Toxicity Filter–Contextual Toxicity Judge
This API evaluates contextual toxicity by analyzing the deeper semantic meaning behind user text. Unlike simple keyword-based filters, this model detects implied hostility, hidden aggression, sarcasm, veiled insults, and harmful subtext. Ideal for: AI moderation systems Chatbot safety filters Community platforms Corporate communication monitoring AI agents needing safe conversation handling…
1 subscribers
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.
Toxicity Filter–Contextual Toxicity Judge endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
/ / |
This endpoint determines whether text contains toxic elements |
Toxicity Filter–Contextual Toxicity Judge pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $9 / month | — |
|
| ULTRA | $19 / month | — |
|
