Use one of the following methods to undeploy a model and delete the endpoint.
Google Cloud console
-
Undeploy the model as follows:
-
In the Google Cloud console, in the Vertex AI section, go to the Endpointspage.
-
Click the name and version ID of the model you want to undeploy to open its details page.
-
On the row for your model, click Actions, and then click Undeploy model from endpoint.
-
In the Undeploy model from endpointdialog, click Undeploy.
-
To delete additional models, repeat the preceding steps.
-
-
Optional: Delete the online inference endpoint as follows:
-
In the Google Cloud console, in the Vertex AIsection, go to the Online predictionpage.
-
Select the endpoint.
-
To delete the endpoint, click Actions, and then click Delete endpoint.
-
gcloud
-
List the endpoint IDs for all endpoints in your project:
gcloud ai endpoints list \ --project = PROJECT_ID \ --region = LOCATION_IDReplace PROJECT_ID with your project name and LOCATION_ID with the region where you are using Vertex AI.
-
List the model IDs for the models that are deployed to an endpoint:
gcloud ai endpoints describe ENDPOINT_ID \ --project = PROJECT_ID \ --region = LOCATION_IDReplace ENDPOINT_ID with the endpoint ID.
-
Undeploy a model from the endpoint:
gcloud ai endpoints undeploy-model ENDPOINT_ID \ --project = PROJECT_ID \ --region = LOCATION_ID \ --deployed-model-id = DEPLOYED_MODEL_IDReplace DEPLOYED_MODEL_ID with the model ID.
-
Optional: Delete the online inference endpoint:
gcloud ai endpoints delete ENDPOINT_ID \ --project = PROJECT_ID \ --region = LOCATION_ID
