With Amazon Elastic Inference, you pay only for the accelerator hours you use. There are no upfront costs or minimum fees. There is no charge for the AWS-optimized versions of the TensorFlow and Apache MXNet deep learning frameworks. There are no additional charges for AWS PrivateLink VPC Endpoints to Amazon Elastic Inference, as long as you have at least one instance configured with an accelerator, that is running in an Availability Zone where a VPC endpoint is provisioned.

Amazon Elastic Inference accelerator pricing for Amazon EC2

Following is the Amazon Elastic Inference pricing with Amazon EC2 instances. For Amazon Elastic Inference pricing with Amazon SageMaker instances, please see the Model Deployment section on the Amazon SageMaker pricing page.

  • US East
  • US West
  • EU
  • Asia Pacific
  • US East
  • US East (N. Virginia) Region

    Accelerator type Throughput in trillion 32-bit floating point operations per second (FP-32 TFLOPS) Throughput in trillion 16-bit floating point operations per second (FP-16 TFLOPS) Memory Pricing
    eia1.medium 1 FP-32 TFLOPS 8 FP-16 TFLOPS 1 GB $0.130 per hour
    eia1.large 2 FP-32 TFLOPS 16 FP-16 TFLOPS 2 GB $0.260 per hour
    eia1.xlarge 4 FP-32 TFLOPS 32 FP-16 TFLOPS 4 GB $0.520 per hour

    US East (Ohio) Region

    Accelerator type Throughput in trillion 32-bit floating point operations per second (FP-32 TFLOPS) Throughput in trillion 16-bit floating point operations per second (FP-16 TFLOPS) Memory Pricing
    eia1.medium 1 FP-32 TFLOPS 8 FP-16 TFLOPS 1 GB $0.130 per hour
    eia1.large 2 FP-32 TFLOPS 16 FP-16 TFLOPS 2 GB $0.260 per hour
    eia1.xlarge 4 FP-32 TFLOPS 32 FP-16 TFLOPS 4 GB $0.520 per hour
  • US West
  • US West (Oregon) Region

    Accelerator type Throughput in trillion 32-bit floating point operations per second (FP-32 TFLOPS) Throughput in trillion 16-bit floating point operations per second (FP-16 TFLOPS) Memory Pricing
    eia1.medium 1 FP-32 TFLOPS 8 FP-16 TFLOPS 1 GB $0.130 per hour
    eia1.large 2 FP-32 TFLOPS 16 FP-16 TFLOPS 2 GB $0.260 per hour
    eia1.xlarge 4 FP-32 TFLOPS 32 FP-16 TFLOPS 4 GB $0.520 per hour
  • EU
  • EU (Ireland) Region

    Accelerator type Throughput in trillion 32-bit floating point operations per second (FP-32 TFLOPS) Throughput in trillion 16-bit floating point operations per second (FP-16 TFLOPS) Memory Pricing
    eia1.medium 1 FP-32 TFLOPS 8 FP-16 TFLOPS 1 GB $0.140 per hour
    eia1.large 2 FP-32 TFLOPS 16 FP-16 TFLOPS 2 GB $0.280 per hour
    eia1.xlarge 4 FP-32 TFLOPS 32 FP-16 TFLOPS 4 GB $0.560 per hour
  • Asia Pacific
  • Asia Pacific (Tokyo) Region

    Accelerator type Throughput in trillion 32-bit floating point operations per second (FP-32 TFLOPS) Throughput in trillion 16-bit floating point operations per second (FP-16 TFLOPS) Memory Pricing
    eia1.medium 1 FP-32 TFLOPS 8 FP-16 TFLOPS 1 GB $0.220 per hour
    eia1.large 2 FP-32 TFLOPS 16 FP-16 TFLOPS 2 GB $0.450 per hour
    eia1.xlarge 4 FP-32 TFLOPS 32 FP-16 TFLOPS 4 GB $0.890 per hour

    Asia Pacific (Seoul) Region

    Accelerator type Throughput in trillion 32-bit floating point operations per second (FP-32 TFLOPS) Throughput in trillion 16-bit floating point operations per second (FP-16 TFLOPS) Memory Pricing
    eia1.medium 1 FP-32 TFLOPS 8 FP-16 TFLOPS 1 GB $0.210 per hour
    eia1.large 2 FP-32 TFLOPS 16 FP-16 TFLOPS 2 GB $0.430 per hour
    eia1.xlarge 4 FP-32 TFLOPS 32 FP-16 TFLOPS 4 GB $0.850 per hour

Pricing example 1

Let’s say you are running a streaming video analytics application. To run deep learning inference to analyze a single video stream in this application, you can choose an Amazon EC2 c5.xlarge instance configured with an Amazon Elastic Inference eia1.medium accelerator. Your hourly cost to run this deep learning model in the US East (N.Virginia) region is:

Hourly price of c5.xlarge instance: $0.17
Hourly price of a eia1.medium accelerator: $0.13
Total hourly price of the instance configured with the accelerator: $0.30
Total monthly cost = $0.30 * 24 * 31 = $223.20

Pricing example 2

Let’s say you are running a web application that analyzes images uploaded by your end users in real time. To use deep learning inference for this application, you can choose an Amazon EC2 c5.large instance configured with an Amazon Elastic Inference eia1.medium accelerator and scale this instance capacity using Amazon EC2 Auto Scaling to meet the demands of your application. Your hourly cost for this combination in the US East (N.Virginia) region is:

Hourly price of c5.large instance: $0.085
Hourly price of a eia1.medium accelerator: $0.13
Total hourly price of the instance configured with the accelerator: $0.215
Total monthly cost = $0.215 * 24 * 31 = $159.96

Additional pricing resources

TCO Calculator

Calculate your total cost of ownership (TCO)

Simple Monthly Calculator

Easily calculator your monthly costs with AWS

Economics Resource Center

Additional resources for switching to AWS

Product-Page_Standard-Icons_01_Product-Features_SqInk
Learn how to get started

Learn more from tutorials and documentation.

Learn more 
Product-Page_Standard-Icons_02_Sign-Up_SqInk
Sign up for a free account

Instantly get access to the AWS Free Tier. 

Sign up 
Product-Page_Standard-Icons_03_Start-Building_SqInk
Start building in the console

Get started with Amazon Elastic Inference on Amazon SageMaker or Amazon EC2.

Sign in