Documents

Get a document

get/v1/documents/{id}

Request

  • Base URL: https://api.talonic.com
  • URL: https://api.talonic.com/v1/documents/{id}
  • Auth: HTTP bearer

Path parameters

idstring uuid required
Example:a1b2c3d4-e5f6-7890-abcd-ef1234567890

Resource UUID.

Response

Document details.

idstring uuid required
filenamestring required
pagesinteger
size_bytesinteger
mime_typestring
type_detectedstring nullable
language_detectedstring nullable
text_source'ocr' | 'local_parser' | 'vision_fallback'

Which converter produced the document's markdown. Present only when recorded. vision_fallback = OCR failed and Claude transcribed the file.

text_degradedboolean

True when the markdown is NOT a verbatim transcription of the file (a summary, translation or truncated read after an OCR failure). Quotes and provenance from such text are never reported as verified. Present only when recorded.

text_degraded_reasonsstring[]

Why the verbatim guard flagged the text. Present only when text_degraded is true.

status'pending' | 'processing' | 'completed' | 'error' required
errorstring

Human-readable failure message. Present ONLY when status is error; omitted otherwise.

field_countinteger

Number of fields captured from the document. 0 until extraction completes.

original_pathstring nullable

Folder path of the file at its source, when ingested from a connector.

batch_idstring

Caller grouping key supplied at ingest (batch_id). Present ONLY when the document was tagged; omitted otherwise (backwards-compatible).

metadataobject

Caller flat metadata supplied at ingest. Present ONLY when the document was tagged; omitted otherwise (backwards-compatible).

extraction_countinteger
latest_extraction_idstring uuid nullable
created_atstring date-time required

Example response

{
  "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "filename": "contract-2024.pdf",
  "pages": 12,
  "size_bytes": 1048576,
  "mime_type": "application/pdf",
  "type_detected": "Service Contract",
  "language_detected": "en",
  "text_source": "ocr",
  "text_degraded_reasons": [
    "summary_phrasing",
    "language_mismatch:en!=de"
  ],
  "status": "completed",
  "error": "Extraction failed",
  "source": {
    "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "type": "manual"
  },
  "field_count": 42,
  "triage": {
    "sensitivity": "internal",
    "department": "finance",
    "jurisdiction": "DE",
    "pii_detected": true,
    "pii_categories": [
      "name",
      "email"
    ],
    "confidentiality_marking": "Vertraulich"
  },
  "original_path": "/invoices/2026/04",
  "batch_id": "2026-07-14-run-042",
  "metadata": {
    "customer": "bridgeway",
    "source": "sftp"
  },
  "extraction_count": 1,
  "latest_extraction_id": "d1a2b3c4-5678-9abc-def0-1234567890ab",
  "processing_log": [
    {
      "step": "ocr",
      "status": "completed",
      "duration_ms": 3120
    }
  ],
  "created_at": "2026-04-25T14:30:00.000Z"
}

Changes

No recorded changes to this operation across all 1 revision of this API.