HALOWERKDokumente extrahieren
ocr
Read a picture, a scan or a screenshot: full text in reading order, typed blocks with their box on the page, tables as a matrix plus markdown, and every QR code and barcode with its decoded content.
POST https://doc.halowerk.com/ocrEingaben
| Feld | Typ | Pflicht | Beschreibung |
|---|---|---|---|
| image_base64 | string | Nein | The picture or PDF as base64. Use this or "url", not both. |
| url | string | Nein | Public http or https URL of the picture or PDF. Use this or "image_base64", not both. |
| mime | string | Nein | Media type of the input. Checked against the actual bytes; a mismatch is refused rather than worked around. |
| languages | array | Nein | Languages to read, default deu plus eng. Installed models: deu, eng. |
| want | array | Nein | Which parts of the answer to compute. The price does not change with it; asking for less is simply faster. |
| pages | Siehe Schema | Nein | Optional page range for PDF input, for example "1-5" or "2,4,7". At most 50 pages per call. Not allowed for a single image. |
Vollständiges Eingabeschema anzeigen
{
"type": "object",
"properties": {
"image_base64": {
"type": "string",
"description": "The picture or PDF as base64. Use this or \"url\", not both."
},
"url": {
"type": "string",
"format": "uri",
"description": "Public http or https URL of the picture or PDF. Use this or \"image_base64\", not both."
},
"mime": {
"type": "string",
"enum": [
"image/png",
"image/jpeg",
"image/webp",
"application/pdf"
],
"description": "Media type of the input. Checked against the actual bytes; a mismatch is refused rather than worked around."
},
"languages": {
"type": "array",
"items": {
"type": "string",
"enum": [
"deu",
"eng"
]
},
"default": [
"deu",
"eng"
],
"description": "Languages to read, default deu plus eng. Installed models: deu, eng."
},
"want": {
"type": "array",
"items": {
"type": "string",
"enum": [
"text",
"tables",
"codes",
"layout"
]
},
"default": [
"text",
"tables",
"codes",
"layout"
],
"description": "Which parts of the answer to compute. The price does not change with it; asking for less is simply faster."
},
"pages": {
"description": "Optional page range for PDF input, for example \"1-5\" or \"2,4,7\". At most 50 pages per call. Not allowed for a single image.",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "integer",
"minimum": 1
}
}
]
}
}
}Veröffentlichtes Eingabebeispiel
{
"languages": [
"deu",
"eng"
],
"want": [
"text",
"tables",
"codes",
"layout"
]
}Ergebnis & Dokumentation
Maschinenlesbare Dokumentation dieses Hubs
Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.
Weitere Endpunkte dieses Hubs
- Dokumente extrahieren0,02 USDC
document
POSThttps://doc.halowerk.com/documentTurn one PDF into structured JSON: header fields, tables as rows and columns, key value pairs and per page full text, each field with its page, position and confidence.