AWS P2 instance types

P2 is a gpu & accelerated Amazon EC2 family with 3 instance types, from 4 – 64 vCPUs and 61 GiB – 732 GiB of memory with NVIDIA K80 accelerators, running on Intel Xeon E5-2686 v4 (Broadwell). Linux on demand starts at $0.90 per hour.

gpu & acceleratedx86-64

sizes: 3
vCPUs: 4 – 64
memory: 61 GiB – 732 GiB
accelerator: K80
on-demand from: $0.90

Compare sizes

P2 sizes and prices

Linux, hourly, US East (N. Virginia) (other regions on each size's page)

Size	vCPU	Memory	Accelerator	Local storage	On-demand	Monthly	Spot
p2.xlarge	4	61 GiB	1 × NVIDIA K80	–	$0.90	$657	$0.4249
p2.8xlarge	32	488 GiB	8 × NVIDIA K80	–	$7.20	$5,256	$2.999
p2.16xlarge	64	732 GiB	16 × NVIDIA K80	–	$14.40	$10,512	$5.787

Other gpu & accelerated families on AWS

Dl1 1 Dl2q 1 F1 3 F2 3 G3 3 G3s 1 G4ad 5 G4dn 7 G5 8 G5g 6 G6 8 G6e 8 G6f 4 G7 6 G7e 6 Gr6 2 Gr6f 1 Inf1 4 Inf2 4 P3 3 P3dn 1 P4d 1 P4de 1 P5 2 P5e 1 P5en 1 P6-b200 1 P6-b300 1 Trn1 2 Trn1n 1

P2 FAQ

What sizes does the AWS P2 family have?

P2 has 3 instance types, from p2.xlarge (4 vCPU, 61 GiB) to p2.16xlarge (64 vCPU, 732 GiB). They run on Intel Xeon E5-2686 v4 (Broadwell).

What is the cheapest P2 instance type?

p2.xlarge at $0.90 per hour (Linux, on demand) in US East (N. Virginia), about $657 per month.

What is P2 best for?

P2 is a gpu & accelerated family. GPUs and AI accelerators for training, inference, rendering and video.