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) |
100,000,000 |
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 Recommendations AI in the Services dropdown list.
You can see recent quota usage by going to the API Dashboard, selecting the Recommendations AI 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.
In the Quotas page, select Recommendations AI in the Services dropdown list.
Select the quotas you want to change.
Click EDIT QUOTAS.
Fill out your name, email, and phone number and click Next.
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.
Limits
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.