inf Inferentia
1 Generation 1
.
24xlarge 96 vCPU · 192 GiB
96 vCPU
192 GiB
EBS only
100 Gbps
14 Gbps
x86_64
Every way to pay
Prices in Mumbai. Bars are relative to on-demand.
| Plan | Monthly | Yearly | Saves | |
|---|---|---|---|---|
On-demand Pay by the second, no commitment | $3,624 | $43,493 | ||
Reserved, 1 yr No upfront, this size and region | $2,283 | $27,401 | −37% | |
Reserved, 3 yr No upfront, this size and region | $1,742 | $20,901 | −52% |
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 Mumbai would save $2,137 a year per instance.
US East (N. Virginia) $4.721 US East (Ohio) $4.721 US West (Oregon) $4.721 Asia Pacific (Mumbai) $4.965 Europe (Stockholm) $5.016 Canada (Central) $5.260 Europe (Ireland) $5.260 Europe (Paris) $5.517 Europe (Milan) $5.530 Europe (London) $5.530 US West (N. California) $5.671
Middle East (Bahrain) $5.786 Asia Pacific (Seoul) $5.812 Asia Pacific (Sydney) $5.902 Europe (Frankfurt) $5.902 AWS GovCloud (US-East) $5.953 AWS GovCloud (US-West) $5.953 Africa (Cape Town) $6.249 Asia Pacific (Tokyo) $6.376 Asia Pacific (Singapore) $6.376 Asia Pacific (Hong Kong) $7.274 South America (São Paulo) $7.800
Not offered in Calgary , Central , Zurich , Spain , Hyderabad , Jakarta , Melbourne , Malaysia , New Zealand , Thailand , Osaka , Taipei , UAE , Tel Aviv .
Specifications
- API name
- inf1.24xlarge
- Processor
- Intel Xeon Platinum 8275CL (Cascade Lake)
- Local storage
- EBS only
- Family
- Machine Learning ASIC Instances
- Clock speed
- —
- Network
- 100 Gbps
- Generation
- Gen 1
- Architecture
- x86_64
- EBS bandwidth
- 14 Gbps
- vCPUs
- 96
- Memory
- 192 GiB
- GPUs
- 16