Deactivating and Activating a Model Deployment
Activate a deactivated Data Science model deployment or deactivate an active one.
Deactivating a model deployment has the following effects:
-
The instances associated with the model deployment shut down.
-
Metering and billing of the model deployment instances and load balancer stop.
-
The deployment HTTP endpoint becomes unavailable.
-
The model deployment metadata is saved.
A deactivated model deployment can be reactivated. The same model HTTP endpoint is available upon reactivation, and requests can be made to that model endpoint.
When a model deployment is in the Inactive state, you can change all of the options at one time and save the changes. The same isn't true when a model deployment is Active. See editing a model deployment.
- From the model deployments page, select the name of a model deployment. If you need help finding the list of model deployments, see Listing Model Deployments.
- Select Deactivate or Activate.
Use the oci data-science model-deployment activate and oci data-science model-deployment deactivate commands and required parameters:
oci data-science model-deployment activate --notebook-session-id<model-deployment-id>.-c [<text>].. [OPTIONS]oci data-science model-deployment deactivate --notebook-session-id<model-deployment-id>.-c [<text>].. [OPTIONS]For a complete list of flags and variable options for CLI commands, see the CLI Command Reference.
Use the ActivateModelDeployment and DeactivateModelDeployment operations to activate or deactivate a model deployment.