Endpoint Service
Create an endpoint
Creates a stable, inference-addressable endpoint. Add one or more deployments and configure its traffic split before sending inference requests to the endpoint name.
Authorization
bearerAuth AuthorizationBearer <token>
In: header
Path Parameters
projectId*string
Project identifier.
Request Body
application/json
Request parameters for creating an endpoint.
name*string
Inference-addressable endpoint name to create.
visibility?string
Who can discover the endpoint. VISIBILITY_PRIVATE restricts it to the project; VISIBILITY_INTERNAL shares it with the organization.
Default
"VISIBILITY_PRIVATE"Value in
- "VISIBILITY_PRIVATE"
- "VISIBILITY_INTERNAL"
Response Body
application/json
application/json
curl -X POST "https://example.com/projects/string/endpoints" \ -H "Content-Type: application/json" \ -d '{ "name": "string" }'{ "id": "string", "projectId": "string", "name": "string", "createdAt": "2019-08-24T14:15:22Z", "updatedAt": "2019-08-24T14:15:22Z", "etag": "string", "trafficSplit": [ { "deploymentId": "string", "weight": 0 } ], "visibility": "VISIBILITY_PRIVATE", "endpointType": "ENDPOINT_TYPE_DEDICATED", "deployments": [ { "id": "string", "modelId": "string", "hardware": "string", "trafficMode": "TRAFFIC_MODE_LIVE", "state": "DEPLOYMENT_STATE_PROVISIONING", "name": "string", "createdAt": "2019-08-24T14:15:22Z", "autoscaling": { "minReplicas": 0, "maxReplicas": 0, "scaleDownWindow": "string", "scaleUpWindow": "string", "scaleToZeroWindow": "string", "scalingMetrics": [ { "name": "active_sessions", "type": "METRIC_TARGET_TYPE_VALUE", "target": 0, "percentile": "string" } ], "scaleUp": { "policies": [ { "type": "SCALING_POLICY_TYPE_PODS", "value": 1, "periodSeconds": 1 } ], "selectPolicy": "SCALING_POLICY_SELECT_MAX" }, "scaleDown": { "policies": [ { "type": "SCALING_POLICY_TYPE_PODS", "value": 1, "periodSeconds": 1 } ], "selectPolicy": "SCALING_POLICY_SELECT_MAX" } }, "desiredReplicas": 0, "readyReplicas": 0, "model": "string", "estimatedEffectiveTrafficShare": 0.1 } ], "activeRolloutId": "string"}