inf1.2xlarge
Amazon EC2 · Inf1 family
The inf1.2xlarge is a gpu & accelerated Amazon EC2 instance type with 8 vCPUs and 16 GiB of memory, 1 × AWS Inferentia, running on Intel Xeon Platinum 8275CL (Cascade Lake) with up to 25 Gigabit networking, starting at $0.362 per hour on demand.
- vCPUs
- 8
- memory
- 16 GiB
- accelerator
- 1× Inferentia
- on-demand
- $0.362
- spot
- $0.1695
- 1-yr reserved
- $0.228
dedicated
2 GiB per vCPU
8 GiB total
$264/mo · us-east-1
−53% vs on-demand
−37% vs on-demand
inf1.2xlarge price by region
21 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $0.362 | $0.1695 | $0.228 | $0.174 |
| US East (Ohio)us-east-2cheapestNorth America | $0.362 | $0.1422 | $0.228 | $0.174 |
| US West (Oregon)us-west-2cheapestNorth America | $0.362 | $0.1276 | $0.228 | $0.174 |
| Asia Pacific (Mumbai)ap-south-1Asia | $0.381 | $0.1463 | $0.24 | $0.183 |
| EU (Stockholm)eu-north-1Europe | $0.385 | $0.0909 | $0.242 | $0.185 |
| Canada (Central)ca-central-1North America | $0.403 | $0.0942 | $0.254 | $0.194 |
| EU (Ireland)eu-west-1Europe | $0.403 | $0.165 | $0.254 | $0.194 |
| EU (Paris)eu-west-3Europe | $0.423 | $0.1124 | $0.266 | $0.203 |
| EU (London)eu-west-2Europe | $0.424 | $0.1311 | $0.267 | $0.204 |
| EU (Milan)eu-south-1Europe | $0.424 | $0.0608 | $0.289 | $0.204 |
| US West (N. California)us-west-1North America | $0.435 | $0.1364 | $0.274 | $0.209 |
| Middle East (Bahrain)me-south-1Middle East | $0.444 | $0.1172 | $0.303 | $0.213 |
| Asia Pacific (Seoul)ap-northeast-2Asia | $0.446 | $0.1789 | $0.281 | $0.214 |
| Asia Pacific (Sydney)ap-southeast-2Oceania | $0.453 | $0.1944 | $0.285 | $0.217 |
| EU (Frankfurt)eu-central-1Europe | $0.453 | $0.1594 | $0.285 | $0.217 |
| AWS GovCloud (US-East)us-gov-east-1North America | $0.456 | – | $0.288 | $0.219 |
| AWS GovCloud (US)us-gov-west-1North America | $0.456 | – | $0.288 | $0.219 |
| Asia Pacific (Singapore)ap-southeast-1Asia | $0.489 | $0.1929 | $0.308 | $0.265 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $0.489 | $0.1667 | $0.308 | $0.235 |
| Asia Pacific (Hong Kong)ap-east-1Asia | $0.558 | $0.1315 | $0.351 | $0.268 |
| South America (Sao Paulo)sa-east-1South America | $0.598 | $0.0799 | $0.377 | $0.287 |
Specifications
compute
- vCPUs
- 8
- Memory
- 16 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
- Up to 25 Gigabit
- Peak bandwidth
- 25 Gbps
accelerators
- Model
- AWS Inferentia
- Count
- 1
- Memory (total)
- 8 GiB
- Vendor
- AWS
aws details
- API name
inf1.2xlarge- Family
- Inf1
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 21 (Asia, Europe, Middle East, North America, Oceania, South America)
- Cheapest region
- US East (N. Virginia) · $0.362/hr
- Dedicated EBS throughput
- 875 Mbps
- Enhanced networking
- No
- Spot interruption rate (us-east-1)
- >20%
- Spot savings vs on-demand (us-east-1)
- 73%
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 |
inf1.2xlarge FAQ
How much does inf1.2xlarge cost?
inf1.2xlarge costs $0.362 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $264 per month. Across 21 regions the Linux on-demand price ranges from $0.362 in US East (N. Virginia) to $0.598 in South America (Sao Paulo). Spot capacity costs $0.1695 per hour (53% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $0.228 per hour.
How many vCPUs and how much memory does inf1.2xlarge have?
inf1.2xlarge has 8 vCPUs and 16 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 inf1.2xlarge have?
inf1.2xlarge has 1 × AWS Inferentia with 8 GiB of accelerator memory in total.