Help Center/ ModelArts/ FAQs/ Inference Deployment (New Version)/ What Is the Format of a Real-Time Service API?
Updated on 2026-07-02 GMT+08:00
View PDF
Share

What Is the Format of a Real-Time Service API?

After a real-time inference service is deployed, you can use the API for prediction.

The format of a prediction API is as follows:

Protocol://IP or domain name/Version/infer/Service ID

The following shows an example.

Table 1 Prediction API examples

Protocol

Example

https

https://xxx/v2/infer/41dc3228-5bd1-44b6-xxxxxxxxxxxx

http

http://xxx/v2/infer/d9b15284-6e49-463d-98b6-xxxxxxxxxxxx

wss

wss://xxx/v2/infer/d9b15284-6e49-463d-98b6-xxxxxxxxxxxx

ws

ws://xxx/v2/infer/d9b15284-6e49-463d-98b6-xxxxxxxxxxxx
Parent Topic: Inference Deployment (New Version)