Live Floor
$0.4030
Vast · US
The NVIDIA A100 SXM4 is based on the Ampere architecture with 80 GB of HBM2e VRAM and an SXM4 form factor for high-bandwidth NVLink interconnects.
Best live route via Vast · US
Live Floor
$0.4030
Vast · US
Average Price
$1.5846
Across 21 live offers
Reliability
96.8%
Based on 21 scored hosts
Last Day Delta
-$0.0541
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 | $0.4030 | 40 GB | 1x | 98.5% | US | View Deal |
| Vast | $0.4852 | 40 GB | 1x | 91.4% | US | View Deal |
| Vast | $0.5363 | 39 GB | 1x | 99.6% | CA | View Deal |
| Vast | $0.5563 | 40 GB | 1x | 95.8% | US | View Deal |
| Vast | $0.7252 | 40 GB | 1x | 94.8% | US | View Deal |
| Vast | $0.8030 | 40 GB | 2x | 98.5% | US | View Deal |
| Vast | $0.9652 | 40 GB | 2x | 91.4% | US | View Deal |
| Vast | $1.0560 | 80 GB | 1x | 99.6% | CZ | View Deal |
| Vast | $1.0681 | 80 GB | 1x | 99.0% | TW | View Deal |
| Vast | $1.1030 | 40 GB | 2x | 95.8% | US | View Deal |
| Vast | $1.1627 | 80 GB | 1x | 99.0% | CZ | View Deal |
| Vast | $1.1897 | 80 GB | 1x | 99.9% | US | View Deal |
| Vast | $1.1951 | 80 GB | 1x | 99.8% | US | View Deal |
| Vast | $1.3385 | 40 GB | 2x | 98.8% | US | View Deal |
| Vast | $1.4452 | 40 GB | 2x | 94.8% | US | View Deal |
| Vast | $1.6496 | 40 GB | 3x | 95.8% | US | View Deal |
| Vast | $2.1963 | 40 GB | 4x | 95.8% | US | View Deal |
| Vast | $2.8852 | 40 GB | 4x | 94.8% | US | View Deal |
| Vast | $3.6319 | 40 GB | 4x | 98.8% | US | View Deal |
| Vast | $3.8363 | 40 GB | 7x | 95.8% | US | View Deal |
| Vast | $5.0452 | 40 GB | 7x | 94.8% | US | View Deal |
GPU Overview
The NVIDIA A100 SXM4 is based on the Ampere architecture with 80 GB of HBM2e VRAM and an SXM4 form factor for high-bandwidth NVLink interconnects. It remains a widely deployed datacenter accelerator, offering proven scalability for distributed training and large-batch inference.
With 80 GB of VRAM, the A100 SXM4 handles Large Language Models (LLM) and fine-tuning of substantial model architectures. Its benchmark score of 100 reflects uncompromising performance for enterprise-grade AI, and it continues to serve as a reliable workhorse for production AI clusters worldwide.