Content Moderator
Detect and filter toxic, profane, and inappropriate content in text. Essential for user-generated content platforms, chat applications, and community moderation.
Content Moderator endpoints
| Method | Endpoint | Description |
|---|---|---|
| Moderation | ||
| POST |
censorContent /censor |
Quick censoring without full analysis. Replaces profane words with censor characters. Faster than /moderate for simple use cases. |
| POST |
moderateContent /moderate |
Analyze text for inappropriate content. Returns toxicity score, flagged categories, identified words, and sanitized text. |
| System | ||
| GET |
healthCheck /health |
Check API health status |
Content Moderator pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 1 / second |
|
| PRO | $4.99 / month | 100 / second |
|
| ULTRA | $14.99 / month | — |
|