With Amazon SageMaker, you pay only for what you use. Building, training and hosting is billed by the second, with no minimum fees and no upfront commitments. Pricing within Amazon SageMaker is broken down by on-demand ML instances, ML storage, and fees for data processing in notebooks and hosting instances.
Free Tier
As part of the AWS Free Tier, you can get started with Amazon SageMaker for free. For the first two months after sign-up, you are offered a monthly free tier of 250 hours of t2.medium notebook usage for building your models, plus 50 hours of m4.xlarge for training, and a combined total of 125 hours of m4.xlarge for deploying your machine learning models for real-time inferencing and batch transform with Amazon SageMaker.
On-Demand ML instances
For building, training, and deploying your models on Amazon SageMaker, on-demand ML instances let you pay for machine learning compute capacity by the second, with a one-minute minimum, with no long-term commitments. This frees you from the costs and complexities of planning, purchasing, and maintaining hardware, and transforms what are commonly large fixed costs into much smaller variable costs. Pricing is per instance-hour consumed for each instance, from the time an instance is available for use until it is terminated or stopped. Each partial instance-hour consumed will be billed per-second, with a one-minute minimum.
Inference Acceleration
When building and deploying your model, you have the option to attach fractional GPU compute capacity to your Amazon SageMaker endpoint using Amazon Elastic Inference in select AWS Regions. If you choose to add an Amazon Elastic Inference accelerator, you will be billed for the accelerator hours. For more details on inference acceleration with Amazon SageMaker, see the Amazon Elastic Inference website. For regional availability of Amazon Elastic Inference, see the Region table.
ML General Purpose storage
For model training, Amazon SageMaker provides you with the ability to select up to 6 TB of associated General Purpose (SSD) storage capacity for your training data. For notebook, model training, and model hosting, General Purpose (SSD) storage capacity is also added for temporary data storage. With General Purpose (SSD), you will be charged for this storage. However, you will not be charged for the I/Os consumed.
Data processed
During building and hosting your models, data processed by Amazon SageMaker is pulled into and out of notebook instances, and model hosting instances.
US East (N. Virginia)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0464 ml.t2.large $0.1299 ml.t2.xlarge $0.2598 ml.t2.2xlarge $0.5197 ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS** Memory Price per Hour eia1.medium 1 8 1 GB
$0.182 eia1.large 2 16 2 GB
$0.364 eia1.xlarge 4 32 4 GB
$0.728 * FP-32 TFLOPS = trillion 32-bit floating point operations per second
** FP-16 TFLOPS = trillion 16-bit floating point operations per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451
ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.xlarge $0.238
ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114
ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.065 ml.t2.large $0.1299 ml.t2.xlarge $0.2598 ml.t2.2xlarge $0.5197 ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451 ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.large $0.119 ml.c5.xlarge $0.238 ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.large $0.14 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114 ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16.xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272
Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS** Memory Price per Hour eia1.medium 1 8 1 GB
$0.182 eia1.large 2 16 2 GB
$0.364 eia1.xlarge 4 32 4 GB
$0.728 * FP-32 TFLOPS = trillion 32-bit floating point operations per second
** FP-16 TFLOPS = trillion 16-bit floating point operations per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451
ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.xlarge $0.238
ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114
ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
US East (Ohio)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0464 ml.t2.large $0.1299 ml.t2.xlarge $0.2598 ml.t2.2xlarge $0.5197 ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS* Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.182 eia1.large 2 16 2 GB
$0.364 eia1.xlarge 4 32 1 GB $0.728 *FP-32 TFLOPS = trilion 32-bit floating point operations per second
**FP-16 TFLOPS = trillion 16-bit floating point operations per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451
ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.xlarge $0.238
ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114
ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.065 ml.t2.large $0.1299 ml.t2.xlarge $0.2598 ml.t2.2xlarge $0.5197 ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451 ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.large $0.119 ml.c5.xlarge $0.238 ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.large $0.14 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114 ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p216.xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272
Inference AccelerationAccelerator Throughput in FP-32 TFLOPS* Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.182 eia1.large 2 16 2 GB
$0.364 eia1.xlarge 4 32 1 GB $0.728 *FP-32 TFLOPS = trilion 32-bit floating point operations per second
**FP-16 TFLOPS = trillion 16-bit floating point operations per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451
ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.xlarge $0.238
ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114
ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
US West (Oregon)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0464 ml.t2.large $0.1299 ml.t2.xlarge $0.2598 ml.t2.2xlarge $0.5197 ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.182 eia1.large 2 16 2 GB
$0.364 eia1.xlarge 4 32
4 GB
$0.728 * FP-32 TFLOPS = trillion 32-bit floating point instructions per second
** FP-16 TFLOPS = trillion 16-bit floating point instructions per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451
ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.xlarge $0.238
ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114
ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.065 ml.t2.large $0.1299 ml.t2.xlarge $0.2598 ml.t2.2xlarge $0.5197 ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451 ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.large $0.119 ml.c5.xlarge $0.238 ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.large $0.14 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114 ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p216.xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272
Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.182 eia1.large 2 16 2 GB
$0.364 eia1.xlarge 4 32
4 GB
$0.728 * FP-32 TFLOPS = trillion 32-bit floating point instructions per second
** FP-16 TFLOPS = trillion 16-bit floating point instructions per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.134 ml.m5.xlarge $0.269 ml.m5.2xlarge $0.538 ml.m5.4xlarge $1.075 ml.m5.12xlarge $3.226 ml.m5.24xlarge $6.451
ml.m4.xlarge $0.28 ml.m4.2xlarge $0.56 ml.m4.4xlarge $1.12 ml.m4.10xlarge $2.80 ml.m4.16xlarge $4.48 Compute Instances - Current Generation ml.c5.xlarge $0.238
ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.279 ml.c4.2xlarge $0.557 ml.c4.4xlarge $1.114
ml.c4.8xlarge $2.227 GPU Instances - Current Generation ml.p2.xlarge $1.26 ml.p2.8xlarge $10.08 ml.p2.16xlarge $20.16 ml.p3.2xlarge $4.284 ml.p3.8xlarge $17.136 ml.p3.16xlarge $34.272 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.14 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
US West (N. California)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0552 ml.t2.large $0.1546 ml.t2.xlarge $0.3091 ml.t2.2xlarge $0.6182 ml.m4.xlarge $0.328 ml.m4.2xlarge $0.655 ml.m4.4xlarge $1.31 ml.m4.10xlarge $3.276 ml.m4.16xlarge $5.242 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.157 ml.m5.xlarge $0.314 ml.m5.2xlarge $0.627 ml.m5.4xlarge $1.254 ml.m5.12xlarge $3.763 ml.m5.24xlarge $7.526
ml.m4.xlarge $0.328 ml.m4.2xlarge $0.655 ml.m4.4xlarge $1.31 ml.m4.10xlarge $3.276 ml.m4.16xlarge $5.242 Compute Instances - Current Generation ml.c5.xlarge $0.297
ml.c5.2xlarge $0.594 ml.c5.4xlarge $1.187 ml.c5.9xlarge $2.671 ml.c5.18xlarge $5.342 ml.c4.xlarge $0.349 ml.c4.2xlarge $0.697 ml.c4.4xlarge $1.396
ml.c4.8xlarge $2.79 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.077 ml.t2.large $0.155 ml.t2.xlarge $0.309 ml.t2.2xlarge $0.618 ml.m5.large $0.157 ml.m5.xlarge $0.314 ml.m5.2xlarge $0.627 ml.m5.4xlarge $1.254 ml.m5.12xlarge $3.763 ml.m5.24xlarge $7.526 ml.m4.xlarge $0.328 ml.m4.2xlarge $0.655 ml.m4.4xlarge $1.31 ml.m4.10xlarge $3.276 ml.m4.16xlarge $5.242 Compute Instances - Current Generation ml.c5.large $0.148 ml.c5.xlarge $0.297 ml.c5.2xlarge $0.594 ml.c5.4xlarge $1.187 ml.c5.9xlarge $2.671 ml.c5.18xlarge $5.342 ml.c4.large $0.174 ml.c4.xlarge $0.349 ml.c4.2xlarge $0.697 ml.c4.4xlarge $1.396 ml.c4.8xlarge $2.79 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.157 ml.m5.xlarge $0.314 ml.m5.2xlarge $0.627 ml.m5.4xlarge $1.254 ml.m5.12xlarge $3.763 ml.m5.24xlarge $7.526
ml.m4.xlarge $0.328 ml.m4.2xlarge $0.655 ml.m4.4xlarge $1.31 ml.m4.10xlarge $3.276 ml.m4.16xlarge $5.242 Compute Instances - Current Generation ml.c5.xlarge $0.297
ml.c5.2xlarge $0.594 ml.c5.4xlarge $1.187 ml.c5.9xlarge $2.671 ml.c5.18xlarge $5.342 ml.c4.xlarge $0.349 ml.c4.2xlarge $0.697 ml.c4.4xlarge $1.396
ml.c4.8xlarge $2.79 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
