# Content Moderation API

> Content Moderation API is a paid API for AI agents from content-moderation-api-hhy1.onrender.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Checks text for profanity and explicit terms using a wordlist with leetspeak/obfuscation detection, returning a flag, matched terms with positions, match count, and a redacted version.

## Facts

- Endpoint: POST https://content-moderation-api-hhy1.onrender.com/moderate
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/content-moderation-api-b37855ae
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-PD_agW_W7GJ_7zd0Rk4K

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 content-moderation-api-b37855ae -d '<json body>'
```

Example prompt: Can you check this user comment for profanity or explicit terms and give me a redacted version if anything bad is found: 'You are an asshole and I hate you'?

## When to prefer this

Choose this endpoint when you need a fast, wordlist-based profanity check with leetspeak/obfuscation detection that also returns exact match positions and a ready-to-display redacted version. It is well-suited for real-time moderation of user-generated text in chat, forums, or profile fields where speed matters more than nuanced semantic understanding. Prefer a more advanced ML-based moderation service if you need context-aware detection of hate speech, sentiment, or implicit toxicity beyond explicit keyword matching.

## Known failure modes

- Text exceeding 50,000 characters may be rejected or truncated
- Highly novel obfuscations not in the wordlist may go undetected (false negatives)
- Legitimate words that resemble profanity may be incorrectly flagged (false positives)
- Non-English profanity may not be detected if not in the wordlist
- Empty or whitespace-only input may return unexpected results
- Service hosted on Render free tier may experience cold-start latency or downtime

## How this service works

Check text for profanity/explicit terms (wordlist-based, with basic leetspeak/obfuscation detection); returns a flag, matched terms, and a redacted version.

## Output

Returns a JSON object with: a boolean 'flagged' field indicating whether any profanity was detected, a 'matches' array listing each detected term with its start and end character positions, a 'match_count' integer, and a 'redacted_text' string where matched terms are replaced with asterisks.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to check for profanity/explicit terms. Max 50,000 characters."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "flagged": true,
  "matches": [
   {
    "end": 17,
    "term": "asshole",
    "start": 10
   }
  ],
  "match_count": 1,
  "redacted_text": "You are a *******."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/content-moderation-api-b37855ae/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from content-moderation-api-hhy1.onrender.com](https://www.zero.xyz/host/content-moderation-api-hhy1.onrender.com/llms.txt)