Great Work Labs
Models / Understand text

Lingo

Language detection
lingo-1

Which language is this? 183 of them, from a few words up.

Price$0.02 per 1,000 texts
Speed (our servers)23 to 115 ms
Languages183 languages and scripts (FLORES-200)
InputText, batches up to 64
Built onHorizon-Labs/language-detection-small (Apache-2.0)

Lingo names the language of a text and its script, from a full page down to a short phrase. It returns an ISO code you can store, the language's English name, and the runner-up guesses with scores.

Use only to restrict the answer to languages you expect: it's the easiest way to stop a short message in Spanish being called Galician.

Use it

curl https://labs.greatwork.company/v1/run \
  -H "Authorization: Bearer $GWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "lingo-1",
  "input": "¿Dónde está la estación de tren más cercana? Llevamos una hora caminando."
}'

Set GWL_API_KEY to a key from your dashboard. The bare name lingo works too and follows new versions.

Options

input: A string, or an array of up to 64 strings to run as a batch.

NameTypeDefaultWhat it does
top_kinteger3How many candidate languages to return.
onlystring[]Restrict answers to these languages (ISO 639-1 like en, or FLORES codes like eng_Latn).

Output

FieldTypeMeaning
languagestringBest guess as an ISO 639 code (en, es, zh), or the 3-letter code when no 2-letter code exists.
namestringEnglish name of the language.
scriptstringISO 15924 script code (Latn, Cyrl, Hani).
codestringFLORES-200 code, language plus script (eng_Latn).
scorenumberConfidence, 0 to 1.
candidatesobject[]Top guesses with language, name, code and score.

Every response wraps this in {"id", "model", "output", "usage": {"units", "unit", "cost_usd"}, "latency_ms"}. Send an array as input and output is an array in the same order.

Examples

Spanish

{
  "model": "lingo-1",
  "input": "¿Dónde está la estación de tren más cercana? Llevamos una hora caminando."
}
{
  "language": "es",
  "name": "Spanish",
  "script": "Latn",
  "code": "spa_Latn",
  "score": 0.8457,
  "candidates": [
    {
      "language": "es",
      "name": "Spanish",
      "script": "Latn",
      "code": "spa_Latn",
      "score": 0.8457
    },
    {
      "language": "eu",
      "name": "Basque",
      "script": "Latn",
      "code": "eus_Latn",
      "score": 0.0376
    },
    {
      "language": "gn",
      "name": "Guarani",
      "script": "Latn",
      "code": "grn_Latn",
      "score": 0.0269
    }
  ]
}

Captured on our production servers: 85 ms, 1 text, $0.00002.

Batch of three

{
  "model": "lingo-1",
  "input": [
    "Merci beaucoup pour votre aide !",
    "Vielen Dank für die schnelle Antwort.",
    "ありがとうございます、助かりました。"
  ]
}
[
  {
    "language": "fr",
    "name": "French",
    "script": "Latn",
    "code": "fra_Latn",
    "score": 0.3579,
    "candidates": [
      {
        "language": "fr",
        "name": "French",
        "script": "Latn",
        "code": "fra_Latn",
        "score": 0.3579
      },
      {
        "language": "ln",
        "name": "Lingala",
        "script": "Latn",
        "code": "lin_Latn",
        "score": 0.1971
      },
      {
        "language": "wo",
        "name": "Wolof",
        "script": "Latn",
        "code": "wol_Latn",
        "score": 0.1914
      }
    ]
  },
  {
    "language": "de",
    "name": "German",
    "script": "Latn",
    "code": "deu_Latn",
    "score": 0.9045,
    "candidates": [
      {
        "language": "de",
        "name": "German",
        "script": "Latn",
        "code": "deu_Latn",
        "score": 0.9045
      },
      {
        "language": "ak",
        "name": "Akan",
        "script": "Latn",
        "code": "aka_Latn",
        "score": 0.0107
      },
      {
        "language": "lb",
        "name": "Luxembourgish",
        "script": "Latn",
        "code": "ltz_Latn",
        "score": 0.0104
      }
    ]
  },
  {
    "language": "ja",
    "name": "Japanese",
    "script": "Jpan",
    "code": "jpn_Jpan",
    "score": 0.9974,
    "candidates": [
      {
        "language": "ja",
        "name": "Japanese",
        "script": "Jpan",
        "code": "jpn_Jpan",
        "score": 0.9974
      },
      {
        "language": "ak",
        "name": "Akan",
        "script": "Latn",
        "code": "aka_Latn",
        "score": 0.0003
      },
      {
        "language": "ko",
        "name": "Korean",
        "script": "Hang",
        "code": "kor_Hang",
        "score": 0.0002
      }
    ]
  }
]

Captured on our production servers: 115 ms, 3 texts, $0.00006.

Restricted

{
  "model": "lingo-1",
  "input": "obrigado pela ajuda",
  "only": [
    "pt",
    "es",
    "gl"
  ]
}
{
  "language": "pt",
  "name": "Portuguese",
  "script": "Latn",
  "code": "por_Latn",
  "score": 0.9805,
  "candidates": [
    {
      "language": "pt",
      "name": "Portuguese",
      "script": "Latn",
      "code": "por_Latn",
      "score": 0.9805
    },
    {
      "language": "gl",
      "name": "Galician",
      "script": "Latn",
      "code": "glg_Latn",
      "score": 0.0148
    },
    {
      "language": "es",
      "name": "Spanish",
      "script": "Latn",
      "code": "spa_Latn",
      "score": 0.0046
    }
  ]
}

Captured on our production servers: 23 ms, 1 text, $0.00002.

Good for

  • Route support tickets to the right team
  • Pick the translation or speech model to call next
  • Tag user content for search filters
  • Spot replies in the wrong language before sending

Limits and caveats

  • Very short texts (one or two words) are often low confidence: check score.
  • Mixed-language text gets one label.
  • Chinese is one label (zh, Simplified and Traditional together); Arabic dialects are one label (ar).
  • Weaker on Bosnian vs Croatian vs Serbian (Latin).

Pricing

$0.02 per 1,000 texts. One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. Failed calls aren't charged, and a call never costs more than its estimate (POST /v1/estimate tells you before you run it).

Built on

Horizon-Labs/language-detection-small, 141M (mmBERT-small encoder) parameters. License: Apache-2.0. We run it on our servers with our own long-text chunking and score aggregation.