IATE Terminology API

2,456,445 terms across 24 EU official languages. Exact lookup, semantic search, cross-lingual translation, TBX/TMX export, and custom glossaries.

Base URL: https://staging.pauhu.eu

Authentication: Authorization: Bearer YOUR_API_KEY — Get a key at /keys/.

Rate limits: Free tier: 3 requests/day. Paid tiers: per plan (see Pricing).

GET/iate/lookup

Exact term lookup against the full IATE terminology database. Returns matching entries with definitions, domains, and reliability scores.

Parameters

Example

curl "https://staging.pauhu.eu/iate/lookup?term=data%20protection&lang=fi" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "query": { "term": "data protection", "lang": "fi" },
  "found": true,
  "count": 3,
  "results": [
    {
      "id": 12345,
      "term": "tietosuoja",
      "definition": "Protection of personal data from unauthorised processing",
      "context": "Regulation (EU) 2016/679 (GDPR)",
      "domain": "1011",
      "reliability": 4,
      "language": "fi",
      "source": "IATE-1234567"
    },
    {
      "id": 12346,
      "term": "henkilotietojen suoja",
      "definition": "Protection of individuals with regard to the processing of personal data",
      "context": "Charter of Fundamental Rights, Article 8",
      "domain": "1236",
      "reliability": 4,
      "language": "fi",
      "source": "IATE-1234568"
    }
  ]
}

GET/iate/search

Fuzzy and semantic search across terminology. Uses 1024-dimensional embeddings (BGE-M3, cosine similarity) to find terms by meaning, not just exact string matches. Ideal for discovering related terminology you may not know the exact wording for.

Parameters

Example

curl "https://staging.pauhu.eu/iate/search?q=personal%20data%20processing&lang=en&domain=1236&limit=5" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "query": "personal data processing",
  "lang": "en",
  "domain": "1236",
  "count": 5,
  "results": [
    {
      "id": 23456,
      "term": "processing of personal data",
      "definition": "Any operation performed on personal data, whether or not by automated means",
      "context": "GDPR Article 4(2)",
      "domain": "1236",
      "reliability": 4,
      "language": "en",
      "source": "IATE-2345678",
      "score": 0.94
    },
    {
      "id": 23457,
      "term": "data controller",
      "definition": "Natural or legal person which determines the purposes and means of the processing of personal data",
      "context": "GDPR Article 4(7)",
      "domain": "1236",
      "reliability": 4,
      "language": "en",
      "source": "IATE-2345679",
      "score": 0.87
    }
  ]
}

Score range: 0.0 to 1.0 (cosine similarity). Scores above 0.8 indicate high relevance. See confidence scores below.

GET/iate/translate

Look up a term in one language and retrieve its official translations in another language via IATE concept IDs. Unlike machine translation, these are institutionally verified terminology equivalents.

Parameters

Example

curl "https://staging.pauhu.eu/iate/translate?term=data%20protection&source=en&target=fi" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "term": "data protection",
  "source": "en",
  "target": "fi",
  "translations": [
    {
      "id": 12345,
      "term": "tietosuoja",
      "definition": "Protection of personal data from unauthorised processing",
      "domain": "1011",
      "reliability": 4,
      "language": "fi",
      "source": "IATE-1234567"
    }
  ],
  "all_languages": {
    "de": [{ "term": "Datenschutz", "reliability": 4 }],
    "fr": [{ "term": "protection des donn\u00e9es", "reliability": 4 }],
    "es": [{ "term": "protecci\u00f3n de datos", "reliability": 4 }],
    "fi": [{ "term": "tietosuoja", "reliability": 4 }],
    "sv": [{ "term": "dataskydd", "reliability": 4 }]
  }
}

The all_languages field returns translations in all available languages for the concept. Use this for multilingual terminology alignment.

GET/iate/export

Bulk export of terminology in industry-standard formats. Compatible with SDL Trados, memoQ, Phrase, and other CAT tools.

Parameters

Example: TBX export

curl "https://staging.pauhu.eu/iate/export?format=tbx&domain=1236&lang=en&limit=500" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -o legal-terminology.tbx

Returns application/x-tbx+xml with a Content-Disposition header for download.

Example: TMX export

curl "https://staging.pauhu.eu/iate/export?format=tmx&domain=1236&lang=en&target=fi&limit=500" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -o legal-en-fi.tmx

Returns application/x-tmx+xml. Each entry contains a source term and its translation, linked by IATE concept IDs. Import directly into your translation management system.

