# Strict Content Moderation Tool

**Use case:** 

Apply a low threshold to catch borderline unsafe comments and return detailed category scores as JSON for strict review.

## Input

```json
{
  "texts": [
    "I cannot stand dealing with clueless people like this all day."
  ],
  "threshold": 0.3
}
```

## Output

```json
{
  "text": {
    "label": "Text",
    "format": "string"
  },
  "safe": {
    "label": "Safe",
    "format": "boolean"
  },
  "overallToxicity": {
    "label": "Overall toxicity",
    "format": "number"
  },
  "flagged": {
    "label": "Flagged",
    "format": "array"
  },
  "categories": {
    "label": "Category scores",
    "format": "object"
  },
  "reason": {
    "label": "Reason",
    "format": "string"
  },
  "observedAt": {
    "label": "Scored at",
    "format": "string"
  },
  "error": {
    "label": "Error",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [Tool: Content Moderation & Toxicity Scorer](https://apify.com/scrapers_lat/content-moderation-tool) with a specific input configuration. Visit the [Actor detail page](https://apify.com/scrapers_lat/content-moderation-tool) to learn more, explore other use cases, and run it yourself.