Live Floor
$0.0830
Vast · US
The NVIDIA V100 is based on the Volta architecture with 16 GB of HBM2 VRAM.
Best live route via Vast · US
Live Floor
$0.0830
Vast · US
Average Price
$0.4693
Across 20 live offers
Reliability
97.4%
Based on 20 scored hosts
Last Day Delta
+$0.0000
Latest daily low: 2026-10-13
30-Day Price Trend
Available Offers
Sorted by cheapest hourly rate
| Provider | Price/hr | VRAM | GPUs | Reliability | Region | |
|---|---|---|---|---|---|---|
| Vast | $0.0830 | 16 GB | 1x | 99.1% | US | View Deal |
| Vast | $0.1007 | 16 GB | 1x | 97.5% | CA | View Deal |
| Vast | $0.1356 | 32 GB | 1x | 97.3% | UA | View Deal |
| Vast | $0.1363 | 32 GB | 1x | 92.1% | US | View Deal |
| Vast | $0.1489 | 32 GB | 1x | 95.7% | US | View Deal |
| RunPod | $0.1900 | 16 GB | 1x | 90.0% | -- | View Deal |
| Vast | $0.1941 | 16 GB | 2x | 97.5% | CA | View Deal |
| Vast | $0.2129 | 32 GB | 1x | 99.9% | US | View Deal |
| Vast | $0.2222 | 32 GB | 1x | 98.6% | BG | View Deal |
| Vast | $0.2689 | 32 GB | 2x | 97.3% | UA | View Deal |
| Vast | $0.2696 | 32 GB | 2x | 98.6% | US | View Deal |
| Vast | $0.2956 | 32 GB | 2x | 95.7% | US | View Deal |
| Vast | $0.4356 | 32 GB | 2x | 98.7% | BG | View Deal |
| Vast | $0.4716 | 32 GB | 2x | 100.0% | US | View Deal |
| Vast | $0.5356 | 32 GB | 2x | 99.9% | US | View Deal |
| Vast | $0.5889 | 32 GB | 4x | 95.7% | US | View Deal |
| Vast | $0.8449 | 32 GB | 4x | 99.8% | US | View Deal |
| Vast | $1.0689 | 32 GB | 4x | 99.9% | US | View Deal |
| Vast | $1.1756 | 32 GB | 8x | 95.7% | US | View Deal |
| Vast | $2.0076 | 32 GB | 8x | 99.8% | US | View Deal |
GPU Overview
The NVIDIA V100 is based on the Volta architecture with 16 GB of HBM2 VRAM. It was a landmark datacenter GPU that introduced Tensor Cores, and it continues to serve as a scalable accelerator in legacy AI infrastructure and cloud instances.
Its 16 GB of VRAM supports inference on mid-sized models and training of smaller architectures. The V100 remains a practical choice for budget-conscious datacenter deployments where established ML pipelines run efficiently on Volta-generation hardware, particularly in cloud environments offering competitive per-hour pricing.