To use a quick start model, deploy it from the Model Hub page and make requests through the API.
1On the Model Hub page, find the desired quick start model and click Start Deployment.
2When the status becomes Available, click the name of the quick start model on either the Model Hub page or the Monitor page. The overview pages opens and you can view information about the deployed quick start model, including the model endpoint URL.
The following image shows the overview information:
3Use the endpoint URL to make prediction requests through the API. For more information about making API requests, see Model Serve REST API.
4To release the resources, stop the deployment when you no longer need it.