Stay organized with collections
Save and categorize content based on your preferences.
This document lists the quotas and system limits that apply to
AI Applications.
Quotas specify the amount of a countable, shared resource that you
can use. Quotas are defined by Google Cloud services such as
AI Applications.
System limits are fixed values that cannot be changed.
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
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.
There are also system limits on AI Applications resources.
System limits can't be changed.
Allocation quotas
The following quotas don't reset over time. Instead, they're released when you
release the resource. You can request a quota increase
if the default quota isn't enough.
Quota
Value
Total number of data stores per project
100*
Total number of engines per project
150†
Number of pending import long running operations per project
300
Number of pending purge documents long running operations per project
100
Number of serving controls per project
1,000
Number of boost serving controls per serving config
100
Number of filter serving controls per serving config
100
Number of redirect serving controls per serving config
100
Number of synonym serving controls per serving config
100
Regional number of data stores per project per location (Global, US, EU)
100
Regional number of documents per project per location (Global, US, EU)
10,000,000
Regional number of engines per project per location (Global, US, EU)
150
Regional number of user events per project per location (Global, US, EU)
40,000,000,000
* Due to a technical limitation, the maximum quota for data stores is
500 per project. If you need more data stores, use new projects.
† Due to a technical limitation, the maximum quota for engines is 500
per project. If you need more engines, use new projects.
Rate quotas
The following quotas apply to AI Applications API requests. You can
request a quota increase if the default quota
isn't enough.
Quota
Value
Complete query requests per minute per project
300
Conversational search read requests per minute per project
300
Conversational search write requests per minute per project
300
Document batch requests (such as inline import and purge) per minute per project
100
Document async import (Cloud Storage, BigQuery, etc.) requests per minute per project
5
Document purge requests per minute per project
100
Document read requests per minute per project
300
Document write requests per minute per project
12,000
Evaluation create requests per day per project
5
Evaluation read requests per minute per project
100
Evaluation write requests per minute per project
100
LLM query requests (search summarization, multi-turn search) per minute per project
60
Number of pending FHIR or BigQuery streaming writes per minute
6,000
Number of sample query sets per project
100
Ranking API requests per minute per project
500
Recommend requests per minute per project
60,000
Sample query read requests per minute per project
200
Sample query set read requests per minute per project
100
Sample query set write requests per minute per project
100
Sample query write requests per minute per project
200
Schema read requests per minute per project
100
Schema write requests per minute per project
100
Regional search requests per minute per project per location (Global, US, EU)
300
User event batch requests (such as import and purge) per minute per project
100
User event collect requests per minute per project per user
240
User event write requests per minute per project
60,000
Quota for web page indexing
When you have a data store with
Advanced website indexing
turned on, every web page that you index counts towards the "Number of documents
per project" quota in the Allocation quotas list. You can
also see the number of pages in your project and the page quota for that project
in the Project pages vs quota field in the Data page for a data store.
If you add websites to a data store in a project and the web pages in those
websites exceed the project's quota, the websites are not
indexed. If you have websites in your data store that are already indexed, those
websites continue to be indexed as before. You can request to upgrade your
quota at any time.
Request a quota increase
To adjust most quotas, use the Google Cloud console.
For more information, see
Request a quota adjustment.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[[["\u003cp\u003eQuotas define the amount of shared resources, like hardware, software, and network components, that a Google Cloud project can use within Vertex AI Agent Builder, and they are set by Google Cloud services to ensure fairness and prevent overloading.\u003c/p\u003e\n"],["\u003cp\u003eSystem limits are fixed constraints on Vertex AI Agent Builder resources that cannot be altered, unlike quotas, which can be increased upon request.\u003c/p\u003e\n"],["\u003cp\u003eThere are two types of quotas detailed: allocation quotas, which are released when the resource is no longer in use and include limits like the number of documents or data stores per project, and request quotas, which apply to API requests and involve limits on requests like document read/write, search, and user events per minute.\u003c/p\u003e\n"],["\u003cp\u003eIndexing web pages in a data store with Advanced website indexing enabled counts towards the "Number of documents per project" quota, and exceeding this quota will prevent new web pages from being indexed, though already indexed pages will continue as before.\u003c/p\u003e\n"],["\u003cp\u003eYou can request increases to most quotas, but system limits cannot be modified, and you can go to the "Request a quota adjustment" page on the Google cloud console for more information.\u003c/p\u003e\n"]]],[],null,["This document lists the quotas and system limits that apply to\nAI Applications.\n\n- *Quotas* specify the amount of a countable, shared resource that you can use. Quotas are defined by Google Cloud services such as AI Applications.\n- *System limits* are fixed values that cannot be changed.\n\nGoogle Cloud uses quotas to help ensure fairness and reduce\nspikes in resource use and availability. A quota restricts how much of a\nGoogle Cloud resource your Google Cloud project can use. Quotas\napply to a range of resource types, including hardware, software, and network\ncomponents. For example, quotas can restrict the number of API calls to a\nservice, the number of load balancers used concurrently by your project, or the\nnumber of projects that you can create. Quotas protect the community of\nGoogle Cloud users by preventing the overloading of services. Quotas also\nhelp you to manage your own Google Cloud resources.