# workbot1.oddsys.org High-Page-Count OCR (Deep)

> workbot1.oddsys.org High-Page-Count OCR (Deep) is a paid API for AI agents from workbot1.oddsys.org, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-12).

Performs OCR on scanned PDFs up to 100 pages using Tesseract (English, machine-printed), with a 240-second time budget and graceful partial-result truncation.

## Facts

- Endpoint: POST https://workbot1.oddsys.org/ocr-deep?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/workbot1-oddsys-org-high-page-count-ocr-deep-f5876530
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YWowkOrm1j83QYk6Earbf

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability workbot1-oddsys-org-high-page-count-ocr-deep-f5876530 -d '<json body>'
```

Example prompt: Can you OCR this 80-page scanned PDF for me and give me the clean extracted text? It's a machine-printed English document.

## When to prefer this

Choose this endpoint when you need to OCR more than 25 pages per call (up to 100) and can tolerate a longer processing window (up to 240 seconds). Prefer this over the standard /ocr endpoint for large documents. Use the standard /ocr endpoint for smaller documents where speed matters more. For PDFs with an existing text layer, this endpoint still works efficiently by bypassing OCR.

## Known failure modes

- Time budget exceeded (240s): partial result returned with truncatedReason='time-budget'
- PDF exceeds 100-page limit: request rejected
- Non-English or handwritten documents: poor OCR accuracy
- Corrupted or password-protected PDF: processing failure
- Image quality too low for Tesseract to reliably extract text

## How this service works

High-page-count OCR: scanned PDF into clean text (Tesseract, English, machine-printed documents), up to 100 pages per call — four times the /ocr cap. Runs under a 240s wall-clock budget; slower documents return the completed pages with truncatedReason "time-budget". Text-layer PDFs are extracted the fast way at the same price.

## Output

Returns clean extracted text for each successfully processed page. If the 240-second time budget is exhausted before all pages are done, returns the completed pages alongside a truncatedReason field set to 'time-budget'. Text-layer PDFs bypass OCR and are extracted directly at the same price.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "maxPages": {
   "type": "number",
   "description": "Pages to OCR from the start of the document (1-100, default: all up to 100)."
  },
  "pdfBase64": {
   "type": "string",
   "description": "Base64-encoded PDF file (scanned/image PDFs; machine-printed text, English)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/workbot1-oddsys-org-high-page-count-ocr-deep-f5876530/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from workbot1.oddsys.org](https://www.zero.xyz/host/workbot1.oddsys.org/llms.txt)