# x402 AI Tools – Image Text Detection (Rekognition)

> x402 AI Tools – Image Text Detection (Rekognition) is a paid API for AI agents from ai.kagurazaka.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-30).

Detects words and lines of text in a JPEG or PNG image at a URL using Amazon Rekognition, returning up to 100 words with positions.

## Facts

- Endpoint: POST https://ai.kagurazaka.dev/v1/image-text?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-ai-tools-image-text-detection-rekognition-6cee7f0c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0ro-3eTZgejbtrzCPfLvV

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 x402-ai-tools-image-text-detection-rekognition-6cee7f0c -d '<json body>'
```

Example prompt: Can you read all the text visible in this photo — https://example.com/storefront.jpg — I need to know what's written on the signs and labels?

## When to prefer this

Use this endpoint when you need to detect text in natural scene images such as signs, product labels, receipts, or UI screenshots in JPEG or PNG format. Prefer /v1/ocr (Textract) instead when dealing with structured documents, forms, PDFs, or handwritten text that requires layout-aware extraction beyond 100 words.

## Known failure modes

- Image URL is not publicly accessible or returns a non-200 response
- Image exceeds 5 MB size limit
- Unsupported image format (not JPEG or PNG)
- Image contains no detectable text
- More than 100 words present — only top 100 returned
- Low-quality or heavily blurred images reduce detection accuracy

## How this service works

Detects words and lines of text in a photo or screenshot (JPEG or PNG at a URL) with Amazon Rekognition, up to 100 words. Suited to signs, product labels and UI text; for documents use /v1/ocr.

## Output

A list of up to 100 detected text items from the image, each with the word or line content, bounding box coordinates, and a confidence score indicating how certain Amazon Rekognition is about the detection.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "https URL of a JPEG or PNG image (up to 5 MB)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-ai-tools-image-text-detection-rekognition-6cee7f0c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ai.kagurazaka.dev](https://www.zero.xyz/host/ai.kagurazaka.dev/llms.txt)