Skip to main content

Create Endpoint

POST 

/inference/endpoints

Create Endpoint

Request

Body

required

JSON Payload

    gpuCount integerrequired
    gpuType stringrequired
    locationName stringrequired
    maxReplicas integer
    minReplicas integer
    modelName stringrequired
    name stringrequired
    scaleToZeroRetentionPeriodSeconds integer

Responses

OK

Schema

    id string
    token string
Loading...