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.

Price History

Pricing by Region

Region On-Demand Spot Reserved 1Y
us-east-1$55.040$11.639$41.266
us-east-2$55.040$9.118$41.266
us-west-2$55.040$7.020$41.266
eu-north-1$58.893$19.413$44.155
ca-central-1$63.296$16.969$47.456
ap-south-1$66.048$66.048$49.519
ap-northeast-1$68.800$51.582
us-west-1$68.800$14.600$51.582
ap-southeast-2$71.552$71.552$53.646
eu-west-2$71.552$71.552$53.646
ap-northeast-2$75.955
ap-southeast-3$75.955$56.947
sa-east-1$92.467$79.830$69.327

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.
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 $5124.60/mo with spot pricing.

Run a free assessment to identify overprovisioned workloads, idle capacity, and your potential savings, in minutes.

Most clusters are overprovisioned.
Let's prove yours is.