AWS GovCloud (US)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0544 ml.t2.large $0.1523 ml.t2.xlarge $0.3046 ml.t2.2xlarge $0.6093 ml.m4.xlarge $0.353 ml.m4.2xlarge $0.672 ml.m4.4xlarge $1.411 ml.m4.10xlarge $3.528 ml.m4.16xlarge $5.645 GPU Instances - Current Generation ml.p2.xlarge $1.512 ml.p2.8xlarge $12.096 ml.p2.16xlarge $24.192 ml.p3.2xlarge $5.141 ml.p3.8xlarge $20.563 ml.p3.16xlarge $41.126 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.169 ml.m5.xlarge $0.339 ml.m5.2xlarge $0.678 ml.m5.4xlarge $1.355 ml.m5.12xlarge $4.066 ml.m5.24xlarge $8.131 ml.m4.xlarge $0.353 ml.m4.2xlarge $0.706 ml.m4.4xlarge $1.411 ml.m4.10xlarge $3.528 ml.m4.16xlarge $5.645 Compute Instances - Current Generation ml.c5.xlarge $0.286 ml.c5.2xlarge $0.571 ml.c5.4xlarge $1.142 ml.c5.9xlarge $2.570 ml.c5.18xlarge $5.141 ml.c4.xlarge $0.335 ml.c4.2xlarge $0.671 ml.c4.4xlarge
$1.341 ml.c4.8xlarge $2.681 GPU Instances - Current Generation ml.p2.xlarge $1.512 ml.p2.8xlarge $12.096 ml.p2.16xlarge $24.192 ml.p3.2xlarge $5.141 ml.p3.8xlarge $20.563 ml.p3.16xlarge $41.126 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0762 ml.t2.large $0.1523 ml.t2.xlarge $0.3046 ml.t2.2xlarge $0.6093 ml.m5.large $0.169 ml.m5.xlarge $0.339 ml.m5.2xlarge $0.678 ml.m5.4xlarge $1.355 ml.m5.12xlarge $4.066 ml.m5.24xlarge $8.131 ml.m4.xlarge $0.353 ml.m4.2xlarge $0.706 ml.m4.4xlarge $1.411 ml.m4.10xlarge $3.528 ml.m4.16xlarge $5.645 Compute Instances - Current Generation ml.c5.large $0.143 ml.c5.xlarge $0.286 ml.c5.2xlarge $0.571 ml.c5.4xlarge $1.142 ml.c5.9xlarge $2.570 ml.c5.18xlarge $5.141 ml.c4.large $0.168 ml.c4.xlarge $0.335 ml.c4.2xlarge $0.671 ml.c4.4xlarge $1.341 ml.c4.8xlarge $2.681 GPU Instances - Current Generation ml.p2.xlarge $1.512 ml.p2.8xlarge $12.096 ml.p2.16xlarge $24.192 ml.p3.2xlarge $5.141 ml.p3.8xlarge $20.563 ml.p3.16xlarge $41.126 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.169 ml.m5.xlarge $0.339 ml.m5.2xlarge $0.678 ml.m5.4xlarge $1.355 ml.m5.12xlarge $4.066 ml.m5.24xlarge $8.131 ml.m4.xlarge $0.353 ml.m4.2xlarge $0.706 ml.m4.4xlarge $1.411 ml.m4.10xlarge $3.528 ml.m4.16xlarge $5.645 Compute Instances - Current Generation ml.c5.xlarge $0.286 ml.c5.2xlarge $0.571 ml.c5.4xlarge $1.142 ml.c5.9xlarge $2.570 ml.c5.18xlarge $5.141 ml.c4.xlarge $0.335 ml.c4.2xlarge $0.671 ml.c4.4xlarge
$1.341 ml.c4.8xlarge $2.681 GPU Instances - Current Generation ml.p2.xlarge $1.512 ml.p2.8xlarge $12.096 ml.p2.16xlarge $24.192 ml.p3.2xlarge $5.141 ml.p3.8xlarge $20.563 ml.p3.16xlarge $41.126 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
Canada Central (Montreal)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0512 ml.t2.large $0.1434 ml.t2.xlarge $0.2867 ml.t2.2xlarge $0.5734 ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 GPU Instances - Current Generation ml.p3.2xlarge $4.712 ml.p3.8xlarge $18.85 ml.p3.16xlarge $37.699 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.15 ml.m5.xlarge $0.30 ml.m5.2xlarge $0.599 ml.m5.4xlarge $1.198 ml.m5.12xlarge $3.595 ml.m5.24xlarge $7.19
ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 Compute Instances - Current Generation ml.c5.xlarge $0.266
ml.c5.2xlarge $0.521 ml.c5.4xlarge $1.042 ml.c5.9xlarge $2.344 ml.c5.18xlarge $4.687 ml.c4.xlarge $0.305 ml.c4.2xlarge $0.613 ml.c4.4xlarge $1.226
ml.c4.8xlarge $2.45 GPU Instances - Current Generation ml.p3.2xlarge $4.712 ml.p3.8xlarge $18.85 ml.p3.16xlarge $37.699 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.072 ml.t2.large $0.143 ml.t2.xlarge $0.287 ml.t2.2xlarge $0.573 ml.m5.large $0.15 ml.m5.xlarge $0.30 ml.m5.2xlarge $0.599 ml.m5.4xlarge $1.198 ml.m5.12xlarge $3.595 ml.m5.24xlarge $7.19 ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 Compute Instances - Current Generation ml.c5.large $0.13 ml.c5.xlarge $0.26 ml.c5.2xlarge $0.521 ml.c5.4xlarge $1.042 ml.c5.9xlarge $2.344 ml.c5.18xlarge $4.687 ml.c4.large $0.154 ml.c4.xlarge $0.305 ml.c4.2xlarge $0.613 ml.c4.4xlarge $1.226 ml.c4.8xlarge $2.45 GPU Instances - Current Generation ml.p3.2xlarge $4.712 ml.p3.8xlarge $18.85 ml.p3.16xlarge $37.699
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.15 ml.m5.xlarge $0.30 ml.m5.2xlarge $0.599 ml.m5.4xlarge $1.198 ml.m5.12xlarge $3.595 ml.m5.24xlarge $7.19
ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 Compute Instances - Current Generation ml.c5.xlarge $0.26
ml.c5.2xlarge $0.521 ml.c5.4xlarge $1.042 ml.c5.9xlarge $2.344 ml.c5.18xlarge $4.687 ml.c4.xlarge $0.305 ml.c4.2xlarge $0.613 ml.c4.4xlarge $1.226
ml.c4.8xlarge $2.45 GPU Instances - Current Generation ml.p3.2xlarge $4.712 ml.p3.8xlarge $18.85 ml.p3.16xlarge $37.699 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
EU (Ireland)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.05 ml.t2.large $0.1411 ml.t2.xlarge $0.2822 ml.t2.2xlarge $0.5645 ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 GPU Instances - Current Generation ml.p2.xlarge $1.361 ml.p2.8xlarge $10.886 ml.p2.16xlarge $21.773 ml.p3.2xlarge $4.627 ml.p3.8xlarge $18.508 ml.p3.16xlarge $37.016 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.196 eia1.large 2 16 2 GB
$0.392 eia1.xlarge 4 32 4 GB
$0.784
* FP-32 TFLOPS = trillion 32-bit floating point instructions per second
** FP-16 TFLOPS = trillion 16-bit floating point instructions per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.15 ml.m5.xlarge $0.3 ml.m5.2xlarge $0.599 ml.m5.4xlarge $1.198 ml.m5.12xlarge $3.595 ml.m5.24xlarge $7.19 ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 Compute Instances - Current Generation ml.c5.xlarge $0.269 ml.c5.2xlarge $0.538 ml.c5.4xlarge $1.075 ml.c5.9xlarge $2.419 ml.c5.18xlarge $4.838 ml.c4.xlarge $0.316 ml.c4.2xlarge $0.634 ml.c4.4xlarge
$1.267 ml.c4.8xlarge $2.535 GPU Instances - Current Generation ml.p2.xlarge $1.361 ml.p2.8xlarge $10.886 ml.p2.16xlarge $21.773 ml.p3.2xlarge $4.627 ml.p3.8xlarge $18.508 ml.p3.16xlarge $37.016 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.07 ml.t2.large $0.1411 ml.t2.xlarge $0.2822 ml.t2.2xlarge $0.5645 ml.m5.large $0.15 ml.m5.xlarge $0.30 ml.m5.2xlarge $0.599 ml.m5.4xlarge $1.198 ml.m5.12xlarge $3.595 ml.m5.24xlarge $7.19 ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 Compute Instances - Current Generation ml.c5.large $0.134 ml.c5.xlarge $0.269 ml.c5.2xlarge $0.538 ml.c5.4xlarge $1.075 ml.c5.9xlarge $2.419 ml.c5.18xlarge $4.838 ml.c4.large $0.158 ml.c4.xlarge $0.316 ml.c4.2xlarge $0.634 ml.c4.4xlarge $1.267 ml.c4.8xlarge $2.535 GPU Instances - Current Generation ml.p2.xlarge $1.361 ml.p2.8xlarge $10.886 ml.p2.16xlarge $21.773 ml.p3.2xlarge $4.627 ml.p3.8xlarge $18.508 ml.p3.16xlarge $37.016 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.196 eia1.large 2 16 2 GB
$0.392 eia1.xlarge 4 32 4 GB
$0.784
* FP-32 TFLOPS = trillion 32-bit floating point instructions per second
** FP-16 TFLOPS = trillion 16-bit floating point instructions per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.15 ml.m5.xlarge $0.3 ml.m5.2xlarge $0.599 ml.m5.4xlarge $1.198 ml.m5.12xlarge $3.595 ml.m5.24xlarge $7.19 ml.m4.xlarge $0.311 ml.m4.2xlarge $0.622 ml.m4.4xlarge $1.243 ml.m4.10xlarge $3.108 ml.m4.16xlarge $4.973 Compute Instances - Current Generation ml.c5.xlarge $0.269 ml.c5.2xlarge $0.538 ml.c5.4xlarge $1.075 ml.c5.9xlarge $2.419 ml.c5.18xlarge $4.838 ml.c4.xlarge $0.316 ml.c4.2xlarge $0.634 ml.c4.4xlarge
$1.267 ml.c4.8xlarge $2.535 GPU Instances - Current Generation ml.p2.xlarge $1.361 ml.p2.8xlarge $10.886 ml.p2.16xlarge $21.773 ml.p3.2xlarge $4.627 ml.p3.8xlarge $18.508 ml.p3.16xlarge $37.016 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
EU (Frankfurt)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0536 ml.t2.large $0.1501 ml.t2.xlarge $0.3002 ml.t2.2xlarge $0.6003 ml.m4.xlarge $0.336 ml.m4.2xlarge $0.672 ml.m4.4xlarge $1.344 ml.m4.10xlarge $3.36 ml.m4.16xlarge $5.376 GPU Instances - Current Generation ml.p2.xlarge $1.856 ml.p2.8xlarge $14.851 ml.p2.16xlarge $29.702 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.1666 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.161 ml.m5.xlarge $0.322 ml.m5.2xlarge $0.644 ml.m5.4xlarge $1.288 ml.m5.12xlarge $3.864 ml.m5.24xlarge $7.728 ml.m4.xlarge $0.336 ml.m4.2xlarge $0.672 ml.m4.4xlarge $1.344 ml.m4.10xlarge $3.36 ml.m4.16xlarge $5.376 Compute Instances - Current Generation ml.c5.xlarge $0.272 ml.c5.2xlarge $0.543 ml.c5.4xlarge $1.086 ml.c5.9xlarge $2.444 ml.c5.18xlarge $4.889 ml.c4.xlarge $0.318 ml.c4.2xlarge $0.636 ml.c4.4xlarge
$1.273 ml.c4.8xlarge $2.544 GPU Instances - Current Generation ml.p2.xlarge $1.856 ml.p2.8xlarge $14.851 ml.p2.16xlarge $29.702 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.075 ml.t2.large $0.1501 ml.t2.xlarge $0.3002 ml.t2.2xlarge $0.6003 ml.m5.large $0.161 ml.m5.xlarge $0.322 ml.m5.2xlarge $0.644 ml.m5.4xlarge $1.288 ml.m5.12xlarge $3.864 ml.m5.24xlarge $7.728 ml.m4.xlarge $0.336 ml.m4.2xlarge $0.672 ml.m4.4xlarge $1.344 ml.m4.10xlarge $3.36 ml.m4.16xlarge $5.376 Compute Instances - Current Generation ml.c5.large $0.136 ml.c5.xlarge $0.272 ml.c5.2xlarge $0.543 ml.c5.4xlarge $1.086 ml.c5.9xlarge $2.444 ml.c5.18xlarge $4.889 ml.c4.large $0.16 ml.c4.xlarge $0.318 ml.c4.2xlarge $0.636 ml.c4.4xlarge $1.273 ml.c4.8xlarge $2.544 GPU Instances - Current Generation ml.p2.xlarge $1.856 ml.p2.8xlarge $14.851 ml.p2.16xlarge $29.702 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.161 ml.m5.xlarge $0.322 ml.m5.2xlarge $0.644 ml.m5.4xlarge $1.288 ml.m5.12xlarge $3.864 ml.m5.24xlarge $7.728 ml.m4.xlarge $0.336 ml.m4.2xlarge $0.672 ml.m4.4xlarge $1.344 ml.m4.10xlarge $3.36 ml.m4.16xlarge $5.376 Compute Instances - Current Generation ml.c5.xlarge $0.272 ml.c5.2xlarge $0.543 ml.c5.4xlarge $1.086 ml.c5.9xlarge $2.444 ml.c5.18xlarge $4.889 ml.c4.xlarge $0.318 ml.c4.2xlarge $0.636 ml.c4.4xlarge
$1.273 ml.c4.8xlarge $2.544 GPU Instances - Current Generation ml.p2.xlarge $1.856 ml.p2.8xlarge $14.851 ml.p2.16xlarge $29.702 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.154 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
EU (London)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0520 ml.t2.large $0.1478 ml.t2.xlarge $0.2957 ml.t2.2xlarge $0.5914 ml.m4.xlarge $0.325 ml.m4.2xlarge $0.65 ml.m4.4xlarge $1.299 ml.m4.10xlarge $3.248 ml.m4.16xlarge $5.197 GPU Instances - Current Generation ml.p3.2xlarge $5.025 ml.p3.8xlarge $20.098 ml.p3.16xlarge $40.197 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.162 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.155 ml.m5.xlarge $0.311 ml.m5.2xlarge $0.622 ml.m5.4xlarge $1.243 ml.m5.12xlarge $3.73 ml.m5.24xlarge $7.459 ml.m4.xlarge $0.325 ml.m4.2xlarge $0.65 ml.m4.4xlarge $1.299 ml.m4.10xlarge $3.248 ml.m4.16xlarge $5.197 Compute Instances - Current Generation ml.c5.xlarge $0.283 ml.c5.2xlarge $0.566 ml.c5.4xlarge $1.131 ml.c5.9xlarge $2.545 ml.c5.18xlarge $5.09 ml.c4.xlarge $0.332 ml.c4.2xlarge $0.666 ml.c4.4xlarge
$1.33 ml.c4.8xlarge $2.663 GPU Instances - Current Generation ml.p3.2xlarge $5.025 ml.p3.8xlarge $20.098 ml.p3.16xlarge $40.197 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.162 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.073 ml.t2.large $0.148 ml.t2.xlarge $0.296 ml.t2.2xlarge $0.591 ml.m5.large $0.155 ml.m5.xlarge $0.311 ml.m5.2xlarge $0.622 ml.m5.4xlarge $1.243 ml.m5.12xlarge $3.73 ml.m5.24xlarge $7.459 ml.m4.xlarge $0.325 ml.m4.2xlarge $0.65 ml.m4.4xlarge $1.299 ml.m4.10xlarge $3.248 ml.m4.16xlarge $5.197 Compute Instances - Current Generation ml.c5.large $0.141 ml.c5.xlarge $0.283 ml.c5.2xlarge $0.566 ml.c5.4xlarge $1.131 ml.c5.9xlarge $2.545 ml.c5.18xlarge $5.09 ml.c4.large $0.167 ml.c4.xlarge $0.332 ml.c4.2xlarge $0.666 ml.c4.4xlarge $1.33 ml.c4.8xlarge $2.663 GPU Instances - Current Generation ml.p3.2xlarge $5.025 ml.p3.8xlarge $20.098 ml.p3.16xlarge $40.197 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.155 ml.m5.xlarge $0.311 ml.m5.2xlarge $0.622 ml.m5.4xlarge $1.243 ml.m5.12xlarge $3.73 ml.m5.24xlarge $7.459 ml.m4.xlarge $0.325 ml.m4.2xlarge $0.65 ml.m4.4xlarge $1.299 ml.m4.10xlarge $3.248 ml.m4.16xlarge $5.197 Compute Instances - Current Generation ml.c5.xlarge $0.283 ml.c5.2xlarge $0.566 ml.c5.4xlarge $1.131 ml.c5.9xlarge $2.545 ml.c5.18xlarge $5.09 ml.c4.xlarge $0.332 ml.c4.2xlarge $0.666 ml.c4.4xlarge
$1.33 ml.c4.8xlarge $2.663 GPU Instances - Current Generation ml.p3.2xlarge $5.025 ml.p3.8xlarge $20.098 ml.p3.16xlarge $40.197 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inferencing)Price per Hour General Purpose (SSD) Storage $0.162 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inferencing)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
Asia Pacific (Mumbai)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0496 ml.t2.large $0.1389 ml.t2.xlarge $0.2778 ml.t2.2xlarge $0.5555 ml.m4.xlarge $0.294 ml.m4.2xlarge $0.588 ml.m4.4xlarge $1.176 ml.m4.10xlarge $2.94 ml.m4.16xlarge $4.704 GPU Instances - Current Generation ml.p2.xlarge $2.405 ml.p2.8xlarge $19.242 ml.p2.16xlarge $38.483 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.160 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.141 ml.m5.xlarge $0.283 ml.m5.2xlarge $0.566 ml.m5.4xlarge $1.131 ml.m5.12xlarge $3.394 ml.m5.24xlarge $6.787 ml.m4.xlarge $0.294 ml.m4.2xlarge $0.588 ml.m4.4xlarge $1.176 ml.m4.10xlarge $2.94 ml.m4.16xlarge $4.704 Compute Instances - Current Generation ml.c5.xlarge $0.238 ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.28 ml.c4.2xlarge $0.56 ml.c4.4xlarge
$1.12 ml.c4.8xlarge $2.24 GPU Instances - Current Generation ml.p2.xlarge $2.405 ml.p2.8xlarge $19.242 ml.p2.16xlarge $38.483 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.160 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.069 ml.t2.large $0.139 ml.t2.xlarge $0.278 ml.t2.2xlarge $0.556 ml.m5.large $0.141 ml.m5.xlarge $0.283 ml.m5.2xlarge $0.566 ml.m5.4xlarge $1.131 ml.m5.12xlarge $3.394 ml.m5.24xlarge $6.787 ml.m4.xlarge $0.294 ml.m4.2xlarge $0.588 ml.m4.4xlarge $1.176 ml.m4.10xlarge $2.94 ml.m4.16xlarge $4.704 Compute Instances - Current Generation ml.c5.large $0.119 ml.c5.xlarge $0.238 ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.large $0.14 ml.c4.xlarge $0.28 ml.c4.2xlarge $0.56 ml.c4.4xlarge $1.12 ml.c4.8xlarge $2.24 GPU Instances - Current Generation ml.p2.xlarge $2.405 ml.p2.8xlarge $19.242 ml.p2.16xlarge $38.483 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.141 ml.m5.xlarge $0.283 ml.m5.2xlarge $0.566 ml.m5.4xlarge $1.131 ml.m5.12xlarge $3.394 ml.m5.24xlarge $6.787 ml.m4.xlarge $0.294 ml.m4.2xlarge $0.588 ml.m4.4xlarge $1.176 ml.m4.10xlarge $2.94 ml.m4.16xlarge $4.704 Compute Instances - Current Generation ml.c5.xlarge $0.238 ml.c5.2xlarge $0.476 ml.c5.4xlarge $0.952 ml.c5.9xlarge $2.142 ml.c5.18xlarge $4.284 ml.c4.xlarge $0.28 ml.c4.2xlarge $0.56 ml.c4.4xlarge
$1.12 ml.c4.8xlarge $2.24 GPU Instances - Current Generation ml.p2.xlarge $2.405 ml.p2.8xlarge $19.242 ml.p2.16xlarge $38.483 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.160 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
Asia Pacific (Seoul)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0576 ml.t2.large $0.1613 ml.t2.xlarge $0.3226 ml.t2.2xlarge $0.6451 ml.m4.xlarge $0.344 ml.m4.2xlarge $0.689 ml.m4.4xlarge $1.378 ml.m4.10xlarge $3.444 ml.m4.16xlarge $5.51 GPU Instances - Current Generation ml.p2.xlarge $2.051 ml.p2.8xlarge $16.408 ml.p2.16xlarge $32.816 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.294 eia1.large 2 16 2 GB
