Help Center/ ModelArts/ FAQs/ Inference Deployment (New Version)/ Can Upgrading a Real-Time Service Deployment Retain Compatibility with the Original API?
Updated on 2026-07-02 GMT+08:00
View PDF
Share

Can Upgrading a Real-Time Service Deployment Retain Compatibility with the Original API?

ModelArts supports multiple versions and flexible traffic policies. You can modify a service deployment to upgrade the deployment or switch between real-time service versions to smoothly upgrade the service version. When you modify a real-time service deployment to upgrade the deployment, its prediction API remains unchanged.

The procedure for switching between real-time service versions is as follows.

Prerequisites

Multiple versions of the real-time service have been deployed.

Procedure

  1. Log in to the ModelArts console and choose Model Inference > Real-Time Inference.
  2. Click the target service name. On the service details page that is displayed, switch to the Deploy tab.
  3. Locate the target deployment card and choose ... > Change Version to switch the current version.
  4. In the displayed dialog box, select the target version of the real-time service, click Switch to This Version in the Operation column, confirm the version comparison information, and click OK.
  5. The URL used to call the real-time service remains unchanged before and after the deployment version is changed.
Parent Topic: Inference Deployment (New Version)