Vast.ai
PartnerRent cloud GPUs from anywhere. Save up to 90% vs AWS, Azure, GCP with a few clicks.
🇺🇸Los Angeles, CAFounded2018MarketplaceUpdated 3 hours ago
Cheapest / hr
$0.01
Tesla P4
Most expensive
$9.38
B300
Average / GPU
$0.95
across 605 configs
GPU types
75
605 configurations
VRAM range
4–288GB
per single GPU
Regions
45
with offerings
GPU pricing by type
Median price per GPU/hour across all configurations offered by Vast.ai.
GPU configurations
1,030 offerings across 75 GPU types. Prices update every 4 hours.
605of 1,030
| Region | Total VRAM | Storage | Status | ||||||
|---|---|---|---|---|---|---|---|---|---|
4 GB VRAM per GPU· 2 configs |  | ×1 | 4 GB | 2 | 8 GB | 226 GB | $0.01–$0.61 | $0.01 | Available |
8 GB VRAM per GPU· 4 configs |  | ×1 | 8 GB | 0 | 16 GB | 163 GB | $0.02–$0.03 | $0.02 | Available |
6 GB VRAM per GPU· 2 configs | | ×1 | 6 GB | 4 | 19 GB | 43 GB | $0.02–$0.34 | $0.02 | Available |
16 GB VRAM per GPU· 19 configs | | ×1 | 16 GB | 10 | 31 GB | 67 GB | $0.03–$2.67 | $0.03 | Available |
6 GB VRAM per GPU· 5 configs |  | ×1 | 6 GB | 11 | 21 GB | 522 GB | $0.03–$1.34 | $0.03 | Available |
10 GB VRAM per GPU· 9 configs | | ×1 | 10 GB | 16 | 63 GB | 232 GB | $0.03–$0.15 | $0.03 | Available |
12 GB VRAM per GPU· 9 configs |  | ×2 | 24 GB | 0 | 16 GB | 81 GB | $0.03–$0.93 | $0.06 | Available |
12 GB VRAM per GPU |  | ×1 | 12 GB | 32 | 15 GB | 93 GB | $0.03 | $0.03 | Available |
8 GB VRAM per GPU· 6 configs | | ×1 | 8 GB | 2 | 8 GB | 146 GB | $0.03–$0.05 | $0.03 | Available |
6 GB VRAM per GPU· 4 configs |  | ×1 | 6 GB | 0 | 8 GB | 181 GB | $0.04–$0.07 | $0.04 | Available |
8 GB VRAM per GPU· 4 configs | | ×1 | 8 GB | 36 | 63 GB | 715 GB | $0.04–$0.07 | $0.04 | Available |
12 GB VRAM per GPU· 20 configs |  | ×1 | 12 GB | 4 | 31 GB | 819 GB | $0.05–$0.68 | $0.05 | Available |
8 GB VRAM per GPU | | ×1 | 8 GB | 2 | 9 GB | 70 GB | $0.05 | $0.05 | Available |
8 GB VRAM per GPU· 4 configs | | ×2 | 16 GB | 0 | 3 GB | 32 GB | $0.05–$0.07 | $0.10 | Available |
12 GB VRAM per GPU· 3 configs | | ×4 | 48 GB | 16 | 42 GB | 969 GB | $0.05–$0.06 | $0.20 | Available |
11 GB VRAM per GPU· 7 configs | | ×1 | 11 GB | 8 | 31 GB | 70 GB | $0.06 | $0.06 | Available |
6 GB VRAM per GPU· 2 configs | | ×1 | 6 GB | 2 | 9 GB | 110 GB | $0.06–$0.42 | $0.06 | Available |
8 GB VRAM per GPU· 5 configs | | ×1 | 8 GB | 32 | 30 GB | 432 GB | $0.06–$2.67 | $0.06 | Available |
8 GB VRAM per GPU· 3 configs |  | ×1 | 8 GB | 0 | 19 GB | 20 GB | $0.06–$1.20 | $0.06 | Available |
8 GB VRAM per GPU· 10 configs |  | ×1 | 8 GB | 28 | 31 GB | 316 GB | $0.07–$0.14 | $0.07 | Available |
24 GB VRAM per GPU· 4 configs |  | ×1 | 24 GB | 8 | 23 GB | 63 GB | $0.07–$0.11 | $0.07 | Available |
8 GB VRAM per GPU· 3 configs | | ×1 | 8 GB | 11 | 21 GB | 233 GB | $0.07–$0.12 | $0.07 | Available |
16 GB VRAM per GPU· 19 configs | | ×2 | 32 GB | 48 | 62 GB | 792 GB | $0.07–$0.47 | $0.14 | Available |
11 GB VRAM per GPU· 4 configs | | ×2 | 22 GB | 32 | 31 GB | 337 GB | $0.07–$0.81 | $0.14 | Available |
12 GB VRAM per GPU· 4 configs | | ×1 | 12 GB | 18 | 31 GB | 268 GB | $0.08–$0.12 | $0.08 | Available |
