Create a dedicated endpoint
Creates a new dedicated endpoint for serving models. The endpoint starts automatically after creation. You can deploy any supported model on hardware configurations that meet the model's requirements.
Authorization
bearerAuth In: header
Request Body
application/json
A human-readable name for the endpoint
The model to deploy on this endpoint
The hardware configuration to use for this endpoint
Configuration for automatic scaling of the endpoint
This parameter is deprecated and no longer has any effect.
falseWhether to disable speculative decoding for this endpoint
falseThe desired state of the endpoint
"STARTED"Value in
- "STARTED"
- "STOPPED"
The number of minutes of inactivity after which the endpoint stops automatically. Set to null, omit, or set to 0 to disable automatic timeout.
Create the endpoint in a specified availability zone (e.g., us-central-4b)
Response Body
application/json
application/json
application/json
curl -X POST "https://example.com/endpoints" \ -H "Content-Type: application/json" \ -d '{ "model": "string", "hardware": "string", "autoscaling": { "min_replicas": 2, "max_replicas": 5 } }'{ "object": "endpoint", "id": "string", "name": "string", "display_name": "string", "model": "string", "hardware": "string", "type": "dedicated", "owner": "string", "state": "PENDING", "autoscaling": { "min_replicas": 2, "max_replicas": 5 }, "created_at": "2019-08-24T14:15:22Z"}