ML Delete Idle Endpoints

Opportunity Name:

ML Delete Idle Endpoints


AWS Resource Type:

Amazon SageMaker Endpoints


Opportunity Description:

Amazon SageMaker customers may have endpoints that are no longer in use but still incur costs. CloudFix identifies these idle endpoints, which have had no invocations over the past 30 days, to help optimize costs by suggesting their removal. This finder also identifies associated models that may no longer be in use.


Criteria for identifying the opportunity:

  • Endpoints with 0 invocations over the past 30 days.
  • Annual cost, extrapolated from the last 31 days of usage, exceeds the annual public cost threshold (default $100).


Potential savings (range in % on annual basis):

  • The savings are equivalent to the cost of maintaining the idle endpoints and associated models.
  • Actual savings will depend on the specific resources identified and their associated costs.


Can CloudFix implement the fix automatically once I accept the recommendation?



Other considerations:

  • Performance impact: Removing idle endpoints should not impact active workloads. However, ensure that these endpoints are indeed not required for any current or future tasks.
  • Data loss considerations: While deleting endpoints does not directly result in data loss, ensure that any associated models or data not backed up elsewhere are not needed before proceeding with deletion.
  • Security concerns: Ensure that the removal of these resources does not impact any security protocols or data access policies within your organization.


Additional Resources:



Please sign in to leave a comment.

Was this article helpful?
0 out of 0 found this helpful
Have more questions? Submit a request