48 vCPU
192 GiB
3.8 TB NVMe
40 Gbps
16 Gbps
x86_64
Every way to pay
Prices in Tokyo. Bars are relative to on-demand.
| Plan | Monthly | Yearly | Saves | |
|---|---|---|---|---|
On-demand Pay by the second, no commitment | $6,005 | $72,061 | ||
Reserved, 1 yr No upfront, this size and region | $3,783 | $45,398 | −37% | |
Reserved, 3 yr No upfront, this size and region | $2,594 | $31,130 | −57% |
What will it cost me?
Enter how you plan to run it.
/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 plan | Monthly | Yearly |
|---|---|---|
| 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 $22,374 a year per instance.
Not offered in N. California , Calgary , Central , US-East , US-West , Zurich , Milan , Hyderabad , Singapore , Melbourne , Malaysia , New Zealand , Thailand , Osaka , Taipei , Bahrain , Cape Town .
Same shape, other families
Every instance with 48 vCPU · 192 GiB in Tokyo, ranked by price.
| Instance | Processor | Generation | Local disk | Price/hr | vs g5.12xlarge | |
|---|---|---|---|---|---|---|
| g4dn.12xlarge | Xeon Family | Gen 4 | 900 GB NVMe | $5.281 | −36% | |
| g6.12xlarge | EPYC Milan | Gen 6 | EBS only | $6.674 | −19% | |
| g5.12xlarge | EPYC Rome | Gen 5 | 3.8 TB NVMe | $8.226 | — |
Specifications
- API name
- g5.12xlarge
- Processor
- AMD EPYC 7R32
- Local storage
- 1 × 3.8 TB NVMe
- Family
- GPU instance
- Clock speed
- 2.8 GHz
- Network
- 40 Gbps
- Generation
- Gen 5
- Architecture
- x86_64
- EBS bandwidth
- 16 Gbps
- vCPUs
- 48
- Memory
- 192 GiB
- GPUs
- 4 · 96 GB