atlas
g GPU graphics
6 Generation 6
.
16xlarge 64 vCPU · 256 GiB

$4.312/hr

On-demand in Paris

64 vCPU

EPYC Milan, 2.6 GHz

256 GiB

4 GiB per vCPU

1.9 TB NVMe

Local storage

25 Gbps

Network bandwidth

20 Gbps

EBS bandwidth

x86_64

Architecture

Every way to pay

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

PlanMonthlyYearlySaves

On-demand

Pay by the second, no commitment

$3,148$37,772

Reserved, 1 yr

No upfront, this size and region

$2,049$24,589−35%

Reserved, 3 yr

No upfront, this size and region

$1,445$17,337−54%

What will it cost me?

Enter how you plan to run it.

× g6.16xlarge, 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 Paris would save $8,016 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 64 vCPU · 256 GiB in Paris, ranked by price.

InstanceProcessorGenerationLocal diskPrice/hrvs g6.16xlarge
g6.16xlargeEPYC MilanGen 61.9 TB NVMe$4.312—
g4dn.16xlargeXeon FamilyGen 4900 GB NVMe$5.088+18%
g5.16xlargeEPYC RomeGen 51.9 TB NVMe$5.199+21%

Specifications

API name
g6.16xlarge
Processor
AMD EPYC 7R13 Processor
Local storage
2 × 940 GB NVMe
Family
GPU instance
Clock speed
2.6 GHz
Network
25 Gbps
Generation
Gen 6
Architecture
x86_64
EBS bandwidth
20 Gbps
vCPUs
64
Memory
256 GiB
GPUs
1 · 24 GB