Class ModelServingClient

Create a new serving endpoint.

Create a new PT serving endpoint.

Delete a serving endpoint.

Retrieves the metrics associated with the provided serving endpoint in either Prometheus or OpenMetrics exposition format.

Retrieves the details for a single serving endpoint.

Get the query schema of the serving endpoint in OpenAPI format. The schema contains information for the supported paths, input and output format and datatypes.

Retrieves the build logs associated with the provided served model.

Retrieves the service logs associated with the provided served model.

Make external services call using the credentials stored in UC Connection.

Get all serving endpoints.

Used to batch add and delete tags from a serving endpoint with a single API call.

Used to update the AI Gateway of a serving endpoint. NOTE: External model, provisioned throughput, and pay-per-token endpoints are fully supported; agent endpoints currently only support inference tables.

Updates any combination of the serving endpoint's served entities, the compute configuration of those served entities, and the endpoint's traffic config. An endpoint that already has an update in progress can not be updated until the current update completes or fails.

Deprecated: Please use AI Gateway to manage rate limits instead.

Updates any combination of the pt endpoint's served entities, the compute configuration of those served entities, and the endpoint's traffic config. Updates are instantaneous and endpoint should be updated instantly

Updates the email and webhook notification settings for an endpoint.