AutoML Translation API isdeprecatedand will no longer be available on Google Cloud after September 30, 2025. The functionality and management of custom models is available throughCloud Translate API - Advanced (v3).
Stay organized with collectionsSave and categorize content based on your preferences.
This document contains current restrictions and usage quotas on use of AutoML Translation.
This page will be updated to reflect any changes to these restrictions and usage quotas.
These quotas apply to each AutoML Translation project and each user, and are
shared across all applications and IP addresses using a given project.
You can edit your quotas up to their maximum values by selectingEDIT QUOTASfrom theQuotaspage of theGoogle Cloud Dashboard. Edit the quotas for theCloud AutoML API.
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.
AutoML Translation has quotas associated with creating models and with making
requests to the models.
Modeling quotas
Activity
Default quota
Model creation requests per minute
10
Concurrent translation model creation requests
2
Content and request quotas
Content to the AutoML Translation is provided as text strings, and both
pricing and usage are based on character counts. All characters sent to the
AutoML Translation, including whitespace characters, count towards these
quotas.
These per-project usage quotas for AutoML Translation apply collectively to all
deployed models.
Activity
Default quota
AutoML model characters per minute
100,000
AutoML model characters per minute per user
up to the per project quota
Batch translation requests per day
unlimited
By adjusting the per user quota, you can set an upper limit on the number of
characters per minute that individual users can translate in a given project.
This quota applies only if it is set to be less than the overall characters
per minute quota.
Content and request limits
On each individualtranslateTextrequest to an AutoML model, there is a limit of1024strings in the contents field.
[[["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 2025-09-04 UTC."],[],[],null,["# Quotas & Limits\n\nThis document contains current restrictions and usage quotas on use of AutoML Translation.\nThis page will be updated to reflect any changes to these restrictions and usage quotas.\n\nThese quotas apply to each AutoML Translation project and each user, and are\nshared across all applications and IP addresses using a given project.\n\nYou can edit your quotas up to their maximum values by selecting **EDIT QUOTAS**\nfrom the **Quotas** page of the\n[Google Cloud Dashboard](https://console.cloud.google.com/project/_/quotas). Edit the quotas for the **Cloud AutoML API**.\nTo request an increase above the maximum quota, edit your quota with\nyour requested increase and justification and submit your update.\nYou will be notified when your request has been received. You might be\ncontacted for more information regarding your request. After your request\nhas been reviewed, you will be notified whether it has been approved or denied.\n\nAutoML Translation has quotas associated with creating models and with making\nrequests to the models.\n\nModeling quotas\n---------------\n\nContent and request quotas\n--------------------------\n\nContent to the AutoML Translation is provided as text strings, and both\npricing and usage are based on character counts. All characters sent to the\nAutoML Translation, including whitespace characters, count towards these\nquotas.\n\nThese per-project usage quotas for AutoML Translation apply collectively to all\ndeployed models.\n\nBy adjusting the per user quota, you can set an upper limit on the number of\ncharacters per minute that individual users can translate in a given project.\nThis quota applies only if it is set to be less than the overall characters\nper minute quota.\n\nContent and request limits\n--------------------------\n\n- On each individual `translateText` request to an AutoML model, there is a limit of **1024** strings in the contents field.\n\nSee also\n--------\n\n- [Cloud Translation API Reference](https://cloud.google.com/translate/docs/reference/rest)"]]
