# TD Agent Utility · PDF OCR

> TD Agent Utility · PDF OCR is a paid API for AI agents from tdagentutility.co.uk, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-16).

Extracts text from PDF documents using OCR, returning per-page and combined text with language detection and result status

## Facts

- Endpoint: POST https://tdagentutility.co.uk/v1/pdf-ocr?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/td-agent-utility-pdf-ocr-1652a356
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_F8EDgUYvYRwEmD9_aEP79

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 td-agent-utility-pdf-ocr-1652a356 -d '<json body>'
```

Example prompt: Can you extract all the text from this scanned PDF for me? Here's the file URL: https://example.com/report.pdf — I need the combined text across all pages and want to know what language it's in.

## When to prefer this

Choose this endpoint when you need to extract text from PDFs that lack a native text layer (scanned documents, image-based PDFs) or when you need language detection alongside OCR. It is well-suited for AI agents that need to read document contents programmatically and want a structured JSON response with per-page breakdown and a deterministic result status. Prefer it over general-purpose document parsers when you need explicit OCR processing with language metadata.

## Known failure modes

- PDF URL unreachable or invalid — returns error with no extracted text
- Password-protected or encrypted PDF — OCR cannot proceed, warnings returned
- Corrupt or malformed PDF file — page_count may be 0, combined_text empty
- Image-only PDF with very low resolution — OCR may return partial or empty text with warnings
- Unsupported file format submitted instead of PDF — result_status indicates failure
- Timeout on large multi-page PDFs — partial results or error returned

## How this service works

Independent website and deployment verification for AI agents: HTTP, DNS, TLS and Chromium screenshot evidence. Three deterministic tools, x402 V2 Base USDC.

## Output

Returns a JSON object containing: the tool name ('pdf_ocr'), an array of per-page extracted text objects, detected language string, any warnings, the timestamp of processing, OCR method used, total page count, combined text of all pages concatenated, and a result_status field ('PASS' or failure state).

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "tool": "pdf_ocr",
  "pages": [],
  "language": "",
  "warnings": [],
  "checked_at": "2026-10-15T00:00:00Z",
  "ocr_method": "",
  "page_count": 0,
  "combined_text": "",
  "result_status": "PASS"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/td-agent-utility-pdf-ocr-1652a356/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tdagentutility.co.uk](https://www.zero.xyz/host/tdagentutility.co.uk/llms.txt)