16 GB VRAM per GPU· 30 configs | | ×8 | 128 GB | 128 | 157 GB | 1.38 TB | $0.08–$0.24 | $0.64 | Available |
12 GB VRAM per GPU· 7 configs | | ×2 | 24 GB | 24 | 31 GB | 359 GB | $0.08–$0.13 | $0.16 | Available |
12 GB VRAM per GPU | | ×1 | 12 GB | 12 | 16 GB | 380 GB | $0.09 | $0.09 | Available |
16 GB VRAM per GPU· 6 configs | | ×4 | 64 GB | 24 | 93 GB | 2.71 TB | $0.09–$0.12 | $0.36 | Available |
16 GB VRAM per GPU· 5 configs | | ×1 | 16 GB | 12 | 31 GB | 174 GB | $0.10–$0.25 | $0.10 | Available |
8 GB VRAM per GPU· 10 configs | | ×1 | 8 GB | 6 | 16 GB | 294 GB | $0.10–$0.43 | $0.10 | Available |
24 GB VRAM per GPU· 33 configs | | ×2 | 48 GB | 36 | 94 GB | 1.36 TB | $0.10–$0.87 | $0.20 | Available |
24 GB VRAM per GPU· 4 configs | | ×2 | 48 GB | 10 | 31 GB | 401 GB | $0.11–$0.15 | $0.22 | Available |
12 GB VRAM per GPU· 3 configs | | ×2 | 24 GB | 11 | 42 GB | 214 GB | $0.11–$0.19 | $0.22 | Available |
20 GB VRAM per GPU | | ×1 | 20 GB | 8 | 251 GB | 354 GB | $0.11 | $0.11 | Available |
16 GB VRAM per GPU· 8 configs | | ×2 | 32 GB | 72 | 63 GB | 1.32 TB | $0.12–$12.00 | $0.24 | Available |
12 GB VRAM per GPU· 7 configs | | ×1 | 12 GB | 56 | 16 GB | 8 GB | $0.12–$0.23 | $0.12 | Available |
16 GB VRAM per GPU· 10 configs | | ×4 | 64 GB | 64 | 126 GB | 1.59 TB | $0.12–$0.34 | $0.48 | Available |
24 GB VRAM per GPU· 51 configs | | ×1 | 24 GB | 18 | 126 GB | 24 GB | $0.12–$4.00 | $0.12 | Available |
16 GB VRAM per GPU· 12 configs |  | ×2 | 32 GB | 64 | 31 GB | 104 GB | $0.13–$0.40 | $0.26 | Available |
24 GB VRAM per GPU· 3 configs | | ×2 | 48 GB | 22 | 94 GB | 592 GB | $0.13–$0.15 | $0.26 | Available |
8 GB VRAM per GPU | | ×1 | 8 GB | 24 | 15 GB | 737 GB | $0.14 | $0.14 | Available |
12 GB VRAM per GPU· 3 configs | | ×1 | 12 GB | 36 | 16 GB | 330 GB | $0.14–$0.23 | $0.14 | Available |
16 GB VRAM per GPU· 13 configs | | ×1 | 16 GB | 24 | 31 GB | 288 GB | $0.15–$1.34 | $0.15 | Available |
8 GB VRAM per GPU |  | ×1 | 8 GB | 28 | 31 GB | 9 GB | $0.15 | $0.15 | Available |
16 GB VRAM per GPU· 4 configs | | ×2 | 32 GB | 32 | 63 GB | 1.53 TB | $0.17–$0.19 | $0.34 | Available |
24 GB VRAM per GPU· 4 configs |  | ×2 | 48 GB | 32 | 125 GB | 3.14 TB | $0.17–$0.31 | $0.34 | Available |
24 GB VRAM per GPU· 9 configs | | ×2 | 48 GB | 6 | 8 GB | 176 GB | $0.20–$0.24 | $0.40 | Available |
24 GB VRAM per GPU | | ×1 | 24 GB | 16 | 63 GB | 220 GB | $0.20 | $0.20 | Available |
8 GB VRAM per GPU· 6 configs | | ×2 | 16 GB | 24 | 94 GB | 10 GB | $0.24–$0.27 | $0.48 | Available |
Showing first 50 of 75 matching configurations
Similar providers
See incorrect data?
Frequently asked questions
What GPUs does Vast.ai offer?
Vast.ai offers 75 GPU types across 605 configurations, including Tesla V100 16GB, H200, Tesla P4, GTX 1660 Super, A100 80GB, RTX 3080 and 69 more. The full list with live hourly pricing is shown above.
How much does Vast.ai cost?
Vast.ai GPU pricing starts at $0.01 per GPU-hour, with an average of $0.95 across its on-demand configurations. Spot and reserved options can be cheaper for interruptible or committed workloads.