Vertex AI in Google Distributed Cloud (GDC) air-gapped appliance provides pre-trained API
endpoints that let you interact with AI services programmatically from the
command-line interface. Checking the service status and endpoints helps you
verify deployments and troubleshoot integration issues across your
applications.

Follow these steps to view the status and endpoints of the
Optical Character Recognition (OCR), Speech-to-Text, and Vertex AI Translation
pre-trained APIs:

1. [Sign in to the GDC console](https://docs.cloud.google.com/distributed-cloud/hosted/docs/latest/appliance/platform/pa-user/iam/sign-in).
2. In the navigation menu, click **Vertex AI** \> **Pre-trained APIs**.
3. On the **Pre-trained APIs** page, you can review the following information:

   - View the status of each pre-trained API on the central panel. The status is
     either **Enabled** or **Not enabled** . If the status is **Not enabled** ,
     you can enable the corresponding API. For more information, see [Provision GPUs and enable Vertex AI pre-trained APIs](https://docs.cloud.google.com/distributed-cloud/hosted/docs/latest/appliance/application/ao-user/vertex-ai-enable-pre-trained-apis).

   - If the status of an API is **Enabled** , you can view its endpoint on the
     central panel. To use this endpoint for programmatically interacting with
     the Vertex AI service, click
     **Copy** to copy it to your clipboard.

If the system fails to enable the API, the page displays information to help you
troubleshoot the issue.

> [!CAUTION]
> **Caution:** GDC air-gapped appliance includes a single NVIDIA A100 80GB GPU. This limits the device to running only *one* GPU-dependent Vertex AI pre-trained API at a time. If you attempt to enable both Vertex AI Translation and OCR, the second API will fail to enable with an error message indicating insufficient GPU resources. You can, however, run Speech-to-Text alongside either Vertex AI Translation or OCR, as Speech-to-Text only requires CPU resources.