Quota not visible for "online_prediction_requests_per_base_model" in Vertex AI

Google Cloud Build with AI Generative AI & Foundational Models
1

Hello,

I am trying to use the veo-2.0-generate-001 model from the Vertex AI API in the us-central1 region. My project ID is gen-lang-client-0196977573.

The API is consistently returning a 429 Quota Exceeded error for the quota online_prediction_requests_per_base_model.

However, when I go to my Quotas dashboard, this specific quota is not listed, so I cannot request an increase. It seems the quota is not provisioned for my project.

Could you please help me make this quota visible or increase its limit?

Thank you.

2

Hi lbt00001,

You’re encountering a common issue with new or specific model quotas that may not be immediately visible in the Google Cloud Console. Since the veo-2.0-generate-001 model is relatively new, its quotas might be handled differently or set to very low initial limits.

Here are some suggestions you can try to make your quota visible or request an increase:

  • Submit a quota increase, you may refer to Vertex AI Quotas in the Google Cloud Console. Even if the quota is not listed, you can still file a request by scrolling to the bottom of the page and clicking on the “Request quota adjustment”. In the form, be sure to include your project ID, the region (us-central1), and the model name (veo-2.0-generate-001). Additionally, specify that the quota is missing and you are encountering a 429 error. This will help the support team understand the issue and assist in increasing your quota.

  • If you’re on a paid support plan, you can open a case through Google Cloud Support, which is the most direct way to get help provisioning hidden quotas.

  • While waiting for quota changes, you may implement retry logic with exponential backoff to reduce the chance of hitting the limit.