$0.602 eia1.xlarge 4 32 4 GB $1.19 * FP-32 TFLOPS = trillion 32-bit floating point instructions per second
** FP-16 TFLOPS = trillion 16-bit floating point instructions per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.1596 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.165 ml.m5.xlarge $0.33 ml.m5.2xlarge $0.661 ml.m5.4xlarge $1.322 ml.m5.12xlarge $3.965 ml.m5.24xlarge $7.93 ml.m4.xlarge $0.344 ml.m4.2xlarge $0.689 ml.m4.4xlarge $1.378 ml.m4.10xlarge $3.444 ml.m4.16xlarge $5.51 Compute Instances - Current Generation ml.c5.xlarge $0.269 ml.c5.2xlarge $0.538 ml.c5.4xlarge $1.075 ml.c5.9xlarge $2.419 ml.c5.18xlarge $4.838 ml.c4.xlarge $0.318 ml.c4.2xlarge $0.636 ml.c4.4xlarge
$1.27 ml.c4.8xlarge $2.541 GPU Instances - Current Generation ml.p2.xlarge $2.051 ml.p2.8xlarge $16.408 ml.p2.16xlarge $32.816 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.1596 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0806 ml.t2.large $0.1613 ml.t2.xlarge $0.3226 ml.t2.2xlarge $0.6451 ml.m5.large $0.165 ml.m5.xlarge $0.33 ml.m5.2xlarge $0.661 ml.m5.4xlarge $1.322 ml.m5.12xlarge $3.965 ml.m5.24xlarge $7.93 ml.m4.xlarge $0.344 ml.m4.2xlarge $0.689 ml.m4.4xlarge $1.378 ml.m4.10xlarge $3.444 ml.m4.16xlarge $5.51 Compute Instances - Current Generation ml.c5.large $0.134 ml.c5.xlarge $0.269 ml.c5.2xlarge $0.538 ml.c5.4xlarge $1.075 ml.c5.9xlarge $2.419 ml.c5.18xlarge $4.838 ml.c4.large $0.16 ml.c4.xlarge $0.318 ml.c4.2xlarge $0.636 ml.c4.4xlarge $1.27 ml.c4.8xlarge $2.541 GPU Instances - Current Generation ml.p2.xlarge $2.051 ml.p2.8xlarge $16.408 ml.p2.16xlarge $32.816 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory Price per Hour eia1.medium 1 8 1 GB
$0.294 eia1.large 2 16 2 GB
$0.602 eia1.xlarge 4 32 4 GB $1.19 * FP-32 TFLOPS = trillion 32-bit floating point instructions per second
** FP-16 TFLOPS = trillion 16-bit floating point instructions per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.165 ml.m5.xlarge $0.33 ml.m5.2xlarge $0.661 ml.m5.4xlarge $1.322 ml.m5.12xlarge $3.965 ml.m5.24xlarge $7.93 ml.m4.xlarge $0.344 ml.m4.2xlarge $0.689 ml.m4.4xlarge $1.378 ml.m4.10xlarge $3.444 ml.m4.16xlarge $5.51 Compute Instances - Current Generation ml.c5.xlarge $0.269 ml.c5.2xlarge $0.538 ml.c5.4xlarge $1.075 ml.c5.9xlarge $2.419 ml.c5.18xlarge $4.838 ml.c4.xlarge $0.318 ml.c4.2xlarge $0.636 ml.c4.4xlarge
$1.27 ml.c4.8xlarge $2.541 GPU Instances - Current Generation ml.p2.xlarge $2.051 ml.p2.8xlarge $16.408 ml.p2.16xlarge $32.816 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.1596 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
Asia Pacific (Singapore)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0584 ml.t2.large $0.1635 ml.t2.xlarge $0.3270 ml.t2.2xlarge $0.6541 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.70 ml.m4.4xlarge $1.40 ml.m4.10xlarge $3.50 ml.m4.16xlarge $5.60 GPU Instances - Current Generation ml.p2.xlarge $2.405 ml.p2.8xlarge $19.242 ml.p2.16xlarge $38.483 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.168 ml.m5.xlarge $0.336 ml.m5.2xlarge $0.672 ml.m5.4xlarge $1.344 ml.m5.12xlarge $4.032 ml.m5.24xlarge $8.064 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.70 ml.m4.4xlarge $1.40 ml.m4.10xlarge $3.50 ml.m4.16xlarge $5.60 Compute Instances - Current Generation ml.c5.xlarge $0.274 ml.c5.2xlarge $0.549 ml.c5.4xlarge $1.098 ml.c5.9xlarge $2.470 ml.c5.18xlarge $4.939 ml.c4.xlarge $0.323 ml.c4.2xlarge $0.647 ml.c4.4xlarge
$1.294 ml.c4.8xlarge $2.587 GPU Instances - Current Generation ml.p2.xlarge $2.41 ml.p2.8xlarge $19.24 ml.p2.16xlarge $38.48 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0818 ml.t2.large $0.1635 ml.t2.xlarge $0.3270 ml.t2.2xlarge $0.6541 ml.m5.large $0.168 ml.m5.xlarge $0.336 ml.m5.2xlarge $0.672 ml.m5.4xlarge $1.344 ml.m5.12xlarge $4.032 ml.m5.24xlarge $8.064 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.70 ml.m4.4xlarge $1.40 ml.m4.10xlarge $3.50 ml.m4.16xlarge $5.60 Compute Instances - Current Generation ml.c5.large $0.137 ml.c5.xlarge $0.274 ml.c5.2xlarge $0.549 ml.c5.4xlarge $1.098 ml.c5.9xlarge $2.470 ml.c5.18xlarge $4.939 ml.c4.large $0.161 ml.c4.xlarge $0.323 ml.c4.2xlarge $0.647 ml.c4.4xlarge $1.294 ml.c4.8xlarge $2.587 GPU Instances - Current Generation ml.p2.xlarge $2.41 ml.p2.8xlarge $19.24 ml.p2.16xlarge $38.48 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.168 ml.m5.xlarge $0.336 ml.m5.2xlarge $0.672 ml.m5.4xlarge $1.344 ml.m5.12xlarge $4.032 ml.m5.24xlarge $8.064 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.70 ml.m4.4xlarge $1.40 ml.m4.10xlarge $3.50 ml.m4.16xlarge $5.60 Compute Instances - Current Generation ml.c5.xlarge $0.274 ml.c5.2xlarge $0.549 ml.c5.4xlarge $1.098 ml.c5.9xlarge $2.470 ml.c5.18xlarge $4.939 ml.c4.xlarge $0.323 ml.c4.2xlarge $0.647 ml.c4.4xlarge
