# Agent Tools OCR (URL-based)

> Agent Tools OCR (URL-based) is a paid API for AI agents from agent-tools.jbarkules.workers.dev, paid per call via x402, $0.0038/call, status unknown (last checked 2026-10-30).

Extracts all text from an image at a public URL (PNG/JPEG, max 10 MB), preserving line breaks.

## Facts

- Endpoint: GET https://agent-tools.jbarkules.workers.dev/v1/ocr?utm_source=zero.xyz
- Price: $0.0038/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-tools-ocr-url-based-e6f4b51e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vEYiJPQFBs3YI3iyjWsvy

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-ocr-url-based-e6f4b51e
```

Example prompt: Can you read all the text from this receipt image? https://example.com/receipt.jpg — I need every line exactly as it appears.

## When to prefer this

Use this endpoint when you have a public URL pointing to a PNG or JPEG image and need to extract its text without uploading bytes. Prefer this over the upload-bytes OCR sibling when the image is already hosted publicly. Choose this over document-parsing endpoints when dealing with raw image files rather than PDFs or multi-page documents.

## Known failure modes

- Image URL is not publicly accessible or returns 4xx/5xx — no text returned
- Image exceeds 10 MB size limit — request rejected
- Unsupported image format (not PNG or JPEG) — parsing fails
- Image contains no readable text (blank, pure graphic) — empty string returned
- Network timeout fetching the image URL

## How this service works

OCR: read all text from a screenshot, photo, receipt, sign, scanned page or chart image at a URL (PNG/JPEG, max 10 MB). Keeps line breaks.

## Output

Returns the full text content found in the image, with original line breaks preserved, as a plain text string. Suitable for downstream parsing, search indexing, or data entry.

## 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",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Public image URL"
      }
     }
    }
   },
   "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/agent-tools-ocr-url-based-e6f4b51e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-tools.jbarkules.workers.dev](https://www.zero.xyz/host/agent-tools.jbarkules.workers.dev/llms.txt)