Built a free moderation API after failing to find

{
  "service_type": "platform",
  "base_url": "https://the-profanity-api.com",
  "auth_method": "bearer_token",
  "auth_config": {
    "header": "Authorization",
    "scheme": "Bearer",
    "token_required": true,
    "how_to_get_token": "Sign up and obtain API key from dashboard"
  },
  "endpoints": [
    {
      "name": "check",
      "method": "POST",
      "path": "/api/v1/check",
      "description": "Analyzes text for profanity or harmful content with context awareness and returns a detection report.",
      "auth_required": true,
      "parameters": [
        { "name": "text", "type": "string", "required": true, "description": "The text to analyze" },
        { "name": "context", "type": "string", "required": false, "description": "Context type (e.g., gaming, professional, child_safe). Defaults to general" },
        { "name": "sensitivity", "type": "string", "required": false, "description": "Mode: strict, standard, or lenient. Defaults to standard" }
      ]
    }
  ],
  "pricing_model": {
    "type": "freemium",
    "details": {
      "free_tier": "300 free requests per month",
      "paid_tier": "Usage-based pricing at $0.008 per request (billed per request)**",
      "notes": "Pricing is per request after free tier; no upfront subscription required"
    }
  },
  "rate_limits": {
    "unknown": "No explicit rate limits documented in the provided data"
  },
  "capabilities": [
    "Context-aware content moderation",
    "5-layer detection pipeline",
    "13 intent categories (e.g., hate speech, harassment, self-harm, sexual content, etc.)",
    "12 context types (gaming, professional, child_safe, social, etc.)",
    "Three sensitivity modes (strict, standard, lenient)",
    "Rest API endpoint (POST /check)",
    "Usage-based pricing with free monthly quota",
    "Documentation for getting started and API reference"
  ],
  "raw_analysis": "The Profanity API is a service built by a developer who struggled to find a free moderation tool and decided to create one. It offers context-aware content moderation, meaning it analyzes text not just for profanity but also for intent and context, which is more sophisticated than simple keyword filtering. The platform targets developers who need to moderate user-generated content in applications such as chat rooms, social media, gaming communities, or forums. It is highly relevant for startups or indie developers who need a cost-effective solution, given the free tier and per-request pricing.\n\nKey features include a 5-layer detection pipeline (L0-L4), which likely handles different depths of analysis from simple word matching to contextual intent. The 13 intent categories help classify whether content is harmful (e.g., hate, harassment, sexual) or benign. The 12 context types allow tuning the detection for different environments, e.g., what is acceptable in a gaming context may differ from professional settings. This reduces false positives compared to generic profanity filters.\n\nThe API is simple with a single primary endpoint POST /check, requiring a Bearer token for auth. Documentation covers quick start, API reference, concepts, and pricing. The service appears to be in an early stage (launched via Show HN), but the thorough documentation and structured pipeline suggest a mature implementation.\n\nPricing is usage-based with a free quota (300/month), and then $0.008 per request, which is affordable for many use cases. Rate limits are not specified, but the pricing model implies no hard rate limits beyond the quota. No integrations are mentioned; however, as a REST API it can be integrated into any backend or serverless function.\n\nOverall, the platform is a valuable asset for developers needing a flexible, context-aware content moderation solution without the overhead of building an in-house system or paying high costs of enterprise solutions. Its focus on context and intent distinguishes it from traditional profanity filters. However, its reliability and uptime are unproven as it is a new service. Potential users should evaluate its accuracy on their specific content and consider fallback options."
}

3/3 tests passed

```json
{
  "overall": 82,
  "dimensions": {
    "token_efficiency": 9.0,
    "first_try_success": 8.5,
    "response_parseability": 8.5,
    "error_clarity": 7.5,
    "doc_quality": 9.0,
    "auth_simplicity": 8.5,
    "latency": 9.5,
    "consistency": 8.0
  },
  "pricing_normalized": {
    "free_tier_requests_per_month": 300,
    "paid_per_request_usd": 0.008,
    "no_upfront_subscription": true
  },
  "issues": [
    "No security headers detected on website or robots.txt responses",
    "Auth mechanism not explicitly described in capabilities (likely API key, but unclear from docs snippet)",
    "Docs snapshot only shows getting started, not full API reference quality",
    "No explicit rate limit or error handling documentation visible in preview"
  ],
  "recommendations": [
    "Add security headers (CSP, HSTS) to improve trust for production use",
    "Explicitly document authentication method (API key, OAuth, etc.) in getting started",
    "Provide example error responses and rate limit headers in API docs",
    "Add a public status page for transparency on uptime and incidents"
  ]
}
```