB $0.99
- NVIDIA RTX 6000 Ada 48GB $0.84
- NVIDIA A100 PCIe 80GB $1.59
- NVIDIA RTX 5000 Ada 32GB $0.83
- NVIDIA RTX PRO 5000 Blackwell 48GB $0.96
- NVIDIA GeForce RTX 5080 16GB $0.59
- NVIDIA RTX PRO 4500 Blackwell 32GB $0.72
- NVIDIA L40 48GB $0.82
- NVIDIA GeForce RTX 4090 24GB $0.74
- NVIDIA RTX A6000 48GB $0.53
- NVIDIA A40 48GB $0.49
- NVIDIA RTX PRO 4000 Blackwell 24GB $0.57
- +16 more on the RunPod page
Company facts
| Fact | Modal | RunPod |
|---|---|---|
| Headquarters |  New York City, United States | United States |
| Type | GPU cloud | GPU cloud |
| Founded | n/a | 2022 |
| GPUs priced | 11 | 43 |
| Fastest GPU | NVIDIA B200 SXM 180GB | NVIDIA B200 SXM 180GB |
| Services | Serverless GPU compute, inference, batch jobs, training, sandboxes | n/a |
| Pricing models | Pay-per-second, no commitments | n/a |
Compliance
Frameworks each provider states it holds, linked to its own statement. Not published means we found no statement, not that the provider fails it. Check the scope with the provider.
Pick your provider
Questions
- What is the difference between Modal and RunPod?
- Modal: Serverless GPU platform where code runs as functions for inference, batch jobs and training, billed per second with no commitments. RunPod: GPU cloud that rents pods billed per second and runs serverless endpoints, with community and secure hosting tiers.
- Is Modal cheaper than RunPod?
- RunPod is cheaper on 6 of the 9 GPUs both rent, Modal on 3. RunPod carries 32 more GPUs.
- How much does a NVIDIA B200 SXM 180GB cost on Modal and RunPod?
- Modal charges $6.25 per GPU-hour and RunPod charges $6.79 per GPU-hour, the cheapest live rate on each.
- Which GPUs can I rent on both Modal and RunPod?
- 9 GPUs, including NVIDIA B200 SXM 180GB, NVIDIA B300 SXM 262GB, NVIDIA H100 SXM5 80GB, NVIDIA H200 SXM 141GB, NVIDIA RTX PRO 6000 Blackwell Workstation Edition, NVIDIA L40S 48GB.
- How are these prices compared?
- Each figure is the cheapest live rate per GPU-hour for that GPU. We use on-demand pricing where a provider sells it and fall back to community or reserved terms, labelled, where that is all they sell. Spot capacity is left out because it can be reclaimed. Rates are refreshed by our daily ingest.
How we define a live price: methodology.
