Skip to main content
POST
OCR extraction

Phase

Phase 3 — Ships only if $1K+ MRR. Requires Tesseract infrastructure.

Request

object
required
The PDF to OCR. Same source options as other endpoints.
string
default:"all"
Pages to process. OCR is computationally expensive — scope to needed pages.
string
default:"eng"
OCR language. Supports Tesseract language codes: eng, fra, deu, spa, por, ita, jpn, kor, chi_sim, chi_tra, hin, ara.
string
default:"text"
text, markdown, or structured. Same as text extraction.
integer
default:"300"
Resolution for page-to-image conversion before OCR. Higher = more accurate, slower. Range: 150-600.

Response

Same shape as text extraction, with additional OCR-specific fields:
number
Average OCR confidence score across all pages. Range: 0.0 to 1.0. Below 0.7 indicates poor scan quality.

Example