Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window. Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window.

Quotas and limits

This document lists the quotas and limits that apply to Cloud Vision.

Google Cloud uses quotas to help ensure fairness and reduce spikes in resource use and availability. A quota restricts how much of a Google Cloud resource your Google Cloud project can use. Quotas apply to a range of resource types, including hardware, software, and network components. For example, quotas can restrict the number of API calls to a service, the number of load balancers used concurrently by your project, or the number of projects that you can create. Quotas protect the community of Google Cloud users by preventing the overloading of services. Quotas also help you to manage your own Google Cloud resources.

The Cloud Quotas system does the following:

Monitors your consumption of Google Cloud products and services
Restricts your consumption of those resources
Provides a means to request changes to the quota value

In most cases, when you attempt to consume more of a resource than its quota allows, the system blocks access to the resource, and the task that you're trying to perform fails.

Quotas generally apply at the Google Cloud project level. Your use of a resource in one project doesn't affect your available quota in another project. Within a Google Cloud project, quotas are shared across all applications and IP addresses.

To increase or decrease most quotas, use the Google Cloud console. For more information, see Request a higher quota.

There are also limits on Vision resources. These limits are unrelated to the quota system. Limits cannot be changed unless otherwise stated.

Quota types

There are 3 kinds of quota:

Request Quota
- The quota counts per request sent to Vision API endpoint.
Feature Quota
- The quota counts per image / file sent to Vision API endpoint.
- Unless specified explicitly, quota with feature name as prefix is generally a Feature quota.
In Processing Quota
- The quota counts per image / file being processed by Vision API unless specified explicitly.
- Can be inferred by "in processing" in quota name.
- This quota determines the maximum number of images/pages that Vision API processes at a time for the asynchronous methods. Users can send more than this quota into the asynchronous methods, but the images/pages over the quota are not processed immediately. The files in excess of the quota are added to a queue to be processed later.

The current API usage quotas for the Vision API are as follows (and are subject to change):

Vision API quota	Quota type	Value
Requests per minute (except request types listed below)	Request quota	1,800
Celebrity recognition requests per minute	Request quota	zero
Label detection requests per minute	Feature quota	1,800
Text detection requests per minute	Feature quota	1,800
Asynchronous image annotation* number of images in processing	In Processing quota	8,000
Asynchronous document text detection^† number of pages in processing	In Processing quota	10,000

Product Search quota	Value
Requests per minute (except request types listed below)	1,800
Batch requests per day	300
Resource management write requests per minute	1,200
Resource management requests per minute	2,400

These limits apply to each Google Cloud console project and are shared across all applications and IP addresses using that project.

Lower quotas can be set per user in the Google Cloud console.

Quota increases

You can edit your quotas up to their maximum values by selecting EDIT QUOTAS from the Quotas page of the Google Cloud console page. To request an increase above the maximum quota, edit your quota with your requested increase and justification and submit your update. You will be notified when your request has been received. You might be contacted for more information regarding your request. After your request has been reviewed, you will be notified whether it has been approved or denied.

Generally each quota has "per project per user" and "per project" variants, please change them correspondingly to your setup.

When requesting feature a quota increase, consider the overall request quota and intended batch size to assure the following:

overall request quota (Requests per minute) * your batch size >= increased feature quota

If you do not fulfill this requirement, you will still be throttled by the overall request quota.

This document contains current content limits and request quotas for the Vision API. This page will be updated to reflect any changes to these restrictions and usage limits.

Limits

The Vision API enforces the following usage limits:

Content Limit	Value
Image file size	20 MB
JSON request object size	10 MB
PDF file size	1 GB
Images per `images:annotate` request	16
Images per `images:asyncBatchAnnotate` request	2000
Pages per `files:annotate` request	5
Pages per `files:asyncBatchAnnotate` request	2000

Base64-encoded images may exceed the JSON size limit, even if they are within the image file size limit. Larger images should be hosted on Cloud Storage or at a publicly-accessible URL. Note that base64-encoded images can have a larger file size than the original image file (usually about 37% larger).

*	`images:asyncBatchAnnotate` requests
†	`files:asyncBatchAnnotate` requests, `DOCUMENT_TEXT_DETECTION` feature