Skip to main content
POST
Create Serving Endpoint

Authorizations

Authorization
string
header
required

An API key or OAuth2/OIDC access token sent as Authorization: Bearer <token>.

Body

application/json
model_id
required

The trained model this endpoint serves (models.id).

predict_options
OnlinePredictionOptions · object
max_qps
integer
default:50

Advisory per-endpoint request-rate ceiling.

Required range: x >= 1

Response

Successful Response

id
required

Server-assigned endpoint id.

endpoint_url
string
required

Public base URL of the endpoint, e.g. https://ep-{id}.serving..

config
OnlineServingEndpointRequest · object
required
launched_at
string<date-time>
required
status
OnlineServingStatus · object
required