One endpoint. Structured JSON. Detects toxicity, spam, and harmful content in real-time with multi-model AI fallback.
1,000 calls/month free · No credit card required
Everything you need to ship content moderation. Nothing you don't.
Gemini → Perspective → HuggingFace → pattern rules. If one model is unavailable, the chain continues. No silent failures.
Identical content is cached. Repeat checks return in <5ms. Novel content typically resolves in 100–300ms end-to-end.
Blocked words, regex patterns, length limits, URL and phone detection — per project, evaluated before AI calls to short-circuit early.
$ curl -X POST \
https://moderateapi.com/api/v1/register \
-H "Content-Type: application/json" \
-d '{"email":"you@co.com",
"password":"••••••••"}'
# → { "user_id": 42, ... }
# Check email to verify, then log in$ curl -X POST \
https://moderateapi.com/api/v1/moderate \
-H "X-API-Key: mk_..." \
-H "Content-Type: application/json" \
-d '{"text":"Hello world"}'{
"safe": true,
"confidence": 0.95,
"suggested_action": "approve",
"issues": [],
"service_used": "gemini",
"response_time_ms": 87
}Click a file to run it through the moderation pipeline.
# mock responses · sign up for live API access with your own content
No seats, no per-user fees. Just API calls.
Need more? Email us for volume pricing.