Vertex AI - veo-2.0-generate-001 Quota for "Regional online prediction requests per base model" is 0

Google Cloud Build with AI Custom ML & MLOps
1

Hello Google Cloud Community, I’m working on a project (Project ID: creo-ai-461218) and trying to use the Vertex AI API with the veo-2.0-generate-001 model in the us-central1 region. I’ve encountered an issue where all my API requests are failing with a 429 RESOURCE_EXHAUSTED error. Upon checking the Quotas page in the Google Cloud Console, I found that the quota for:

…is currently set to 0. Furthermore, the “Adjustable” column for this specific quota in us-central1 is marked as “No,” so I’m unable to request an increase through the self-service console. This effectively prevents any use of the veo-2.0-generate-001 model in this region for my project. Could someone from the Google Cloud team or the community please guide me on the correct procedure to get this essential quota reviewed and provisioned/increased for my project? Any assistance would be greatly appreciated as I’m currently blocked from proceeding with my development. Thank you for your time and help! Best regards, Dante

1 Like
2

Hi @Dantecool ,

You’re correct — the veo-2.0-generate-001 model often has zero default quota and manual approval required.

What to do:

  1. Go to: Vertex AI Quota Requests

  2. Filter by:

    • Service: Vertex AI API

    • Metric: online_prediction_requests_per_base_model

    • Location: us-central1

    • Model: veo-2.0-generate-001

  3. Since it’s not adjustable via console, click “Contact Support” or open a support case here:
    https://cloud.google.com/support

  4. In the request, mention:

    • Project ID: creo-ai-461218

    • Use case (briefly)

    • Region: us-central1

    • Model: veo-2.0-generate-001

Unfortunately, for preview/beta models like Veo, manual approval is required regardless of the account type.

3

Hi @Dantecool,

Welcome to Google Cloud Community!

The error 429 RESOURCE_EXHAUSTED usually indicates that the rate of your requests has surpassed the available processing capacity.

Ensure that you’re filtering the correct resources on the Google Cloud console quota page, specifically for veo-2.0-generate-001 in the us-central1 region. Once validated, and if applicable for a quota increase, you can refer to this documentation on how to request a quota increase. Free-tier users may have limited quota, if you are using the free tier and frequently encountering the 429 error, you may need to upgrade to a paid plan.

You can also implement a retry mechanism with exponential backoff, as this is essential for managing rate limits effectively.

Was this helpful? If so, please accept this answer as “Solution”. If you need additional assistance, reply here within 2 business days and I’ll be happy to help.

4

Hi folks,

I have this same issue however, I am not able to get a single request to work. When I look in console it says I have a limit of 10 however, when I try use through python I get a 429 resource exhaustion error. Has anyone found a solution for this?