gcloud ai endpoints

NAME
gcloud ai endpoints - manage Vertex AI endpoints
SYNOPSIS
gcloud ai endpointsCOMMAND[GCLOUD_WIDE_FLAG …]
DESCRIPTION
An endpoint contains one or more deployed models, all of which must have thesame interface but may come from different models. An endpoint is to obtainonline prediction and explanation from one of its deployed models.

When you communicate with Vertex AI services, you identify a specific endpointthat is deployed in the cloud using a combination of the current project, theregion, and the endpoint.

GCLOUD WIDE FLAGS
These flags are available to all commands:--help.

Run$gcloud help for details.

COMMANDS
COMMAND is one of the following:
create
Create a new Vertex AI endpoint.
delete
Delete an existing Vertex AI endpoint.
deploy-model
Deploy a model to an existing Vertex AI endpoint.
describe
Describe an existing Vertex AI endpoint.
direct-predict
Run Vertex AI online direct prediction.
direct-raw-predict
Run Vertex AI online direct raw prediction.
explain
Request an online explanation from an Vertex AI endpoint.
list
List existing Vertex AI endpoints.
predict
Run Vertex AI online prediction.
raw-predict
Run Vertex AI online raw prediction.
stream-direct-predict
Run Vertex AI online stream direct prediction.
stream-direct-raw-predict
Run Vertex AI online stream direct raw prediction.
stream-raw-predict
Run Vertex AI online stream raw prediction.
undeploy-model
Undeploy a model from an existing Vertex AI endpoint.
update
Update an existing Vertex AI endpoint.
NOTES
These variants are also available:
gcloudalphaaiendpoints
gcloudbetaaiendpoints

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-09-16 UTC.