# AgentRXI OCR

> AgentRXI OCR is a paid API for AI agents from agentrxi.com, paid per call via x402, $0.008/call, status unknown (last checked 2026-10-15).

Extracts text from scanned images or PDFs using Tesseract OCR, supporting English, French, Spanish, and German at 300 dpi

## Facts

- Endpoint: GET https://agentrxi.com/v1/ocr?utm_source=zero.xyz
- Price: $0.008/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrxi-ocr-e9d715d9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_cEyVxTUD9zbiUUzWxhvIs

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 agentrxi-ocr-e9d715d9
```

Example prompt: Can you read the text from this scanned PDF for me? Here's the URL: https://example.com/contract.pdf — please OCR up to 10 pages in English.

## When to prefer this

Choose this endpoint when you need to extract text from scanned images or PDFs in English, French, Spanish, or German, especially when you need per-page control (up to 30 pages), can supply a public URL or base64-encoded file, and want a cost-effective pay-per-page model ($0.008 base + $0.002/extra page). Prefer this over general-purpose vision LLMs when you need structured OCR output rather than semantic understanding, or when processing multi-page scanned documents systematically.

## Known failure modes

- File exceeds 20 MB limit — request rejected
- Unsupported file type or missing file extension — detection may fail
- Language not supported beyond eng/fra/spa/deu — poor recognition quality
- max_pages exceeds 30 — capped or error
- URL not publicly accessible or returns non-200 — fetch failure
- Base64 payload malformed or too large — parse error
- Payment not provided or insufficient — 402 response

## How this service works

Read the text in a scanned image or PDF with Tesseract (English, French, Spanish, German). PDFs with a text layer are read directly; scanned pages are OCR'd at 300 dpi. $0.008 for one page or image, +$0.002 per extra page (max_pages up to 30; default 5 for .pdf URLs). Also callable as GET with the same fields as query parameters.

## Output

Returns the extracted text content from the image or PDF, with text recognized at 300 dpi using Tesseract in the specified language(s). For PDFs with a native text layer, text is read directly; for scanned pages, OCR is applied. Results are structured per page or as a combined text block.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string",
       "description": "https URL of the file (max 20 MB)"
      },
      "lang": {
       "type": "string",
       "description": "eng (default), fra, spa, deu; combine with +"
      },
      "filename": {
       "type": "string",
       "description": "Name with extension, helps detect the type"
      },
      "force_ocr": {
       "type": "boolean",
       "description": "OCR even when the PDF has a text layer"
      },
      "max_pages": {
       "type": "integer",
       "description": "PDF pages to read, 1-30"
      },
      "file_base64": {
       "type": "string",
       "description": "Or the file as base64 / data URI"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrxi-ocr-e9d715d9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrxi.com](https://www.zero.xyz/host/agentrxi.com/llms.txt)