# Agent Tools UK OCR

> Agent Tools UK OCR is a paid API for AI agents from agent-tools-production-e6aa.up.railway.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-13).

Extracts text from images, screenshots, scans, and scanned PDFs using OCR, or returns embedded text from native PDFs directly

## Facts

- Endpoint: POST https://agent-tools-production-e6aa.up.railway.app/v1/ocr?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-tools-uk-ocr-a5f30ce5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_iFSbqy5viyWLY4BxRJZvw

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 agent-tools-uk-ocr-a5f30ce5 -d '<json body>'
```

Example prompt: Can you read all the text from this scanned receipt image for me? Here's the URL: https://example.com/receipt.jpg — it's in English.

## When to prefer this

Choose this endpoint when you need to extract text from image-based documents such as photos, screenshots, scanned letters, receipts, or forms where the text is not machine-readable. It is also optimal for scanned PDFs where embedded text is absent. Prefer this over native PDF text extractors when the source document is image-only. The endpoint automatically detects native PDF text and returns it directly (faster and exact), so it works well even when you are unsure whether a PDF is scanned or native.

## Known failure modes

- 400 Bad Request — neither `url` nor `base64` was provided, or both were provided simultaneously, or the file format is unsupported
- 413 Payload Too Large — the file exceeds the 20 MB size limit or the PDF exceeds 20 pages
- URL unreachable — the provided URL is not publicly accessible or returns an error
- Poor OCR quality — heavily degraded, blurry, or low-resolution images may produce garbled or incomplete text output
- Unsupported language code — an invalid Tesseract language code will cause a processing error

## How this service works

Read the text from a photo, screenshot, scan or scanned PDF (OCR). If the PDF already has real text, that is returned instead (faster and exact). Use when text is only available as an image: receipts, letters, forms, signs. Send {url} or {base64}, optional lang (default eng, e.g. eng+fra). Max 20 MB, 20 pages. Returns {text, method, pages}. Errors: 400 bad input, 413 too large.

## Output

Returns a JSON object with: `text` (the full extracted text string), `method` (either 'ocr' if Tesseract was used on an image or scanned PDF, or 'native' if the PDF already contained real embedded text), and `pages` (the number of pages processed).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public URL of the file. Provide url OR base64."
  },
  "lang": {
   "type": "string",
   "description": "Tesseract language code(s), e.g. eng or eng+fra"
  },
  "base64": {
   "type": "string",
   "description": "File contents, base64-encoded (max 20 MB). Provide url OR base64."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-tools-uk-ocr-a5f30ce5/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-tools-production-e6aa.up.railway.app](https://www.zero.xyz/host/agent-tools-production-e6aa.up.railway.app/llms.txt)