OCR API
**OCR API** extracts text from images using the industry-standard Tesseract OCR engine, the same open-source OCR library used by Google, Amazon, and thousands of developers worldwide. ### Important Note on First-Request Latency On first use of each language, the API downloads Tesseract language data (~5MB per language). This initial request takes **10–30 seconds**. All subsequent requests use…
5 subscribers
3 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
OCR API endpoints
| Method | Endpoint | Description |
|---|---|---|
| OCR | ||
| POST |
/extract /extract |
Perform OCR on an image provided as URL or base64 string. Returns extracted text, confidence score, and word count. Word-level bounding boxes available on ULTRA+ plans. |
| POST |
/batch /batch |
Process multiple images in one request. Batch size: BASIC=1, PRO=3, ULTRA=10, MEGA=20. |
| GET |
/languages /languages |
Returns the list of OCR languages available on your current plan. |
OCR API pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 5 / minute |
|
| PRO | $9 / month | 30 / minute |
|
| ULTRA | $29 / month | 100 / minute |
|
| MEGA Recommended | $99 / month | 300 / minute |
|
