Skip to main content
Google Vertex AI integrations are deprecated and maintenance-only. New integrations cannot be created.Existing Enterprise integrations keep working and remain editable. You can update the region, model version, or service account. You can also enable, disable, or remove the integration.

​
Prerequisites for existing integrations

  • Your runner must be able to reach aiplatform.googleapis.com over HTTPS. For runners that egress through a private VPC, this means either Private Google Access on the runner’s subnet or a NAT gateway with outbound internet access. Without this, agent calls fail with connection errors.
  • The Claude models you use must stay enabled in Vertex AI Model Garden for your project.

​
Endpoint format

Existing integrations use endpoints of the form:
Use the global region for dynamic routing across available infrastructure.

​
Manage an existing integration

  1. Go to the Runners settings page
  2. Select the runner with the Vertex integration
  3. Scroll down to the “LLM Providers” section
  4. Click Edit on the Vertex integration. You can update:
    • Region: we recommend the global region for dynamic routing across available infrastructure.
    • Model Version: for example claude-sonnet-5. See Anthropic’s model availability.
    • Service Account JSON: drag a new service account file here to replace the stored one.
You can also disable or remove the integration from here.

​
Troubleshooting

Authentication errors
  • Verify your service account has the correct IAM roles (Vertex AI User)
  • Ensure the JSON key file is valid and properly formatted
  • Check that the Vertex AI API is enabled for your project
Endpoint not found
  • Verify your project ID, region, and model name in the endpoint URL
  • Ensure the model is available in your selected region
Permission denied
  • Check that your service account has Vertex AI User role
  • Verify your project has billing enabled
  • Ensure Vertex AI API is enabled
If you encounter issues:
  1. Check the Ona Agent logs for detailed error messages
  2. Verify your Google Cloud quotas and limits
  3. Contact your account manager for additional support