Quotas and limits

This page provides information about quotas and limits for Vertex AI Search for retail.

Default quotas

By default, your project has the following quotas for Vertex AI Search for retail.

To increase or otherwise edit these quotas, see Edit your quotas.

Quota Value
User event writes per minute 60,000
User event imports per minute 100
User event writes per user per minute 240
User event reads per minute 300
Product writes per minute 12,000
Product imports per minute 100
Product reads per minute 300
Predictions per minute 60,000
Predictions per minute for a specific user 60,000
Searches per minute 300
Completion read per minute 1200
Total user events 40,000,000,000
Total products (search not enabled) 40,000,000
Total products (search enabled) 4,000,000
Total tags
(sum of per-product tag counts, not unique tags)
Pending Cloud Storage import long running operations 300
Pending BigQuery import long running operations 100
Pending Merchant Center import long running operations 10
Concurrent active models 10
Total models (active and paused) 20
Total placements 100
Total Controls 100

Check your quotas

To check the current quotas for Vertex AI Search for retail resources in your project, go to the Quotas page in the Google Cloud console and select Vertex AI Search for Retail API in the Services dropdown list.

You can see recent quota usage by going to the API Dashboard, selecting Vertex AI Search for Retail API, and opening the Quotas tab.

Edit your quotas

As your use of Google Cloud expands over time, you might want to increase your quotas accordingly. Or you might need to limit certain quotas. If you expect a notable upcoming increase in usage, make your request to increase your quotas a few days in advance to ensure that your quotas are adequately sized.

  1. In the Quotas page, select Vertex AI Search for Retail API in the Services dropdown list.

  2. Select the quotas you want to change.

  3. Click EDIT QUOTAS.

  4. Fill out your name, email, and phone number and click Next.

  5. Fill in your quota request and click Submit request.

You will receive a response from the Vertex AI Search for retail team within 48 hours of your request.


The following limits are enforced:

  • You can start up to five model operations per minute. Limited model operations include creation, deletion, pause, and resume.

  • Your site can have up to 250,000 user event writes per visitor ID or user ID per week.

  • Your site can have up to 10,000 product writes per product ID per week and one product write per product ID per second. Too frequent updates on the same product are unexpected, and the additional updates might be rejected with a RESOURCE_EXHAUSTED error.