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 Natural Language.

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 Natural Language resources. These limits are unrelated to the quota system. Limits cannot be changed unless otherwise stated.

Language restrictions

The Natural Language API currently supports only the languages listed in Language Support.

Content quotas

Content to the Natural Language API is provided as a text string. The Natural Language API processes this text into a series of tokens, which roughly correspond to word boundaries. All Natural Language API features (Sentiment Analysis, Entity Extraction, and Syntactic Analysis) use these tokens as the building blocks for performing analysis on the provided text.

The API contains the following quotas on the size of this content for each request:

Content Quota	Value	Overflow Result
Text Content	1,000,000 bytes	API Error
Token Quota	100,000 tokens	Ignored
Entity Mentions	5,000*	Ignored

Attempting to process content in excess of the Text Content quota will produce an error. Attempting to process tokens in excess of the Token Quota will not produce an error, but any tokens over that quota will be ignored.

Note that byte counts may not reflect character counts, depending on the encoding used within the text content.

* The Entity Mentions quota includes not only returned mentions within the document, but any noun references to those entities, including pronouns. Note that those pronouns are not returned directly in the mentions field, though they do count against the quota.

Request quotas

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

Type of Quota	Usage Quota
Requests per minute	600
Requests per day	800,000