# x402 AI Tools – Image Label Detection (Amazon Rekognition)

> x402 AI Tools – Image Label Detection (Amazon 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 objects, scenes, activities, and concepts in a JPEG or PNG image at a URL using Amazon Rekognition, returning labels with confidence scores, categories, parent labels, and instance counts.

## Facts

- Endpoint: POST https://ai.kagurazaka.dev/v1/labels?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-label-detection-amazon-rekognition-0810ba7b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eGSXlrPV7N-j92QxNyPzF

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-label-detection-amazon-rekognition-0810ba7b -d '<json body>'
```

Example prompt: Can you analyze this image at https://example.com/photo.jpg and tell me all the objects, scenes, and activities you can detect — show me at least the top 30 labels with confidence scores above 70?

## When to prefer this

Choose this endpoint when you need to identify and enumerate what objects, scenes, activities, or concepts appear in a JPEG or PNG image accessible via URL, especially when you need confidence scores and hierarchical label categories. It is backed by Amazon Rekognition and is well-suited for content tagging, catalog enrichment, scene understanding, and preliminary image classification. Prefer it over face-detection or text-in-image endpoints when the goal is general object/scene labeling rather than faces or OCR.

## Known failure modes

- Image URL is not publicly accessible or returns a non-200 HTTP response
- Image format is not JPEG or PNG
- Image exceeds 5 MB file size limit
- min_confidence or max_labels outside valid range (0–100 / 1–100)
- URL uses HTTP instead of HTTPS
- Amazon Rekognition service error or throttling
- No labels detected above the specified confidence threshold

## How this service works

Detects objects, scenes, activities and concepts in a JPEG or PNG at a URL with Amazon Rekognition. Returns labels with confidence, their categories and parent labels, and how many instances were located.

## Output

Returns a list of labels detected in the image, each with a confidence score (0–100), one or more category names, parent label hierarchy, and a count of how many distinct instances of that label were located in the image. Up to max_labels results are returned, filtered to those meeting the min_confidence threshold.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "https URL of a JPEG or PNG image (up to 5 MB)"
  },
  "max_labels": {
   "type": "integer",
   "description": "1-100 (default 20)"
  },
  "min_confidence": {
   "type": "number",
   "description": "0-100 (default 60)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-ai-tools-image-label-detection-amazon-rekognition-0810ba7b/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)