inf1.24xlarge
Amazon EC2 · Inf1 family
The inf1.24xlarge is a gpu & accelerated Amazon EC2 instance type with 96 vCPUs and 192 GiB of memory, 16 × AWS Inferentia, running on Intel Xeon Platinum 8275CL (Cascade Lake) with 100 Gigabit networking, starting at $4.721 per hour on demand.
- vCPUs
- 96
- memory
- 192 GiB
- accelerator
- 16× Inferentia
- on-demand
- $4.721
- spot
- $1.968
- 1-yr reserved
- $2.974
dedicated
2 GiB per vCPU
128 GiB total
$3,446/mo · us-east-1
−58% vs on-demand
−37% vs on-demand
inf1.24xlarge price by region
22 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $4.721 | $1.968 | $2.974 | $2.269 |
| US East (Ohio)us-east-2cheapestNorth America | $4.721 | $1.264 | $2.974 | $2.269 |
| US West (Oregon)us-west-2cheapestNorth America | $4.721 | $0.8298 | $2.974 | $2.269 |
| Asia Pacific (Mumbai)ap-south-1Asia | $4.965 | $1.662 | $3.128 | $2.386 |
| EU (Stockholm)eu-north-1Europe | $5.016 | $0.5396 | $3.16 | $2.411 |
| Canada (Central)ca-central-1North America | $5.26 | $0.9698 | $3.314 | $2.528 |
| EU (Ireland)eu-west-1Europe | $5.26 | $1.931 | $3.314 | $2.528 |
| EU (Paris)eu-west-3Europe | $5.517 | $0.6349 | $3.476 | $2.651 |
| EU (London)eu-west-2Europe | $5.53 | $1.55 | $3.484 | $2.658 |
| EU (Milan)eu-south-1Europe | $5.53 | $0.7037 | $3.774 | $2.658 |
| US West (N. California)us-west-1North America | $5.671 | $0.6301 | $3.573 | $2.725 |
| Middle East (Bahrain)me-south-1Middle East | $5.786 | $4.365 | $3.949 | $2.781 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $5.812 | $0.663 | $3.661 | $2.793 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $5.902 | $0.8069 | $3.718 | $2.836 |
| EU (Frankfurt)eu-central-1Europe | $5.902 | $0.6837 | $3.718 | $2.836 |
| AWS GovCloud (US-East)us-gov-east-1North America | $5.953 | – | $3.75 | $2.861 |
| AWS GovCloud (US)us-gov-west-1North America | $5.953 | – | $3.75 | $2.861 |
| Africa (Cape Town)af-south-1Africa | $6.249 | $1.341 | $3.937 | $3.003 |
| Asia Pacific (Singapore)ap-southeast-1Asia | $6.376 | $0.67 | $4.017 | $3.45 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $6.376 | $0.7457 | $4.017 | $3.064 |
| Asia Pacific (Hong Kong)ap-east-1Asia | $7.274 | $0.8012 | $4.583 | $3.496 |
| South America (Sao Paulo)sa-east-1South America | $7.80 | $0.78 | $4.914 | $3.749 |
Specifications
compute
- vCPUs
- 96
- Memory
- 192 GiB
- Memory per vCPU
- 2 GiB
- Processor
- Intel Xeon Platinum 8275CL (Cascade Lake)
- CPU vendor
- Intel
- Architecture
- x86-64
- Burstable CPU
- No
storage & network
- Local storage
- Network storage only
- Storage detail
- EBS only
- Network
- 100 Gigabit
- Peak bandwidth
- 100 Gbps
accelerators
- Model
- AWS Inferentia
- Count
- 16
- Memory (total)
- 128 GiB
- Vendor
- AWS
aws details
- API name
inf1.24xlarge- Family
- Inf1
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 22 (Africa, Asia, Europe, Middle East, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $4.721/hr
- Dedicated EBS throughput
- 14000 Mbps
- Enhanced networking
- No
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 76%
Inf1 family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | Spot | 1-yr |
|---|---|---|---|---|---|---|---|---|
| inf1.xlarge | 4 | 8 GiB | 1 × AWS Inferentia | – | $0.228 | $166 | $0.0908 | $0.144 |
| inf1.2xlarge | 8 | 16 GiB | 1 × AWS Inferentia | – | $0.362 | $264 | $0.1695 | $0.228 |
| inf1.6xlarge | 24 | 48 GiB | 4 × AWS Inferentia | – | $1.18 | $861 | $0.5169 | $0.744 |
| inf1.24xlarge | 96 | 192 GiB | 16 × AWS Inferentia | – | $4.721 | $3,446 | $1.968 | $2.974 |
inf1.24xlarge FAQ
How much does inf1.24xlarge cost?
inf1.24xlarge costs $4.721 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $3,446 per month. Across 22 regions the Linux on-demand price ranges from $4.721 in US East (N. Virginia) to $7.80 in South America (Sao Paulo). Spot capacity costs $1.968 per hour (58% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $2.974 per hour.
How many vCPUs and how much memory does inf1.24xlarge have?
inf1.24xlarge has 96 vCPUs and 192 GiB of memory (2 GiB per vCPU), running on Intel Xeon Platinum 8275CL (Cascade Lake). It is a gpu & accelerated instance type in the Inf1 family.
What accelerator does inf1.24xlarge have?
inf1.24xlarge has 16 × AWS Inferentia with 128 GiB of accelerator memory in total.