Image to Text API
Pricing
from $1.60 / 1,000 image reads
Image to Text API
Image to text: OCR with line and word positions and confidence scores. $0.002 per image OCR result; start extra; usage included; failed results uncharged.
Image to Text API
Pricing
from $1.60 / 1,000 image reads
Image to text: OCR with line and word positions and confidence scores. $0.002 per image OCR result; start extra; usage included; failed results uncharged.
Image URLs (PNG, JPEG, WebP, TIFF, BMP, GIF), http or https, 1–1,000 per run, up to 20 MB, 50 megapixels and 32,767 pixels on a side each. Each URL becomes one record. Processing is sequential, with 540 seconds of work inside the default 600-second run at 1,024 MB; unfinished URLs receive timeout records.
Explicit Tesseract language/variant codes; 1–3 per image, 123 available codes covering 100+ languages. Unknown codes fail validation, never silently English.
[ "eng"]text returns plain text only; lines adds each line with its confidence and box; words adds each word with its confidence and box. paragraphs adds each paragraph with confidence and a box.
Drop words read with a confidence below this (0–100), and lines left with no word; 0 keeps everything.
Tesseract layout: auto (PSM 3), single_block (6), single_line (7), single_word (8), sparse_text (11), raw_line (13). No automatic detection of selected language.
Use a fixed 128 grayscale threshold before OCR; off preserves the existing grayscale and resize path.
Add boxNorm with x,y,w,h in 0–1 image coordinates beside each pixel box.
Add escaped Markdown text, preserving source lines and paragraphs without inventing headings.