p4d.24xlargeAWS Pricing, Specs & Benchmarks

The p4d family is a generation-4 GPU-accelerated (NVIDIA) line running on Intel Xeon (x86_64). p4d.24xlarge provides 96 vCPUs and 1152GB of RAM (a 1:12 vCPU-to-memory ratio), priced at $0.0000/hr On-Demand — about $0.00 per month at 24×7 utilization.

GPU-accelerated (NVIDIA) instances are sized for deep-learning training, large-scale inference, HPC simulation, and any workload that scales with CUDA-enabled GPU compute. If your workload doesn't match that profile — for example, if you're running a memory-bound app on a compute-optimized instance, or a CPU-pegged batch job on a burstable t-series — you'll likely pay for capacity you can't use or run into bottlenecks you didn't anticipate. The pages for sibling families (linked further down) cover those alternatives in detail.

In the AWS instance-naming convention, the digit after the series letter is the generation — higher is newer. This appears to be one of AWS's newer generations in the series, so for most fresh workloads it's a reasonable default within its category. The family suffix tells you about hardware variants: "d" = local NVMe instance-store volumes (lost when the instance stops).

Pricing varies by region (sometimes meaningfully — the gap between the cheapest and most expensive AWS region for the same SKU is often 15–30%). The regional pricing table further down shows where p4d.24xlarge is cheapest today, both On-Demand and Spot. Spot pricing for p4d.24xlarge is currently $9.2831/hr — roughly -Infinity% off On-Demand — which makes the instance viable for fault-tolerant batch jobs, CI fleets, and any workload that can tolerate interruption with short notice.