# geld machen image-ocr

> geld machen image-ocr is a paid API for AI agents from geld-machen-x402.fly.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts text from an image URL or base64-encoded image using local Tesseract OCR, returning the text, word count, confidence score, image dimensions, and timing metadata.

## Facts

- Endpoint: GET https://geld-machen-x402.fly.dev/product/image-ocr.json
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/geld-machen-image-ocr-a92a3164
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_RslKfDCMtDyK6dS6Hink_

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 geld-machen-image-ocr-a92a3164
```

Example prompt: Can you read the text out of this image for me? Here's the URL: https://example.com/receipt.jpg — I need the full extracted text and how confident the OCR is.

## When to prefer this

Choose this endpoint when you need zero-cost-per-call OCR (no upstream API key charges) at $0.01/call flat, and you want structured JSON output including confidence, dimensions, and timing. It is well-suited for English-first document and receipt OCR where low latency and predictable pricing matter more than state-of-the-art ML accuracy.

## Known failure modes

- Image URL is unreachable or returns non-image content — OCR fails with an error
- Low-contrast or heavily stylized fonts reduce confidence score significantly
- Non-English text without specifying the correct lang parameter yields garbled output
- Very large images may time out or increase timing_ms substantially
- Base64 payload malformed or truncated causes decoding error

## How this service works

JSON micro-tool for agents: GET ?url= (or POST url / image_base64) → local Tesseract OCR (English-first): text, word_count, confidence, width/height, fetched_at, timing_ms. COGS=0 — no upstream OCR API key. Demand-matched OCR class (competitors ~$0.005–$0.012). Brand: geld machen. x402 $0.01 Base USDC.

## Output

Returns a JSON object containing: the extracted text string, word_count (integer), confidence score (0–100 float), image width and height in pixels, fetched_at ISO timestamp, and timing_ms for the full operation.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "HTTPS image URL to OCR"
  },
  "lang": {
   "type": "string",
   "description": "OCR language (default eng)"
  },
  "image_url": {
   "type": "string",
   "description": "Alias for url"
  },
  "image_base64": {
   "type": "string",
   "description": "Base64 image (alt to url)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/geld-machen-image-ocr-a92a3164/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from geld-machen-x402.fly.dev](https://www.zero.xyz/host/geld-machen-x402.fly.dev/llms.txt)