Savings plans only apply to EC2 (compute and EC2 instance savings plans) and Fargate instances (compute savings plans). They do not apply to other services, such as SageMaker.
For cost optimization, SageMaker supports spot instances for training jobs, and for the hosting of real-time inference endpoints, look at:
- right-sizing and auto-scaling the endpoint
- Using elastic inference or inf1 instances (support for inf1 in SageMaker is on the roadmap)
- Compiling models with Neo to optimize model performance (for rightsizing)
- Using inference pipelines instead of multiple model endpoints
- Hosting in multi-model endpoints
- Hosting in self-managed compute, such as EC2 with RI, Lambda, or Fargate/spot.
Elastic inference, Neo, inference pipelines and multi-model endpoints work well in some, but not all use-cases, depending on use case, model framework, complexity, size, etc. so it will require some investigation and experimentation to figure out of they’re right for you, but they can help reduce inference cost significantly.
How to calculate the number of hours covered by EC2 Instance Savings PlansAccepted Answerasked 2 months ago
Cancel Savings Plansasked 8 months ago
Savings Plans Applicability to ML instancesAccepted Answerasked 3 years ago
Should I commit to the discounted amount or the non-discounted amount for compute savings plans?asked 22 days ago
Transfer EC2 and Savings Plan from one AWS Account to anotherAccepted Answerasked a year ago
Ec2 Savings Plan with Tagsasked a month ago
Savings Plan for LambdaAccepted Answerasked 2 years ago
How to reserve capacity with Savings PlansAccepted Answerasked 3 years ago
Transfer Savings Plan Across Organizationsasked a month ago
Purchase Saving Plans for EC2asked 2 months ago