GET/iate/stats

Aggregated statistics about the terminology database.

Example

curl "https://staging.pauhu.eu/iate/stats" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "total": 2456445,
  "languages": 24,
  "byLanguage": [
    { "lang": "en", "count": 245000 },
    { "lang": "fi", "count": 198000 },
    { "lang": "de", "count": 231000 },
    { "lang": "fr", "count": 228000 }
  ],
  "source": "IATE",
  "reliability": "4-star (Very reliable)"
}

GET/iate/quality

Quality dashboard: reliability distribution, language coverage, domain heatmap, and embedding density.

Example

curl "https://staging.pauhu.eu/iate/quality" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response (abbreviated)

{
  "dashboard": "IATE Quality",
  "totals": {
    "all_terms": 2456445,
    "four_star_terms": 2456445,
    "languages": 24
  },
  "reliability_distribution": [
    { "level": "Very reliable", "count": 2456445, "pct": 100 }
  ],
  "language_coverage": [
    { "language": "en", "reliable": 245000, "total": 245000, "pct": 100 },
    { "language": "fi", "reliable": 198000, "total": 198000, "pct": 100 }
  ],
  "top_domains": [
    { "domain": "law", "term_count": 312000 },
    { "domain": "economics", "term_count": 289000 },
    { "domain": "environment", "term_count": 187000 }
  ]
}

POST/iate/tenant/upload

Upload a custom glossary. Your terms take priority over IATE entries in merged lookups. Supports CSV and TBX formats.

Request Body

CSV Format

source_term,target_term,domain,register,notes
contract,sopimus,law,formal,
liability,vastuu,law,formal,

Supported delimiters: comma, semicolon, tab, pipe.

Example

curl -X POST "https://staging.pauhu.eu/iate/tenant/upload" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tenant_id": "acme-corp",
    "name": "ACME Legal Glossary",
    "source_lang": "en",
    "target_lang": "fi",
    "domain": "law",
    "format": "csv",
    "content": "contract,sopimus\nliability,vastuu"
  }'

Response

{
  "glossary_id": "abc123",
  "tenant_id": "acme-corp",
  "name": "ACME Legal Glossary",
  "term_count": 2,
  "inserted": 2,
  "created_at": "2026-03-02T12:00:00Z"
}

GET/iate/tenant/lookup

Merged lookup across your custom glossary and IATE. Your terms take priority.

Parameters

Example

curl "https://staging.pauhu.eu/iate/tenant/lookup?tenant_id=acme-corp&source_lang=en&target_lang=fi&terms=contract,liability" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "tenant_id": "acme-corp",
  "count": 2,
  "results": [
    { "source": "contract", "target": "sopimus", "origin": "tenant", "domain": "law" },
    { "source": "liability", "target": "vastuu", "origin": "tenant", "domain": "law" }
  ]
}

GET/iate/tenant/list

List all glossaries for your organisation.

Example

curl "https://staging.pauhu.eu/iate/tenant/list?tenant_id=acme-corp" \
  -H "Authorization: Bearer YOUR_API_KEY"

DELETE/iate/tenant/glossary

Remove a glossary and all its terms.

Parameters

Example

curl -X DELETE "https://staging.pauhu.eu/iate/tenant/glossary?glossary_id=abc123&tenant_id=acme-corp" \
  -H "Authorization: Bearer YOUR_API_KEY"

Term Structure

Every term returned by the IATE API has the following fields:

Reliability Scale

IATE assigns a reliability score to each term, reflecting the quality and verification status of the terminology entry:

Filter by reliability in your application logic. For official translations and legal documents, prefer terms with reliability 3 or 4.

Supported Languages (24)

Error Codes

Confidence Scores (Semantic Search)

Semantic search results include a score field (0.0–1.0, cosine similarity):

• 0.9+ — Near-exact semantic match
• 0.8–0.9 — Strong relevance
• 0.6–0.8 — Related concept
• Below 0.6 — Weak match, review manually

Data Residency

All terminology data is stored and processed within the EU. No data leaves EU jurisdiction at any point in the pipeline.

Data Source Attribution

Terminology data is sourced from IATE — Interactive Terminology for Europe, the EU’s inter-institutional terminology database managed by the Translation Centre for the Bodies of the European Union. IATE data is used under the applicable EU open data reuse terms.

All Documentation · Full API Reference · Data Catalog