How to deploy a model to API

  1. Click in New deployment in the Deployment view.

    Select experiment and epoch in the Create deployment pop-up. Both best epoch and last epoch for each trained experiment are available for deployment.

  2. Make sure that the new deployment is selected in the Experiments navigation section.

    Deployment - select experiment
  3. Check that the input parameters of the request match the expected format and type in order to get a successful prediction. Adjust the parameters naming if needed for the service calls.

  4. Click the Enable switch to enable the deployment API.

    Deployment enabling
  5. The API is called by sending an HTTP POST to the endpoint URL shown in the interface. The token is required to authenticate the calls.

    Deployment API

Deploy an operational AI model tutorial

Learn how to build and deploy a model in the Deploy an operational AI model tutorial.

Try the platform