> ## Documentation Index > Fetch the complete documentation index at: https://support.lilt.com/llms.txt > Use this file to discover all available pages before exploring further. # Translate a segment > Translate a source string. 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. The rich format can be seen in the example response on this page. 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. ## OpenAPI ````yaml /api-reference/openapi-bundled.yaml post /v2/translate openapi: 3.0.3 info: title: LILT API description: > LILT API Support: https://lilt.atlassian.net/servicedesk/customer/portals The LILT API enables programmatic access to the full-range of LILT backend services including: * Training of and translating with interactive, adaptive machine translation * Large-scale translation memory * The Lexicon (a large-scale termbase) * Programmatic control of the LILT CAT environment * Translation memory synchronization Requests and responses are in JSON format. The REST API only responds to HTTPS / SSL requests. The base url for this REST API is `https://api.lilt.com/`. ## Authentication Requests are authenticated via API key, which requires the Business plan. Requests are authenticated using [HTTP Basic Auth](https://en.wikipedia.org/wiki/Basic_access_authentication). Add your API key as both the `username` and `password`. For development, you may also pass the API key via the `key` query parameter. This is less secure than HTTP Basic Auth, and is not recommended for production use. ## Quotas Our services have a general quota of 4000 requests per minute. Should you hit the maximum requests per minute, you will need to wait 60 seconds before you can send another request. version: v3.0.3 license: name: LILT Platform Terms and Conditions url: https://lilt.com/lilt-platform-terms-and-conditions servers: - url: https://api.lilt.com security: - BasicAuth: [] - ApiKeyAuth: [] paths: /v2/translate: post: tags: - Translate summary: Translate a segment description: >+ Translate a source string. 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. The rich format can be seen in the example response on this page. 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. operationId: translateSegmentPost requestBody: content: application/json: schema: title: TranslateSegmentBody required: - memory_id type: object properties: source: type: string description: A unique Segment identifier. memory_id: type: integer description: A unique Memory identifier. source_hash: type: integer description: A source hash code. 'n': type: integer description: Return top n translations (deprecated). prefix: type: string description: A target prefix rich: type: boolean description: >- Returns rich translation information (e.g., with word alignments). default: false tm_matches: type: boolean description: Include translation memory fuzzy matches. default: true project_tags: type: boolean description: >- Project tags. Projects tags in source to target if set to true. default: false containsICUData: type: boolean description: >- Contains ICU data. If true then tags in the source following the ICU standard will be parsed and retained. default: false required: false responses: '200': description: A TranslationList object. content: application/json: schema: $ref: '#/components/schemas/TranslationList' '401': $ref: '#/components/responses/UnauthorizedError' default: description: Unexpected error content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: TranslationList: type: object properties: untokenizedSource: type: string description: >- The untokenized source segment. Punctuation has not been separated from words. example: Authentication not required. tokenizedSource: type: string description: >- The tokenized source segment. Punctuation has been separated from words. example: Authentication not required . sourceDelimiters: type: array description: >- A format string that indicates, for each word, if the word should be preceded by a space. example: - '' - ' ' - ' ' - '' - '' items: type: string translation: type: array description: A list of Translation objects. items: $ref: '#/components/schemas/Translation' description: An ranked list of translations and associated metadata. Error: type: object properties: message: type: string description: A human-readable message describing the error. description: | Response in the event of an unexpected error. example: message: Internal server error. Translation: type: object properties: target: type: string description: The target string. targetWithTags: type: string description: The target string with source tags projected into the target. align: type: string description: > "MT only: A whitespace delimited list of source-target alignment indices." provenance: type: string description: > Positive values indicate that the word is from the Memory, with contiguous identical entries (e.g., 2 2) indicating phrase matches. Negative contiguous values indicate entries from the Lexicon. 0 indicates a word from the background data. score: type: number description: The score of the translation. isTMMatch: type: boolean description: 'TM only: If true, indicates an exact translation memory match.' targetDelimiters: type: array description: >- A format string that indicates, for each word, if the word should be preceded by a space. items: type: string targetWords: type: array description: > The target string can be constructed by suffixing each `targetDelimiters` entry with its corresponding word in `targetWords` and concatenating the constructed array. Please note that the `targetDelimiters` array has one more entry than `targetWords` array which is why the last entry in the array will be the last value of `targetDelimiters`. items: type: string description: >- A machine translation (MT) or a translation memory (TM) match of a source segment. example: - score: 3.4936864e-8 align: 0-0 1-1 2-2 3-3 targetDelimiters: - '' - ' ' - ' ' - '' - '' targetWords: - Authentifizierung - nicht - erforderlich - . target: Authentifizierung nicht erforderlich . targetWithTags: Authentifizierung nicht erforderlich. isTMMatch: false provenance: 0 0 0 0 responses: UnauthorizedError: description: Unauthorized content: application/octet-stream: schema: type: string text/plain: schema: type: string securitySchemes: BasicAuth: type: http scheme: basic ApiKeyAuth: type: apiKey name: key in: query ````