Platform for AI (PAI) provides an end-to-end machine learning solution that covers data processing, model training, service deployment, and online prediction for both traditional machine learning and deep learning workloads.
PAI Elastic Algorithm Service (EAS) deploys trained models as online inference services. EAS allows you to publish trained models to API Gateway as RESTful APIs, so that business systems can invoke predictions through standard HTTP requests.
For instructions on calling a deployed prediction service, see Call a service over a public endpoint.