atlas
g GPU graphics
6 Generation 6
.
2xlarge 8 vCPU · 32 GiB

$403/mo

3-yr reserved in Seoul

8 vCPU

EPYC Milan, 2.6 GHz

32 GiB

4 GiB per vCPU

450 GB NVMe

Local storage

Up to 10 Gbps

Network bandwidth

Up to 5 Gbps

EBS bandwidth

x86_64

Architecture

Every way to pay

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

PlanMonthlyYearlySaves

On-demand

Pay by the second, no commitment

$878$10,530

Reserved, 1 yr

No upfront, this size and region

$571$6,855−35%

Reserved, 3 yr

No upfront, this size and region

$403$4,833−54%

What will it cost me?

Enter how you plan to run it.

× g6.2xlarge, 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 Seoul would save $903 a year per instance.

Not offered in N. California , Calgary , Central , Ireland , Milan , Singapore , Jakarta , Melbourne , New Zealand , Thailand , Osaka , Hong Kong , Taipei , Bahrain , Tel Aviv , Cape Town .

Same shape, other families

Every instance with 8 vCPU · 32 GiB in Seoul, ranked by price.

InstanceProcessorGenerationLocal diskPrice/movs g6.2xlarge
g4dn.2xlargeXeon FamilyGen 4225 GB NVMe$292−28%
g6.2xlargeEPYC MilanGen 6450 GB NVMe$403—
g5.2xlargeEPYC RomeGen 5450 GB NVMe$470+17%

Specifications

API name
g6.2xlarge
Processor
AMD EPYC 7R13 Processor
Local storage
1 × 450 GB NVMe
Family
GPU instance
Clock speed
2.6 GHz
Network
Up to 10 Gbps
Generation
Gen 6
Architecture
x86_64
EBS bandwidth
Up to 5 Gbps
vCPUs
8
Memory
32 GiB
GPUs
1 · 24 GB