This page documents production updates to Translation API. We recommend that Translation API developers periodically check this list for any new announcements. Major changes are also announced via the google-translate-api mailing list.
To get the latest product updates delivered to you, add the URL of this page to your
reader, or add the feed URL directly:
November 05, 2019
Cloud Translation v3, rebranded as Translation API - Advanced, is now generally available. In addition to the features of Cloud Translation API v3beta1, Translation API - Advanced supports: * User labels * Audit logging * Separate quotas for batch translation and for translation using AutoML models * Client libraries for additional languages PHP, GO, C#, and Ruby
Note: Existing users should pay careful attention to client library versions before updating. Translation API - Basic and Translation API - Advanced client libraries are not backward or forward compatible.
Translation API - Advanced also fixes bugs from the v3beta1 version, notably for the glossary feature.
Translation API - Advanced has a revised pricing structure. Each account receives $10 worth of free usage per month, applied to usage of any of these SKUs:
- Neural Translation Model Predictions (D90A-CFB2-7CCD)
- Neural Translation Model Predictions In Translation V3 (E205-31DB-F1F4)
- Phrase-Based Translation Model Predictions (53BA-5E1D-4314)
This credit replaces the free tier for Text Translation requests using NMT for 0-500k characters on Translation API v3beta1.
April 10, 2019
- custom glossaries for customer-specific terminology,
- batch translation for asynchronous translation of .txt, .tsv, and .html files saved in Google Cloud Storage.
September 10, 2018
The maximum values for Characters per 100 seconds quotas have increased. The new maximum for both Characters per 100 seconds per project and Characters per 100 seconds per project per user is 10,000,000 characters. The default quotas remain unchanged.
The recently updated default Characters per day quota has been adjusted again; it is now 1 billion characters.
See Quotas & Limits.
August 22, 2018
The change to the default Characters per day quota has taken effect. It is now unlimited. See Quotas & Limits.
August 01, 2018
On August 15, the default Characters per day quota will be updated to unlimited. For more information, see Quotas & Limits.
November 01, 2017
The maximum Characters per day quota has been updated to unlimited. For more information, see Quotas & Limits.
October 25, 2017
The Neural Machine Translation (NMT) models for the following languages have been updated for improved translation quality:
- English (en) <-> French (fr)
- English (en) -> German (de)
- English (en) -> Spanish (es)
For a list of all NMT supported languages, see Language Support for the Neural Machine Translation Model.
September 26, 2017
Quotas for usage of the Translation API have been updated. The quota for characters requested per 100 seconds, per project has been updated to a maximum of 1,000,000. While the quotas are updated, you may see a brief period where the maximum is not limited to the per project maximum. The quota for characters requested per 100 seconds, per user remains at 100,000 characters per user, per project. For more information, see Quotas & Limits.
September 15, 2017
The Translation API has added support for 70 new languages in the Neural Machine Translation (NMT) model. For a list of all NMT supported languages, see Language Support for the Neural Machine Translation Model.
June 19, 2017
The Translation API no longer supports conditional HTTPS requests.
ETag headers in requests to the Translation API are ignored. The Translation API returns a status code of 200 for successful requests, but does not return a status code of 304 for conditional HTTPS requests. Conditional HTTPS requests are billed as a normal request to the Translation API.
https://www.googleapis.com/language/translate/v2 endpoint now supports the Neural Machine Translation (NMT) model. However, we recommend that you use the
https://translation.googleapis.com/language/translate/v2 endpoint for requests to the Translation API.
April 06, 2017
The Cloud Translation API is no longer taking requests for access to the Premium Edition (Beta). Instead, the premium features of the Cloud Translation API have been made generally available in the Standard Edition.
You now have access to the robust translation features available using the Neural Machine Translation (NMT) model. There is no difference in pricing between the standard, Phrase-Based Machine Translation (PBMT) model, and the NMT model.
By default, when you make a translation request to the Cloud Translation API, your text is translated using the NMT model. If the NMT model is not supported for the requested language translation pair, or if you explicitly request it, the PBMT model is used.
In order for your request to be translated using the NMT model, you must send your request to the current Translation API endpoint:
https://www.googleapis.com/language/translate/v2 endpoint does not support the NMT model.
NMT models are computationally intensive and may take more time to translate your query as compared to the same query translated using the PBMT model. If your application is latency sensitive, we recommend that you try both models to determine which best fits your needs for response time.
model query parameter has been added to the
translate method. You can use the model parameter to explicitly specify the translation model for your request. Specify
base to use the PBMT model, and
nmt to use the NMT model.
If you do not specify a
model parameter for your request, then
nmt is used.
If you specify the
nmt model, and the requested language translation pair is not supported for the NMT model, then the request is translated using the
November 15, 2016
Changed API endpoint from
API endpoint of
www.googleapis.com will continue to work, but migrate code to
translation.googleapis.com to take advantage of the latest features.