This Recommendations AI documentation references the Recommendations console. We recommend switching to the Retail console and using the Retail documentation, which documents Recommendations AI, the Retail console, and Retail Search.

If you are using the v1beta version of Recommendations AI, migrate to the Retail API version.

Quotas and limits

This page provides information about the Recommendations AI quotas and limits.

Default quotas

By default, your project has the following Recommendations AI 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
Catalog item writes per minute 12,000
Catalog item imports per minute 100
Catalog item reads per minute 300
Predictions per minute 60,000
Predictions per minute for a specific user 60,000
Total user events 40,000,000,000
Total catalog items 40,000,000
Total tags
(sum of per-item 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

Checking your quotas

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

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

Increasing your quotas

As your use of Google Cloud expands over time, your quotas can increase accordingly. If you expect a notable upcoming increase in usage, you should make your request a few days in advance to ensure your quotas are adequately sized.

  1. In the Quotas page, select Retail 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 Recommendations AI team within 48 hours of your request.


Recommendations AI enforces the following limits:

  • You can register up to 20 API keys per project for making prediction requests.

  • You can start up to 5 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 have up to 10,000 catalog item writes per item ID per week.