This endpoint creates a deployment, which is an instance for running a model and performing predictions.
To create a deployment, you only need to provide a unique name. Upon successful creation, the endpoint will return an HTTP URL where you can send requests for predictions (also known as inferences).
The deployment name cannot be changed after creation.
Here’s a breakdown of the deployment creation options:
Model (Optional): You can either:
Threshold (Optional):
Successful Response
The response is of type object
.