p5en.48xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | p5en.48xlarge |
Description | GPU accelerated [Network and EBS optimized] [Extra storage or memory] Gen5 48xlarge |
Family | p5en |
Hw Virt | - |
Status | active |
Observed At | 2026-09-16T02:40:02.481741 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Northern Virgina (US) / us-east-1 | 27.12095 USD/h | 63.296 USD/h |
Ohio (US) / us-east-2 | 27.1608 USD/h | 63.296 USD/h |
Oregon (US) / us-west-2 | 27.148433 USD/h | 63.296 USD/h |
Stockholm (SE) / eu-north-1 | 60.5908 USD/h | 67.7267 USD/h |
Aragón (ES) / eu-south-2 | 21.4736 USD/h | 68.3597 USD/h |
Mumbai (IN) / ap-south-1 | 24.9921 USD/h | 75.9552 USD/h |
United Arab Emirates / me-central-1 | - | 75.9552 USD/h |
Tokyo (JP) / ap-northeast-1 | 30.1883 USD/h | 79.12 USD/h |
California (US) / us-west-1 | 79.12 USD/h | 79.12 USD/h |
Seoul (KR) / ap-northeast-2 | 18.4857 USD/h | 87.3485 USD/h |
Jakarta (ID) / ap-southeast-3 | 69.06035 USD/h | 87.3485 USD/h |
Processor
vCPUs | 192 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 96 |
CPU Speed | 2.4 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 2 TB |
| GPU | |
|---|---|
GPU Count | 8 |
GPU Memory Min | 141 GiB |
GPU Memory Total | 1 TB |
GPU Manufacturer | NVIDIA |
GPU Family | Hopper |
GPU Model | H200 |
GPUs |
|
| STORAGE | |
|---|---|
Storage Size | 30400 GB |
Storage Type | nvme ssd |
Storages |
|
| NETWORK | |
|---|---|
Network Speed Baseline | 200 Gbps |
Network Speed Max | 200 Gbps |
Network Storage Speed Baseline | 100 Gbps |
Network Storage Speed Max | 100 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
A high-density GPU instance featuring eight NVIDIA H200 accelerators, massive NVMe storage, and high-bandwidth networking for intensive parallel computing.
Amazon Web Services p5en.48xlarge is a high-performance, GPU-accelerated server instance designed for intensive computational workloads. Built on the AWS Nitro hypervisor, it features an Intel x86_64 architecture with 192 vCPUs across 96 physical cores running at 2.4 GHz. The system is equipped with 2048.0 GB of system memory and eight NVIDIA Hopper H200 GPUs, providing a total of 1128 GB of VRAM. For high-speed local data access, the instance includes 30400 GB of local NVMe SSD storage. Network connectivity is supported by a baseline bandwidth of 200 Gbps. Given its massive GPU, memory, and storage resources, this instance is optimized for demanding workloads such as deep learning, large language model training, and complex data science simulations.
Economics
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|