Prior Version(s) of Amazon SageMaker Service Level Agreement – Not Currently In Effect

This Amazon SageMaker Service Level Agreement (“SLA”) is a policy governing the use of Amazon SageMaker under the terms of the AWS Customer Agreement or other agreement with us governing your use of our Services (the “Agreement”). This SLA applies separately to each account using Amazon SageMaker. Unless otherwise provided herein, this SLA is subject to the terms of the Agreement and capitalized terms will have the meaning specified in the Agreement. We reserve the right to change the terms of this SLA in accordance with the Agreement.

This SLA applies to the following functions of Amazon SageMaker:

“Online Inference” - the Amazon SageMaker InvokeEndpoint API, for model endpoints supported by more than one instance.
“Batch Transform” - the Amazon SageMaker CreateTransformJob API and StopTransformJob API.

Service Commitment

AWS will use commercially reasonable efforts to make Amazon SageMaker available with a Monthly Uptime Percentage (defined below) for each AWS region, during any monthly billing cycle (the “Service Commitment”). In the event Amazon SageMaker does not meet the Service Commitment, you will be eligible to receive a Service Credit as described below.

Definitions

• A “Service Credit” is a dollar credit, calculated as set forth below, that we may credit back to an eligible account.
• “Monthly Uptime Percentage” for a given AWS region is calculated as the average of the Availability of all 5-minute intervals in a monthly billing cycle. Monthly Uptime Percentage measurements exclude downtime resulting directly or indirectly from any Amazon SageMaker SLA Exclusion (defined below).
• “Availability” is calculated for each 5-minute interval as the percentage of Requests (defined below) processed by Amazon SageMaker that do not fail with Errors (defined below) and relate solely to the provisioned Amazon SageMaker functions. If you did not make any Requests in a given 5-minute interval, that interval is assumed to be 100% available.
• “Request” means:
  • For Online Inference, an invocation of an Amazon SageMaker function by directly calling the InvokeEndpoint API.
  • For Batch Transform, an invocation of an Amazon SageMaker function by directly calling the CreateTransformJob and StopTransformJob APIs.
• An “Error” is any Request that returns a 500 or 503 error code.

Service Credits

Service Credits are calculated as a percentage of the following charges paid by you for Amazon SageMaker Online Inference or Batch Transform (as applicable) for the monthly billing cycle in which the Monthly Uptime Percentage for a given AWS region fell within the ranges set forth in the table below:

For Online Inference:

We will apply any Service Credits only against future Amazon SageMaker Online Inference or Batch Transform (as applicable) payments otherwise due from you. At our discretion, we may issue the Service Credits to the credit card you used to pay for the billing cycle in which the unavailability occurred. Service Credits will not entitle you to any refund or other payment from AWS. Service Credits will be applicable and issued only if the credit amount for the applicable monthly billing cycle is greater than one dollar ($1 USD). Service Credits may not be transferred or applied to any other account. Unless otherwise provided in the Agreement, your sole and exclusive remedy for any unavailability or non-performance or other failure by us to provide Amazon SageMaker is the receipt of Service Credits (if eligible) in accordance with the terms of this SLA.

Credit Request and Payment Procedures

To receive Service Credits, you will need to submit a claim by opening a case in the AWS Support Center. To be eligible, the credit request must be received by us by the end of the second billing cycle after which the incident occurred and must include:

(i) the words “SLA Credit Request” in the subject line;

(ii) the billing cycle and AWS regions with respect to which you are claiming Service Credits, together with the Monthly Uptime Percentage for that AWS region for the billing cycle and the specific dates, times, and Availabilities for each 5-minute interval with less than 100% Availability in that AWS region throughout the billing cycle;

(iii) your request logs that document the Errors for your claimed outage (any confidential or sensitive information in these logs should be removed or replaced with asterisks).

If the Monthly Uptime Percentage of such credit request is confirmed by us and is less than the Service Commitment, then we will issue the Service Credits to you within one billing cycle following the month in which the credit request occurred. Your failure to provide the credit request and other information as required above will disqualify you from receiving Service Credits.

Amazon SageMaker SLA Exclusions

The Service Commitment does not apply to any unavailability, suspension or termination of Amazon SageMaker, or any other Amazon SageMaker performance issues:

(i) caused by factors outside of our reasonable control, including any force majeure event or Internet access or related problems beyond the demarcation point of Amazon SageMaker;

(ii) that result from any voluntary actions or inactions from you or any third party (e.g. scaling of provisioned capacity, misconfiguring security groups, VPC configurations or credential settings, disabling encryption keys or making the encryption keys inaccessible, etc.);

(iii) that result from you not following the best practices described in the Amazon SageMaker Documentation on the AWS Site;

(iv) that result from your equipment, software or other technology and/or third party equipment, software or other technology (other than third party equipment within our direct control);

(v) that result from any maintenance as provided for pursuant to the Agreement; or

(vi) arising from our suspension and termination of your right to use Amazon SageMaker in accordance with the Agreement (collectively, the “Amazon SageMaker SLA Exclusions”).

If availability is impacted by factors other than those explicitly used in our Monthly Uptime Percentage calculation, then we may issue a Service Credit considering such factors at our discretion.