# Radar Image & PDF OCR

> Radar Image & PDF OCR is a paid API for AI agents from 2-29-135-242.sslip.io, paid per call via x402, $0.02/call, status unknown (last checked 2026-11-21).

Extracts text from images and PDF files using OCR, returning per-line or per-word results with confidence scores and bounding boxes

## Facts

- Endpoint: POST https://2-29-135-242.sslip.io/x402/image-pdf-ocr?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-21
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/radar-image-pdf-ocr-ac126ac0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_6Q1heC3_PpDfl13-iub-c

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 radar-image-pdf-ocr-ac126ac0 -d '<json body>'
```

Example prompt: Can you extract all the text from these two scanned images and that PDF — https://example.com/scan1.jpg and https://example.com/invoice.pdf — using OCR, give me the results line by line in English, and cap it at 10 pages for the PDF?

## When to prefer this

Choose this endpoint when you need programmatic text extraction from images or scanned/digital PDFs, especially when you need bounding box coordinates, per-word or per-line granularity, confidence scores, or multi-language OCR support. It is pay-per-call with no subscription, making it ideal for sporadic or batch document digitization tasks. Prefer it over general vision LLMs when you need structured positional data rather than a prose description.

## Known failure modes

- URL not publicly accessible — returns error if image/PDF link requires authentication or is behind a firewall
- Unsupported file format — only png, jpg, webp, tiff, bmp, gif, and PDF are accepted
- PDF page limit exceeded — cost can grow unexpectedly on large PDFs if maxPagesPerPdf is not set
- Low OCR confidence on very low-resolution or heavily degraded scans
- No results returned and no charge if the file cannot be fetched or parsed
- Language mismatch reduces accuracy if wrong language codes are specified

## How this service works

Fast tools (web read, domain RDAP/DNS/SSL, Federal Register, clinical trials, OSV vulnerabilities, literature, e-mail auth) and data APIs on official/open data (leads, tenders, SEC filings, VAT, geocoding, aviation...). POST JSON, pay per call in USDC on Base via x402. Charged only when results are returned.

## Output

A JSON object with a count and an array of result items — one per image or per PDF page — each containing the extracted text organized as lines or words, along with confidence scores and bounding box coordinates for each text element.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "example": [
    "https://www.gutenberg.org/cache/epub/11/pg11.cover.medium.jpg",
    "https://www.gutenberg.org/cache/epub/84/pg84.cover.medium.jpg",
    "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
   ],
   "description": "Direct links to images (png, jpg, webp, tiff, bmp, gif) or PDF files, scanned or digital. One result row is produced per image and per PDF page. Links must be public and point straight to the file."
  },
  "forceOcr": {
   "type": "boolean",
   "example": false,
   "description": "By default, PDF pages that already contain a text layer are read from it (fast, exact). Turn this on to run OCR on every page anyway, for example when the text layer is wrong."
  },
  "languages": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "example": [
    "eng"
   ],
   "description": "Languages of the text in your images. Pick one, or several for mixed text (a little slower). Used only when a page has to be read by OCR."
  },
  "outputMode": {
   "enum": [
    "lines",
    "words"
   ],
   "type": "string",
   "example": "lines",
   "description": "lines = every text line with its confidence and bounding box. words = every single word with confidence and bounding box (bigger output)."
  },
  "maxPagesPerPdf": {
   "type": "integer",
   "example": 20,
   "description": "Read at most this many pages from each PDF (from the first page). You pay per page, so this caps the cost of big documents."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 1,
  "items": [
   {
    "...": "one result object"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/radar-image-pdf-ocr-ac126ac0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 2-29-135-242.sslip.io](https://www.zero.xyz/host/2-29-135-242.sslip.io/llms.txt)
