GPU cloud head to head
RunPod vs Vast.ai
- GPUs
- 43 80
- Cheapest GPU
- $0.13/hr $0.0281/hr
- Price wins
- 4/35 31/35
Vast.ai is cheaper on 31 of the 35 GPUs both rent, RunPod on 4. Vast.ai carries 37 more GPUs.
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
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 35 GPUs both rent. Cheapest live rate per GPU-hour, most powerful first. The cheaper side is in purple.
| GPU | RunPod | Vast.ai | Gap |
|---|---|---|---|
| NVIDIA B200 SXM 180GB | $6.79/hr | $7.50/hr community | 10% |
| NVIDIA B300 SXM 262GB | $7.89/hr | $9.94/hr community | 26% |
| NVIDIA H100 SXM5 80GB | $3.49/hr | $2.13/hr community | 64% |
| NVIDIA H200 SXM 141GB | $4.59/hr | $4.30/hr community | 7% |
| NVIDIA H100 NVL 94GB | $3.19/hr | $2.32/hr community | 37% |
| NVIDIA H200 NVL 141GB | $3.79/hr | $2.65/hr community | 43% |
| NVIDIA H100 PCIe 80GB | $2.89/hr | $2.33/hr community | 24% |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | $2.19/hr | $1.14/hr community | 92% |
| NVIDIA RTX PRO 6000 Blackwell Server Edition | $0.59/hr | $1.20/hr community | 104% |
| NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | $0.50/hr | $1.07/hr community | 114% |
| NVIDIA GeForce RTX 5090 32GB | $0.99/hr | $0.43/hr community | 132% |
| NVIDIA RTX 6000 Ada 48GB | $0.84/hr | $0.49/hr community | 70% |
| NVIDIA L40S 48GB | $1.09/hr | $0.80/hr community | 36% |
| NVIDIA A100 SXM4 80GB | $1.59/hr | $0.95/hr community | 67% |
| NVIDIA A100 PCIe 80GB | $1.59/hr | $0.87/hr community | 82% |
| NVIDIA RTX 5000 Ada 32GB | $0.83/hr | $0.34/hr community | 147% |
| NVIDIA RTX PRO 5000 Blackwell 48GB | $0.96/hr | $0.62/hr community | 55% |
| NVIDIA GeForce RTX 5080 16GB | $0.59/hr | $0.20/hr community | 191% |
| NVIDIA GeForce RTX 4090 24GB | $0.74/hr | $0.32/hr community | 128% |
| NVIDIA RTX A6000 48GB | $0.53/hr | $0.40/hr community | 32% |
| NVIDIA A40 48GB | $0.49/hr | $0.40/hr community | 22% |
| NVIDIA RTX PRO 4000 Blackwell 24GB | $0.57/hr | $0.20/hr community | 182% |
| NVIDIA L4 24GB | $0.49/hr | $0.33/hr community | 47% |
| NVIDIA RTX 4000 Ada 20GB | $0.28/hr | $0.20/hr community | 38% |
| NVIDIA GeForce RTX 4080 Super 16GB | $0.50/hr | $0.27/hr community | 87% |
| NVIDIA GeForce RTX 4080 16GB | $0.50/hr | $0.20/hr community | 147% |
| NVIDIA GeForce RTX 4070 Ti 12GB | $0.50/hr | $0.32/hr community | 55% |
| NVIDIA GeForce RTX 3090 24GB | $0.50/hr | $0.13/hr community | 273% |
| NVIDIA GeForce RTX 3080 Ti 12GB | $0.18/hr community | $0.11/hr community | 65% |
| NVIDIA GeForce RTX 3080 10GB | $0.17/hr community | $0.11/hr community | 58% |
| NVIDIA GeForce RTX 3070 8GB | $0.13/hr community | $0.0696/hr community | 87% |
| NVIDIA GeForce RTX 3090 Ti 24GB | $0.46/hr | $0.24/hr community | 90% |
| NVIDIA RTX A5000 24GB | $0.27/hr | $0.23/hr community | 16% |
| NVIDIA RTX A4000 16GB | $0.25/hr | $0.0750/hr community | 233% |
| NVIDIA RTX A2000 12GB | $0.50/hr | $0.11/hr community | 353% |
Prices last checked: RunPod 1 Oct 2026, Vast.ai 1 Oct 2026.
Only on one side
Only on RunPod 8
Only on Vast.ai 45
- NVIDIA A100 PCIe 40GB $0.40
- NVIDIA RTX 5880 Ada 48GB $0.67
- NVIDIA RTX PRO 5000 Blackwell 72GB $0.94
- NVIDIA GeForce RTX 5070 Ti 16GB $0.16
- NVIDIA RTX 4500 Ada 24GB $0.37
- NVIDIA GeForce RTX 4090 D 24GB $3.39
- NVIDIA Quadro RTX 6000 24GB $0.14
- NVIDIA Quadro RTX 8000 48GB $0.25
- NVIDIA Titan RTX 24GB $0.27
- NVIDIA V100 SXM2 32GB $0.12
- NVIDIA GeForce RTX 5070 12GB $0.14
- NVIDIA Titan V 12GB $0.16
- NVIDIA GeForce RTX 5060 Ti 16GB $0.12
- NVIDIA GeForce RTX 5060 Ti 8GB $0.13
- NVIDIA Quadro RTX 5000 16GB $0.0948
- NVIDIA GeForce RTX 4070 Ti SUPER 16GB $0.18
- NVIDIA GeForce RTX 5060 8GB $0.0952
- NVIDIA GeForce RTX 4070 SUPER 12GB $0.11
- +27 more on the Vast.ai page
Company facts
| Fact | RunPod | Vast.ai |
|---|---|---|
| Headquarters |  United States | United States |
| Type | GPU cloud | Marketplace |
| Founded | 2022 | 2018 |
| GPUs priced | 43 | 80 |
| Fastest GPU | NVIDIA B200 SXM 180GB | NVIDIA B200 SXM 180GB |
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 RunPod and Vast.ai?
- RunPod: GPU cloud that rents pods billed per second and runs serverless endpoints, with community and secure hosting tiers. Vast.ai: Marketplace where independent hosts list GPUs and renters pick machines by price, with on-demand and interruptible bids.
- Is RunPod cheaper than Vast.ai?
- Vast.ai is cheaper on 31 of the 35 GPUs both rent, RunPod on 4. Vast.ai carries 37 more GPUs.
- How much does a NVIDIA B200 SXM 180GB cost on RunPod and Vast.ai?
- RunPod charges $6.79 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 RunPod and Vast.ai?
- 35 GPUs, including NVIDIA B200 SXM 180GB, NVIDIA B300 SXM 262GB, NVIDIA H100 SXM5 80GB, NVIDIA H200 SXM 141GB, NVIDIA H100 NVL 94GB, NVIDIA H200 NVL 141GB.
- 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.
