v1

latestOpenAPI 3.0.3LILT Platform Terms and Conditions2026-07-26651658.7 KB

Translate

Translate a segment

Translate a source string.

Functionally identical to POST /v2/translate, with parameters passed as query string parameters instead of a JSON request body. Useful for simple integrations that prefer a GET request.

Setting the rich parameter to true will change the response format to include additional information about each translation including a model score, word alignments, and formatting information.

By default, this endpoint also returns translation memory (TM) fuzzy matches, along with associated scores. Fuzzy matches always appear ahead of machine translation output in the response.

The maximum source length is 5,000 characters.

Usage charges apply to this endpoint for production API keys.

get/v2/translate

Query parameters

sourcestring

The source string to translate.

memory_idinteger required

A unique Memory identifier.

source_hashinteger

A source hash code.

ninteger

Return top n translations (deprecated).

prefixstring

A target prefix.

richboolean

Returns rich translation information (e.g., with word alignments).

tm_matchesboolean

Include translation memory fuzzy matches.

project_tagsboolean

Project tags. Projects tags in source to target if set to true.

contains_icu_databoolean

Contains ICU data. If true then tags in the source following the ICU standard will be parsed and retained.

Response

A TranslationList object.

untokenizedSourcestring

The untokenized source segment. Punctuation has not been separated from words.

tokenizedSourcestring

The tokenized source segment. Punctuation has been separated from words.

sourceDelimitersstring[]

A format string that indicates, for each word, if the word should be preceded by a space.

Example response

{
  "untokenizedSource": "Authentication not required.",
  "tokenizedSource": "Authentication not required .",
  "sourceDelimiters": [
    "",
    " ",
    " ",
    "",
    ""
  ]
}