# Agent Web-Access OCR (Tesseract)

> Agent Web-Access OCR (Tesseract) is a paid API for AI agents from web.cyberwarex.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Extracts readable text from an image at a public URL using the Tesseract OCR engine, returning the plain text content of screenshots, scans, receipts, charts, or photos.

## Facts

- Endpoint: GET https://web.cyberwarex.com/ocr
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-web-access-ocr-tesseract-25f403b0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8lvXQiO6-pZ_0OBPnd7H5

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-web-access-ocr-tesseract-25f403b0
```

Example prompt: Can you read the text out of this receipt image for me? Here's the URL: https://example.com/receipt.jpg — use Tesseract OCR on it.

## When to prefer this

Choose this endpoint when you need fast, keyless, cost-efficient OCR of a single image accessible via a public URL, without requiring an LLM or AI-based vision model. Ideal when the image is a screenshot, scan, receipt, or document photo and you need the raw text for downstream processing. Prefer this over LLM vision APIs when budget is tight ($0.005/call), when you want deterministic Tesseract output, or when no API key management is feasible. Not suitable for handwriting recognition requiring deep learning models or for extracting structured data beyond raw text.

## Known failure modes

- Image URL is not publicly accessible or returns a non-200 status — OCR cannot proceed
- Image exceeds ~10MB size limit — request rejected
- Unsupported image format provided — only PNG, JPG, WEBP, TIFF, BMP accepted
- SSRF guard blocks private/internal IP ranges or localhost URLs
- Invalid or unsupported Tesseract language code supplied — may fall back to English or error
- Image contains no readable text or is too low resolution — returns empty or near-empty text string
- Network timeout fetching the remote image — transient failure

## How this service works

Extract text from an image by URL (OCR): PNG/JPG/WEBP/TIFF/BMP of a screenshot, scan, receipt, chart or photo -> the readable text, via the Tesseract engine. Keyless, no LLM. Use it to read text an agent can only see as an image. SSRF-guarded; max ~10MB.

## Output

Returns a JSON object containing the extracted plain text (the 'text' field), the total character count ('chars'), the OCR engine used ('engine', typically 'tesseract'), and the source image URL ('url'). No LLM or AI interpretation is applied — raw Tesseract output only.

## 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",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Public http(s) URL of the image."
      },
      "lang": {
       "type": "string",
       "default": "eng",
       "description": "Tesseract language code (default eng)."
      }
     },
     "additionalProperties": false
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string"
      },
      "text": {
       "type": "string"
      },
      "chars": {
       "type": "integer"
      },
      "engine": {
       "type": "string"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-web-access-ocr-tesseract-25f403b0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from web.cyberwarex.com](https://www.zero.xyz/host/web.cyberwarex.com/llms.txt)