PDF/JPG Google OCR
# OCR Document Processing API A powerful Optical Character Recognition (OCR) API that uses state of the art google algorithms to extract text from various document formats with high accuracy. It returns both the full text (txt like) metadata of all the text present in the document/image as well as the position bounding boxes, detected language etc for more advanced use cases. ## Key Features -…
3 subscribers
2 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
PDF/JPG Google OCR endpoints
| Method | Endpoint | Description |
|---|---|---|
| Optical Character Recognition | ||
| POST |
simple_ocr /api/v1/image_pdf_ocr/ |
Returns text and bounding boxes |
| Freeform OCR | ||
| POST |
freeform_ocr /api/v1/freeform_ocr/ |
Combines OCR with LLM in order to extract text data and parse it |
PDF/JPG Google OCR pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| PRO | $109 / month | 2 / second |
|
| ULTRA | $529 / month | 3 / second |
|
| MEGA | $729 / month | 3 / second |
|
