Help Center/ ModelArts/ ModelArts User Guide (Standard)/ Using ModelArts Standard to Deploy Models for Inference and Prediction/ Deploying a Model as Real-Time Inference Jobs/ Accessing a Real-Time Service Through Different Channels/ Accessing a Real-Time Service Through a Public Network
Updated on 2025-08-18 GMT+08:00
View PDF
Share

Accessing a Real-Time Service Through a Public Network

Context

ModelArts inference accesses real-time services through the public network by default, supporting both HTTPS and WebSocket protocols. After a real-time service is deployed, a standard RESTful API is provided for you to call. You can view the API URL on the Usage Guides tab page of the service details page.

Figure 1 API URL

Constraints

When you call an API to access a real-time service, the size of the prediction request body and the prediction time are subject to the following limitations:
  • The size of a request body cannot exceed 12 MB. Otherwise, the request will fail.
  • Due to the limitation of API Gateway, the prediction duration of each request does not exceed 40 seconds.

Accessing a Real-Time Service

The following authentication modes are available for accessing real-time services from a public network: