August 1, 2018
On August 15, the default Characters per day quota will be updated to unlimited. For more information, see Quotas & Limits.
November 1, 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 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
now supports the Neural Machine Translation (NMT) model. However, we
recommend that you use the
endpoint for requests to the Translation API.
April 6, 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.
query parameter has been added to the
method. You can use the
base to use the PBMT model, and
nmt to use the
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