Modal vs Vast.ai
- GPUs
- 11 80
- Cheapest GPU
- $0.59/hr $0.0281/hr
- Price wins
- 2/8 6/8
Vast.ai is cheaper on 6 of the 8 GPUs both rent, Modal on 2. Vast.ai carries 69 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
Marketplace where independent hosts list GPUs and renters pick machines by price, with on-demand and interruptible bids.
Best for: Low-cost GPUs from independent hosts
Price by GPU
The 8 GPUs both rent. Cheapest live rate per GPU-hour, most powerful first. The cheaper side is in purple.
| GPU | Modal | Vast.ai | Gap |
|---|---|---|---|
| NVIDIA B200 SXM 180GB | $6.25/hr | $7.50/hr community | 20% |
| NVIDIA B300 SXM 262GB | $7.10/hr | $9.94/hr community | 40% |
| NVIDIA H100 SXM5 80GB | $3.95/hr | $2.13/hr community | 85% |
| NVIDIA H200 SXM 141GB | $4.54/hr | $4.30/hr community | 6% |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | $3.03/hr | $1.14/hr community | 165% |
| NVIDIA L40S 48GB | $1.95/hr | $0.80/hr community | 144% |
| NVIDIA A100 SXM4 80GB | $2.50/hr | $0.95/hr community | 162% |
| NVIDIA L4 24GB | $0.80/hr | $0.33/hr community | 139% |
Prices last checked: Modal 1 Oct 2026, Vast.ai 1 Oct 2026.
Only on one side
Only on Vast.ai 72
- NVIDIA H100 NVL 94GB $2.32
- NVIDIA H200 NVL 141GB $2.65
- NVIDIA H100 PCIe 80GB $2.33
- NVIDIA RTX PRO 6000 Blackwell Server Edition $1.20
- NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition $1.07
- NVIDIA GeForce RTX 5090 32GB $0.43
- NVIDIA RTX 6000 Ada 48GB $0.49
- NVIDIA A100 PCIe 40GB $0.40
- NVIDIA A100 PCIe 80GB $0.87
- NVIDIA RTX 5880 Ada 48GB $0.67
- NVIDIA RTX 5000 Ada 32GB $0.34
- NVIDIA RTX PRO 5000 Blackwell 48GB $0.62
- NVIDIA RTX PRO 5000 Blackwell 72GB $0.94
- NVIDIA GeForce RTX 5080 16GB $0.20
- NVIDIA GeForce RTX 5070 Ti 16GB $0.16
- NVIDIA GeForce RTX 4090 24GB $0.32
- NVIDIA RTX 4500 Ada 24GB $0.37
- NVIDIA RTX A6000 48GB $0.40
- +54 more on the Vast.ai page
Company facts
| Fact | Modal | Vast.ai |
|---|---|---|
| Headquarters |  New York City, United States | United States |
| Type | GPU cloud | Marketplace |
| Founded | n/a | 2018 |
| GPUs priced | 11 | 80 |
| 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 Vast.ai?
- Modal: Serverless GPU platform where code runs as functions for inference, batch jobs and training, billed per second with no commitments. Vast.ai: Marketplace where independent hosts list GPUs and renters pick machines by price, with on-demand and interruptible bids.
- Is Modal cheaper than Vast.ai?
- Vast.ai is cheaper on 6 of the 8 GPUs both rent, Modal on 2. Vast.ai carries 69 more GPUs.
- How much does a NVIDIA B200 SXM 180GB cost on Modal and Vast.ai?
- Modal charges $6.25 per GPU-hour and Vast.ai charges $7.50 per GPU-hour, the cheapest live rate on each.
- Which GPUs can I rent on both Modal and Vast.ai?
- 8 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.
