Content Moderation API
# Content Moderation API (Toxic-BERT) AI-powered content moderation using the `unitary/toxic-bert` model, fine-tuned on the Jigsaw Toxic Comment Classification Challenge dataset. ### ⚠️ Known Limitations (Read Before Using) 1. **6 Fixed Categories**: Returns ALWAYS the same 6 toxicity categories: `toxic`, `severe_toxic`, `obscene`, `threat`, `insult`, `identity_hate`. All categories are returned…
2/10 popularity
14799 ms avg latency
27% success rate
1 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Content Moderation API endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Moderate Content /rapidapi/moderation |
🛡️ Content Moderation API Automatically detect toxic content, hate speech, insults, threats, and obscene language using the Toxic-BERT AI model (trained on Jigsaw dataset). 📍… |
Content Moderation API pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 10 / minute |
|
| PRO Recommended | $9.99 / month | 120 / minute |
|
| ULTRA | $29.99 / month | 300 / minute |
|
| MEGA | $79.99 / month | 600 / minute |
|