$1.294 ml.c4.8xlarge $2.587 GPU Instances - Current Generation ml.p2.xlarge $2.41 ml.p2.8xlarge $19.24 ml.p2.16xlarge $38.48 ml.p3.2xlarge $6.973 ml.p3.8xlarge $27.894 ml.p3.16xlarge $55.787 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time InferencePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
Asia Pacific (Sydney)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0584 ml.t2.large $0.1635 ml.t2.xlarge $0.327 ml.t2.2xlarge $0.6541 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.7 ml.m4.4xlarge $1.4 ml.m4.10xlarge $3.5 ml.m4.16xlarge $5.6 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.27 ml.p2.16xlarge $34.541 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.168 ml.m5.xlarge $0.336 ml.m5.2xlarge $0.672 ml.m5.4xlarge $1.344 ml.m5.12xlarge $4.032 ml.m5.24xlarge $7.93 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.7 ml.m4.4xlarge $1.4 ml.m4.10xlarge $3.5 ml.m4.16xlarge $5.6 Compute Instances - Current Generation ml.c5.xlarge $0.311 ml.c5.2xlarge $0.622 ml.c5.4xlarge $1.243 ml.c5.9xlarge $2.797 ml.c5.18xlarge $5.594 ml.c4.xlarge $0.365 ml.c4.2xlarge $0.731 ml.c4.4xlarge
$1.459 ml.c4.8xlarge $2.919 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.27 ml.p2.16xlarge $34.541 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.1596 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0818 ml.t2.large $0.1635 ml.t2.xlarge $0.327 ml.t2.2xlarge $0.6541 ml.m5.large $0.168 ml.m5.xlarge $0.336 ml.m5.2xlarge $0.672 ml.m5.4xlarge $1.344 ml.m5.12xlarge $4.032 ml.m5.24xlarge $8.064 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.7 ml.m4.4xlarge $1.4 ml.m4.10xlarge $3.5 ml.m4.16xlarge $5.6 Compute Instances - Current Generation ml.c5.large $0.155 ml.c5.xlarge $0.311 ml.c5.2xlarge $0.622 ml.c5.4xlarge $1.243 ml.c5.9xlarge $2.797 ml.c5.18xlarge $5.594 ml.c4.large $0.182 ml.c4.xlarge $0.365 ml.c4.2xlarge $0.731 ml.c4.4xlarge $1.459 ml.c4.8xlarge $2.919 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.270 ml.p2.16xlarge $34.541 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.168 ml.m5.xlarge $0.336 ml.m5.2xlarge $0.672 ml.m5.4xlarge $1.344 ml.m5.12xlarge $4.032 ml.m5.24xlarge $7.93 ml.m4.xlarge $0.35 ml.m4.2xlarge $0.7 ml.m4.4xlarge $1.4 ml.m4.10xlarge $3.5 ml.m4.16xlarge $5.6 Compute Instances - Current Generation ml.c5.xlarge $0.311 ml.c5.2xlarge $0.622 ml.c5.4xlarge $1.243 ml.c5.9xlarge $2.797 ml.c5.18xlarge $5.594 ml.c4.xlarge $0.365 ml.c4.2xlarge $0.731 ml.c4.4xlarge
$1.459 ml.c4.8xlarge $2.919 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.27 ml.p2.16xlarge $34.541 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.1596 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
Asia Pacific (Tokyo)
-
Building
On-Demand ML Notebook InstancesStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0608 ml.t2.large $0.1702 ml.t2.xlarge $0.3405 ml.t2.2xlarge $0.681 ml.m4.xlarge $0.361 ml.m4.2xlarge $0.722 ml.m4.4xlarge $1.445 ml.m4.10xlarge $3.612 ml.m4.16xlarge $5.779 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.27 ml.p2.16xlarge $34.541 ml.p3.2xlarge $7.34 ml.p3.8xlarge $29.361 ml.p3.16xlarge $58.722 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory
Price per Hour ml.t2.medium 1 8 1 GB
$0.308 ml.t2.large 2 16 2 GB
$0.63 ml.t2.xlarge 4 32 4 GB
$1.246 * FP-32 TFLOPS = trillion 32-bit floating operations per second
** FP-16 TFLOPS = trillion 16-bit floating operations per second
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage
Data ProcessedCost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB -
Model Training
On-Demand ML Training InstancesStandard Instances - Current Generation Price per Hour ml.m5.large $0.174 ml.m5.xlarge $0.347 ml.m5.2xlarge $0.694 ml.m5.4xlarge $1.389 ml.m5.12xlarge $4.166 ml.m5.24xlarge $8.333 ml.m4.xlarge $0.361 ml.m4.2xlarge $0.722 ml.m4.4xlarge $1.445 ml.m4.10xlarge $3.612 ml.m4.16xlarge $5.779 Compute Instances - Current Generation ml.c5.xlarge $0.3 ml.c5.2xlarge $0.599 ml.c5.4xlarge $1.198 ml.c5.9xlarge $2.696 ml.c5.18xlarge $5.393 ml.c4.xlarge $0.353 ml.c4.2xlarge $0.706 ml.c4.4xlarge
$1.411 ml.c4.8xlarge $2.822 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.27 ml.p2.16xlarge $34.541 ml.p3.2xlarge $7.34 ml.p3.8xlarge $29.361 ml.p3.16xlarge $58.722 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML StoragePrice per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage -
Model Deployment
On-Demand ML Hosting Instances for Real-Time InferenceStandard Instances - Current Generation Price per Hour ml.t2.medium $0.0851 ml.t2.large $0.1702 ml.t2.xlarge $0.3405 ml.t2.2xlarge $0.681 ml.m5.large $0.174 ml.m5.xlarge $0.347 ml.m5.2xlarge $0.694 ml.m5.4xlarge $1.389 ml.m5.12xlarge $4.166 ml.m5.24xlarge $8.333 ml.m4.xlarge $0.361 ml.m4.2xlarge $0.722 ml.m4.4xlarge $1.445 ml.m4.10xlarge $3.612 ml.m4.16xlarge $5.779 Compute Instances - Current Generation ml.c5.large $0.15 ml.c5.xlarge $0.3 ml.c5.2xlarge $0.599 ml.c5.4xlarge $1.198 ml.c5.9xlarge $2.696 ml.c5.18xlarge $5.393 ml.c4.large $0.176 ml.c4.xlarge $0.353 ml.c4.2xlarge $0.706 ml.c4.4xlarge $1.411 ml.c4.8xlarge $2.822 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.27 ml.p2.16xlarge $34.541 ml.p3.2xlarge $7.34 ml.p3.8xlarge $29.361 ml.p3.16xlarge $58.722 Inference AccelerationAccelerator Throughput in FP-32 TFLOPS*
