Live Floor
$1.0778
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
$1.0778
Vast · US
Average Price
$2.4265
Across 9 live offers
Reliability
97.9%
Based on 9 scored hosts
Last Day Delta
+$0.0000
Latest daily low: 2026-05-20
30-Day Price Trend
Available Offers
Sorted by cheapest hourly rate
| Provider | Price/hr | VRAM | GPUs | Reliability | Region | |
|---|---|---|---|---|---|---|
| Vast | $1.0778 | 80 GB | 1x | 86.0% | US | View Deal |
| Vast | $1.1756 | 80 GB | 1x | 99.4% | JP | View Deal |
| Vast | $1.8664 | 80 GB | 1x | 99.7% | US | View Deal |
| Vast | $1.9313 | 80 GB | 1x | 99.6% | US | View Deal |
| Vast | $1.9496 | 40 GB | 2x | 99.0% | US | View Deal |
| Vast | $2.3489 | 80 GB | 2x | 99.5% | JP | View Deal |
| Vast | $3.7313 | 80 GB | 2x | 99.7% | US | View Deal |
| Vast | $3.8612 | 80 GB | 2x | 99.6% | US | View Deal |
| Vast | $3.8963 | 40 GB | 4x | 98.8% | 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.