# x402 AI Tools – Image Content Moderation

> x402 AI Tools – Image Content Moderation 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 explicit, suggestive, violent, drug, hate, and other unsafe content in a JPEG or PNG image at a URL using Amazon Rekognition, returning a safe flag and any flagged labels.

## Facts

- Endpoint: POST https://ai.kagurazaka.dev/v1/moderation?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-content-moderation-c61447a9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9aJqS6ONrTuf1Ed8T9F-U

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-content-moderation-c61447a9 -d '<json body>'
```

Example prompt: Can you check if this image is safe to display on our platform? Here's the URL: https://example.com/upload/photo.jpg — flag anything explicit, violent, or drug-related with at least 70% confidence.

## When to prefer this

Choose this endpoint when you need fast, automated content moderation of individual images hosted at a URL, especially when you need confidence-thresholded detection of a wide range of unsafe content categories (explicit, violent, drug, hate) backed by Amazon Rekognition. Ideal for agent workflows that screen user-generated content before publishing, or that need a simple safe/unsafe boolean with supporting label detail.

## Known failure modes

- Image URL is not publicly accessible or returns a non-200 HTTP response
- Image exceeds 5 MB size limit
- Image is not in JPEG or PNG format
- URL uses a non-HTTPS scheme
- Amazon Rekognition service errors or timeouts
- min_confidence value outside 0-100 range
- Payment not completed, resulting in 402 response

## How this service works

Detects explicit, suggestive, violent, drug, hate and other unsafe content in a JPEG or PNG at a URL with Amazon Rekognition. Returns safe (no label at or above min_confidence) and the labels found.

## Output

Returns a JSON object with a boolean 'safe' field (true if no label meets or exceeds min_confidence) and a 'labels' array listing any detected unsafe content categories with their confidence scores.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "https URL of a JPEG or PNG image (up to 5 MB)"
  },
  "min_confidence": {
   "type": "number",
   "description": "0-100 (default 50)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "safe": true,
  "labels": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-ai-tools-image-content-moderation-c61447a9/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)