This legacy version of AutoML Video Intelligence is deprecated and will no longer be available on Google Cloud after January 23, 2024. All the functionality of legacy AutoML Video Intelligence and new features are available on the Vertex AI platform. See Migrate to Vertex AI to learn how to migrate your resources.
Stay organized with collections Save and categorize content based on your preferences.

Quotas and limits

This page describes current restrictions and usage quotas on use of AutoML Video Intelligence Classification and is updated to reflect any changes to said restrictions and usage quotas.

These quotas apply to each AutoML Video project and are shared across all applications and IP addresses using a given project.


You can request an increase to your quotas from the Google Cloud console. To learn more, see the information on managing your quotas.

Activity Default quota
Requests 600 per minute per project
Create model requests 10 per minute per project
Concurrent model creation 5 per project
Concurrent batch prediction 5 per project


Type of limits Value
Maximum video length 3 hours
Maximum video file size 50GB
Minimum labels per dataset 2
Minimum videos per label 10 (1000 is recommended)
Batch input CSV file size Maximum: 100MB
Number of video segments in batch input Maximum: 1,000