p5en.48xlarge

Amazon EC2 · P5en family

The p5en.48xlarge is a gpu & accelerated Amazon EC2 instance type with 192 vCPUs and 2 TiB of memory, 8 × NVIDIA H200, running on Intel Xeon Scalable (Sapphire Rapids) with 3200 Gigabit networking, starting at $63.30 per hour on demand.

gpu & acceleratedx86-64intelgpu
vCPUs
192

dedicated

memory
2 TiB

10.67 GiB per vCPU

gpu
8× H200

141 GiB total

on-demand
$63.30

$46,206/mo · us-east-1

spot
–

not offered

regions
13

across 4 areas

p5en.48xlarge price by region

13 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved

US East (N. Virginia)us-east-1cheapestreferenceNorth America$63.30
US East (Ohio)us-east-2cheapestNorth America$63.30
US West (Oregon)us-west-2cheapestNorth America$63.30
EU (Stockholm)eu-north-1Europe$67.73
EU (Spain)eu-south-2Europe$68.36
Canada (Central)ca-central-1North America$72.79
Asia Pacific (Mumbai)ap-south-1Asia$75.96
AWS GovCloud (US)us-gov-west-1North America$75.96
Middle East (UAE)me-central-1Middle East$75.96
Asia Pacific (Tokyo)ap-northeast-1Asia$79.12
US West (N. California)us-west-1North America$79.12
Asia Pacific (Jakarta)ap-southeast-3Asia$87.35
Asia Pacific (Seoul)ap-northeast-2Asia$87.35

Specifications

compute

vCPUs
192
Memory
2 TiB
Memory per vCPU
10.67 GiB
Processor
Intel Xeon Scalable (Sapphire Rapids)
CPU vendor
Intel
Architecture
x86-64
Clock speed
3.2 GHz
Burstable CPU
No

storage & network

Local storage
30.7 TB NVME (8 disks)
Storage detail
8 x 3840 NVMe SSD
Network
3200 Gigabit
Peak bandwidth
3,200 Gbps

accelerators

Count
8
Memory (total)
141 GiB
Architecture
Hopper
Vendor
NVIDIA

aws details

API name
p5en.48xlarge
Family
P5en
Category
GPU & accelerated
Generation
Current
Regions
13 (Asia, Europe, Middle East, North America)
Cheapest region
US East (N. Virginia) · $63.30/hr
Dedicated EBS throughput
100 Gbps
Enhanced networking
Yes
Normalization size factor
384
Processor features
Intel AMX
Spot interruption rate (us-east-1)
<5%
Spot savings vs on-demand (us-east-1)
67%

p5en.48xlarge equivalents on other clouds

closest match by vCPU, memory, CPU architecture, accelerator and class · Linux on-demand in each provider's reference region

compare side by side→
ProviderInstancevCPUMemoryProcessorOn-demandvs p5en.48xlarge
AWSp5en.48xlarge1922 TiB8 × NVIDIA H200$63.30–
AzureND96isr H200 v596 vCPU (2× less) · 1900 GiB (1.1× less)961,900 GiB8 × NVIDIA H200$84.80+34%

P5en family sizes

all about P5en→
SizevCPUMemoryAcceleratorLocal storageOn-demandMonthly
p5en.48xlarge1922 TiB8 × NVIDIA H20030.7 TB NVME (8 disks)$63.30$46,206

Similar instance types on AWS

other AWS families with a similar shape, cheapest first

p5en.48xlarge FAQ

How much does p5en.48xlarge cost?

p5en.48xlarge costs $63.30 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $46,206 per month. Across 13 regions the Linux on-demand price ranges from $63.30 in US East (N. Virginia) to $87.35 in Asia Pacific (Jakarta).

How many vCPUs and how much memory does p5en.48xlarge have?

p5en.48xlarge has 192 vCPUs and 2 TiB of memory (10.67 GiB per vCPU), running on Intel Xeon Scalable (Sapphire Rapids). It is a gpu & accelerated instance type in the P5en family.

What GPU does p5en.48xlarge have?

p5en.48xlarge has 8 × NVIDIA H200 with 141 GiB of accelerator memory in total.

What are the equivalents of p5en.48xlarge on other clouds?

The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Azure, ND96isr H200 v5 (96 vCPU, 1,900 GiB, $84.80/hour in East US 2).