Throughput in FP-16 TFLOPS**
Memory
Price per Hour ml.t2.medium 1 8 1 GB
$0.308 ml.t2.large 2 16 2 GB
$0.63 ml.t2.xlarge 4 32 4 GB
$1.246 * FP-32 TFLOPS = trillion 32-bit floating operations per second
** FP-16 TFLOPS = trillion 16-bit floating operations per secondl
Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
On-Demand ML Instances for Batch TransformStandard Instances - Current Generation Price per Hour ml.m5.large $0.174 ml.m5.xlarge $0.347 ml.m5.2xlarge $0.694 ml.m5.4xlarge $1.389 ml.m5.12xlarge $4.166 ml.m5.24xlarge $8.333 ml.m4.xlarge $0.361 ml.m4.2xlarge $0.722 ml.m4.4xlarge $1.445 ml.m4.10xlarge $3.612 ml.m4.16xlarge $5.779 Compute Instances - Current Generation ml.c5.xlarge $0.3 ml.c5.2xlarge $0.599 ml.c5.4xlarge $1.198 ml.c5.9xlarge $2.696 ml.c5.18xlarge $5.393 ml.c4.xlarge $0.353 ml.c4.2xlarge $0.706 ml.c4.4xlarge
$1.411 ml.c4.8xlarge $2.822 GPU Instances - Current Generation ml.p2.xlarge $2.159 ml.p2.8xlarge $17.27 ml.p2.16xlarge $34.541 ml.p3.2xlarge $7.34 ml.p3.8xlarge $29.361 ml.p3.16xlarge $58.722 Except as otherwise noted, our prices are exclusive of applicable taxes and duties, including VAT and applicable sales tax.
ML Storage (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Price per Hour General Purpose (SSD) Storage $0.168 per GB-month of provisioned storage Data Processing (Applicable only for On-Demand ML Hosting Instances for Real-Time Inference)Cost
Data Processed IN $0.016 per GB Data Processed OUT
$0.016 per GB
Pricing Example #1
A data scientist has spent a week working on a model for a new idea. She uses an ml.t2.medium Juptyer notebook for 105 hours, trains four times on an ml.m4.4xlarge for 30 minutes per training run, and deploys to an ml.t2.medium for 10 minutes each time for the evaluation. She prepares 3 GB of data into a notebook, and pushes 2 GB into Amazon S3. The evaluation dataset is 1 GB of data, and inferences are 1/10 the size of the input data.
| Hours | Notebook Instance | Training Instance | Hosting Instance |
Cost per hour |
Total |
|---|---|---|---|---|---|
| 105.00 | ml.t2.medium | $0.0464 | $4.872 | ||
| 2.00 | ml.m4.4xlarge training | $1.12 |
$2.24 | ||
| 0.67 |
ml.t2.medium | $0.065 | $0.04355 | ||
| ------- | |||||
| $7.1555 |
| GB processed In - Notebooks |
GB processed Out - Notebooks |
GB data In - Hosting | GB Data Out - Hosting | Cost per GB In or Out | Total |
|---|---|---|---|---|---|
| 4 * 0.1 = 0.4GB | 4 * 1 = 4GB | 4 * 1 = 4 GB | 4 * 0.1 = 0.4 GB | $0.016 | $0.1408 |
The sub-total for authoring, training, hosting = $7.1555.
The sub-total for pulling in 3GB of training data to notebooks (3 * $0.016= $0.048) and moving 2GB into Amazon S3 (2 * $0.016=$ 0.32) = $0.08
The sub-total for Data Processed In and Out of Notebooks and Hosting = $0.1408.
The Total for this workflow example is $7.3763.
Pricing Example #2
The model in Example #1 is then deployed to production to three (3) ml.t2.medium for reliable multi-AZ hosting, and is regularly retrained once per week. The model receives 100MB of data per day, and inferences are 1/10 the size of the input data.
| Hours per month | Training Instances | Hosting instances | Cost per hour | Total |
|---|---|---|---|---|
| 4 | ml.m4.xlarge | $1.12 | $4.48 | |
| 24 * 31 * 3 = 2232 | ml.t2.medium | $0.065 | $145.08 |
| Data In per Month - Hosting | Data Out per Month- Hosting | Cost per GB In or Out | Total |
|---|---|---|---|
| 100MB * 31 = 3100MB | $0.016 | $0.0496 |
|
| 10MB * 31 = 310MB | $0.016 | $0.00496 |
The sub-total for training and hosting = $149.56; The sub-total for 3100 MB of data processed In and 310MB of data processed Out for Hosting per month = $0.05456. The Total for this workflow example would be $149.61 per month.
Pricing Example #3
Amazon SageMaker Batch Transform only charges you for the instances used during while your jobs are executing. If your data is already in Amazon S3, then there is no cost for reading input data from S3 and writing output data to S3.
The model in Example #1 is used to run Batch Transform. The data scientist runs four separate Batch Transform jobs on 3 ml.m4.4xlarge for 15 minutes per job run. She uploads an evaluation dataset of 1 GB in S3 for each run, and inferences are 1/10 the size of the input data which are stored back in S3.
| Hours | Training Instances | Cost per hour | Total |
|---|---|---|---|
| 3 * 0.25 * 4 = 3 hours | ml.m4.xlarge | $1.12 | $3.36 |
| GB data In - Batch Transform |
GB data Out - Batch Transform | Cost per GB In or Out | Total |
|---|---|---|---|
| 0 | 0 | $0.02 | 0 |
The sub-total for Batch Transform job = $3.36; The sub-total for 4.4 GB into Amazon S3 = 0. The Total for this workflow example would be $3.36.
Learn more about Amazon SageMaker features