\n\nThe Cloud Quotas system does the following:\n\n- Monitors your consumption of Google Cloud products and services\n- Restricts your consumption of those resources\n- Provides a way to [request changes to the quota value](/docs/quotas/help/request_increase) and [automate quota adjustments](/docs/quotas/quota-adjuster)\n\nIn most cases, when you attempt to consume more of a resource than its quota\nallows, the system blocks access to the resource, and the task that\nyou're trying to perform fails.\n\nQuotas generally apply at the Google Cloud project\nlevel. Your use of a resource in one project doesn't affect\nyour available quota in another project. Within a Google Cloud project, quotas\nare shared across all applications and IP addresses.\n\n\nThere are also *system limits* on AI Applications resources.\nSystem limits can't be changed.\n| **Note:** Google Cloud products that use the Discovery Engine API, AI Applications (also known as Vertex AI Search) and Google Agentspace, share quotas. This means that your search and recommendations apps in Vertex AI Search share quotas with your apps in Google Agentspace.\n\nAllocation quotas\n\nThe following quotas don't reset over time. Instead, they're released when you\nrelease the resource. You can [request a quota increase](#request-a-quota-increase)\nif the default quota isn't enough.\n\n| Quota | Value |\n|--------------------------------------------------------------------------|----------------|\n| Total number of data stores per project | 100^\\*^ |\n| Total number of engines per project | 150^†^ |\n| Number of pending import long running operations per project | 300 |\n| Number of pending purge documents long running operations per project | 100 |\n| Number of serving controls per project | 1,000 |\n| Number of boost serving controls per serving config | 100 |\n| Number of filter serving controls per serving config | 100 |\n| Number of redirect serving controls per serving config | 100 |\n| Number of synonym serving controls per serving config | 100 |\n| Regional number of data stores per project per location (Global, US, EU) | 100 |\n| Regional number of documents per project per location (Global, US, EU) | 10,000,000 |\n| Regional number of engines per project per location (Global, US, EU) | 150 |\n| Regional number of user events per project per location (Global, US, EU) | 40,000,000,000 |\n\n\n^\\*^ Due to a technical limitation, the maximum quota for data stores is\n500 per project. If you need more data stores, use new projects.\n\n\n^†^ Due to a technical limitation, the maximum quota for engines is 500\nper project. If you need more engines, use new projects.\n| **Note:** The number of data stores, documents, user events, and engines across all locations can't exceed the total per-project quota for that resource. For example, if you already have 60 data stores in the `eu` multi-region and 40 in the `us` multi-region, you can't create another data store because the overall data store quota for the project is 100.\n\nRate quotas\n\nThe following quotas apply to AI Applications API requests. You can\n[request a quota increase](#request-a-quota-increase) if the default quota\nisn't enough.\n\n| Quota | Value |\n|---------------------------------------------------------------------------------------|--------|\n| Complete query requests per minute per project | 300 |\n| Conversational search read requests per minute per project | 300 |\n| Conversational search write requests per minute per project | 300 |\n| Document batch requests (such as inline import and purge) per minute per project | 100 |\n| Document async import (Cloud Storage, BigQuery, etc.) requests per minute per project | 5 |\n| Document purge requests per minute per project | 100 |\n| Document read requests per minute per project | 300 |\n| Document write requests per minute per project | 12,000 |\n| Evaluation create requests per day per project | 5 |\n| Evaluation read requests per minute per project | 100 |\n| Evaluation write requests per minute per project | 100 |\n| LLM query requests (search summarization, multi-turn search) per minute per project | 60 |\n| Number of pending FHIR or BigQuery streaming writes per minute | 6,000 |\n| Number of sample query sets per project | 100 |\n| Ranking API requests per minute per project | 500 |\n| Recommend requests per minute per project | 60,000 |\n| Sample query read requests per minute per project | 200 |\n| Sample query set read requests per minute per project | 100 |\n| Sample query set write requests per minute per project | 100 |\n| Sample query write requests per minute per project | 200 |\n| Schema read requests per minute per project | 100 |\n| Schema write requests per minute per project | 100 |\n| Regional search requests per minute per project per location (Global, US, EU) | 300 |\n| User event batch requests (such as import and purge) per minute per project | 100 |\n| User event collect requests per minute per project per user | 240 |\n| User event write requests per minute per project | 60,000 |\n\nQuota for web page indexing\n\nWhen you have a data store with\n[Advanced website indexing](/generative-ai-app-builder/docs/about-advanced-features#advanced-website-indexing)\nturned on, every web page that you index counts towards the \"Number of documents\nper project\" quota in the [Allocation quotas](#allocation-quotas) list. You can\nalso see the number of pages in your project and the page quota for that project\nin the **Project pages vs quota** field in the **Data** page for a data store.\n\nIf you add websites to a data store in a project and the web pages in those\nwebsites exceed the project's quota, the websites are not\nindexed. If you have websites in your data store that are already indexed, those\nwebsites continue to be indexed as before. You can request to [upgrade your\nquota](#request-a-quota-increase) at any time.\n\nRequest a quota increase\n\nTo adjust most quotas, use the Google Cloud console.\nFor more information, see\n[Request a quota adjustment](/docs/quotas/help/request_increase)."]]
