Skip to content

Browse Endpoints ​

View the list of serverless endpoints created from Docker images.

Prerequisites ​

  • An account with access to AI Inference
  • The cluster and project to view, selected at the top of the sidebar

Click Serverless → Docker in the sidebar to open the endpoint list. Follow the numbers on the screenshots below.

Open the endpoint list from the Docker menu in the Serverless group.

Sidebar
No.FeatureItemDescription
1-1DockerDocker menu· Screen for serverless endpoints that run your own container image.

Search · Bulk delete ​

Find endpoints by name and delete selected endpoints at once.

Search · Bulk delete
No.FeatureItemDescription
2-1SearchSearch box· Filters the list by endpoint name.
2-2Bulk deleteDelete button· Deletes the endpoints checked in the table. Enabled only when at least one row is selected.

Create endpoint ​

Opens the screen for creating a new endpoint.

Create endpoint
No.FeatureItemDescription
3-1Create endpointCreate endpoint button· Click the button at the top right to open the endpoint creation screen.

Endpoint list ​

Shows the endpoints of the current project and cluster in a table.

Endpoint list
No.FeatureItemDescription
4-1ColumnsStatusEndpoint status. Green means running, gray means paused (including scaled to zero with no requests), and red means an error.
NameEndpoint name, with the deployed model (or image) below it.
GPUGPU resources allocated to each replica.
ReplicasMinimum - maximum replicas. With a minimum of 0, the endpoint scales down to zero when idle.
PortPort on which the endpoint receives requests.
Created atDate the endpoint was created.
4-2Row actionsAction (⋯) button· Click the button at the end of a row to open that endpoint’s action menu.

Row action menu ​

Actions available for each endpoint. Some items are disabled depending on the endpoint status.

Row action menu
No.FeatureItemDescription
5-1Menu itemsService URLView and copy the endpoint URL.
View logsView pod events and container logs.
Send promptSend a test prompt to a running endpoint and check the response.
PausePause a running endpoint.
ResumeResume a paused endpoint.
CancelCancel an endpoint deployment that is in progress.
EditOpen the screen for editing replicas and resources.
DeleteDelete the endpoint. A confirmation modal opens first.

For how to use each item in the row action menu, see Manage endpoints. Docker endpoints use the same menu.

The New Standard for AI Infrastructure