Runpod vs Vast.ai — hourly on-demand and spot GPU prices, normalised per single GPU, side by side.
Vast.ai is cheaper on average across the GPU models both providers list (avg $0.5927/GPU/hr vs $1.2644/GPU/hr). Cheaper on average: Vast.ai.
Runpod sells both secure cloud (their own datacentres) and a community cloud of third-party hosts, billed by the second. It is a common first stop for teams that want per-hour H100/A100 capacity without a contract, plus serverless GPU endpoints and network volumes.
Average normalised on-demand price: $1.2644/GPU/hr · 18 listings
Vast.ai is a marketplace: independent hosts list their own machines and you bid for them. That makes it the cheapest option for interruptible work and for older GPUs, at the cost of more variable reliability and a search-and-bid workflow instead of a fixed catalogue.
Average normalised on-demand price: $0.5927/GPU/hr · 7 listings
| GPU model | VRAM | Runpod On-demand /hr | Vast.ai On-demand /hr | Runpod Spot | Vast.ai Spot | Actions |
|---|---|---|---|---|---|---|
| H100 SXM | 80 GB | $2.6900 | $2.2689 Best value | — | $2.2000 | |
| A100 PCIe | 80 GB | $1.1900 | $0.2681 Best value | — | $0.2000 | |
| RTX 5090 | 32 GB | $0.6900 | $0.2129 Best value | — | $0.1000 | |
| RTX 4090 | 24 GB | $0.3400 | $0.1081 Best value | — | $0.0533 | |
| V100 | 16 GB | $0.1900 | $0.0556 Best value | — | — | |
| RTX 3090 | 24 GB | $0.2200 | $0.0881 Best value | — | — |
For every GPU model both providers list, we compare the normalised single-GPU hourly price. The average of those unit prices is shown for each side, and the lower one is labelled cheaper. We deliberately exclude models only one of the two offers, because that is not a like-for-like comparison.
Not always. Marketplace capacity can be reclaimed at short notice and its hosts vary in network and disk performance, while a dedicated cloud gives more predictable throughput. For multi-node training, interconnect and NVLink support usually matter more than a few cents per hour.
Only roughly. Each platform defines interruption rules, notice periods and reclaim behaviour differently. Treat spot prices as an indication of the cheapest achievable rate, not as a guaranteed price.
Most providers bill by the second or the hour, and per-hour figures are the only ones that can be compared without guessing how many hours you will actually run. Use the GPU cost estimator to convert an hourly rate into a monthly budget.
Reserving large amounts of GPU capacity? Tell us what you need and we will forward your request to the right provider team.