AWS EC2 Instance
p5.48xlarge
The p5.48xlarge is a GPU-accelerated AWS EC2 instance with 192 vCPUs and 2048 GB of memory, 8 H100 GPUs, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $55.0400/hr in us-east-1. Spot pricing starts at $17.1409/hr in ca-central-1.
Price History
Pricing by Region
| Region | On-Demand ↑ | Spot | Reserved 1Y |
|---|---|---|---|
| us-east-1 | $55.040 | $20.418 | $41.266 |
| us-east-2 | $55.040 | $19.861 | $41.266 |
| us-west-2 | $55.040 | $20.320 | $41.266 |
| eu-north-1 | $58.893 | $18.645 | $44.155 |
| ca-central-1 | $63.296 | $17.141 | $47.456 |
| ap-south-1 | $66.048 | $18.511 | $49.519 |
| ap-northeast-1 | $68.800 | $22.304 | $51.582 |
| us-west-1 | $68.800 | $22.956 | $51.582 |
| ap-southeast-2 | $71.552 | $25.235 | $53.646 |
| eu-west-2 | $71.552 | $20.117 | $53.646 |
| ap-northeast-2 | $75.955 | — | — |
| ap-southeast-3 | $75.955 | $62.367 | $56.947 |
| sa-east-1 | $92.467 | $78.346 | $69.327 |
Spot Interruption Risk
Frequently Asked Questions
- What is the p5.48xlarge?
- The p5.48xlarge is a GPU-accelerated AWS EC2 instance with 192 vCPUs and 2048 GB of memory, 8 H100 GPUs, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $55.0400/hr in us-east-1. Spot pricing starts at $17.1409/hr in ca-central-1.
- What is the cheapest region for p5.48xlarge?
- us-east-1 at $55.040/hr on-demand.
- How much does p5.48xlarge cost per month?
- Starting at $40179.20/mo on-demand in us-east-1, or $12512.86/mo with spot pricing.
