atlas
g GPU graphics
4 Generation 4
d Local NVMe
n Network boost
.
12xlarge 48 vCPU · 192 GiB

$3,855/mo

On-demand in Tokyo

48 vCPU

Xeon Family, 2.5 GHz

192 GiB

4 GiB per vCPU

900 GB NVMe

Local storage

50 Gbps

Network bandwidth

7 Gbps

EBS bandwidth

x86_64

Architecture

Every way to pay

Prices in Tokyo. Bars are relative to on-demand.

PlanMonthlyYearlySaves

On-demand

Pay by the second, no commitment

$3,855$46,262

Reserved, 1 yr

No upfront, this size and region

$2,631$31,571−32%

Reserved, 3 yr

No upfront, this size and region

$1,957$23,486−49%

What will it cost me?

Enter how you plan to run it.

× g4dn.12xlarge, on-demand

/mo

a year

You run these most of the time. A 1-year reservation bills every hour, and would still cost /mo.

Same usage on each planMonthlyYearly
On-demand
Reserved 1 yr
Reserved 3 yr

Reservations bill every hour of the month, whether the instance runs or not.

Other sizes in this family

Price roughly doubles with each step. Pick a size to open it.

Price in every region

Cheapest in US East (N. Virginia). Moving from Tokyo would save $11,992 a year per instance.

Not offered in Calgary , Central , Zurich , Spain , Hyderabad , Jakarta , Melbourne , Malaysia , New Zealand , Thailand , Taipei , UAE , Tel Aviv .

Same shape, other families

Every instance with 48 vCPU · 192 GiB in Tokyo, ranked by price.

InstanceProcessorGenerationLocal diskPrice/movs g4dn.12xlarge
g4dn.12xlargeXeon FamilyGen 4900 GB NVMe$3,855—
g6.12xlargeEPYC MilanGen 6EBS only$4,872+26%
g5.12xlargeEPYC RomeGen 53.8 TB NVMe$6,005+56%

Specifications

API name
g4dn.12xlarge
Processor
Intel Xeon Family
Local storage
1 × 900 GB NVMe
Family
GPU instance
Clock speed
2.5 GHz
Network
50 Gbps
Generation
Gen 4
Architecture
x86_64
EBS bandwidth
7 Gbps
vCPUs
48
Memory
192 GiB
GPUs
4 · 64 GB