msg:raw
safe
input:chat
clean
text:ugc
ok
content:v1
issue
payload:txt
safe
post:body
clean
comment:raw
warn
message:in
safe
event:text
flag
Built for modern app teams
FilterIt gives your product a fast, AI-native moderation API.
Flag profanity and inappropriate categories in text. Start with the free base pipeline, then choose paid thorough analysis for explanations and offending excerpts.
Base moderation
Free
Category decisions within account quotas.
Thorough analysis
More depth
Paid explanations and verified excerpts.
Request visibility
Traceable
Usage metadata, decisions, and request IDs.
Built for your moderation workflow
Manage API keys, monitor usage, investigate request decisions, and test integrations from one dashboard.
Quick start
# Set FILTERIT_BASE_URL to your active deployment.
curl "$FILTERIT_BASE_URL/api/v1/analyze" \
-H "x-api-key: $FILTERIT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Your order arrived today. Thank you!",
"options": {
"mode": "fast",
"detectProfanity": true,
"filterProfanity": false,
"detectTone": true,
"strictness": "balanced"
}
}'Integration pattern
// Run in your server, keeping the API key private.
const { data, requestId } = await response.json();
if (!response.ok) throw new Error("Moderation unavailable: " + requestId);
switch (data.decision) {
case "allow":
return publish(text);
case "review":
return queueForReview({ requestId });
case "block":
return rejectContent({ requestId });
}A review decision needs your policy or a human reviewer. Detection can miss context; validate it against your own use case.
Free base. Optional paid analysis.
Fast mode uses zero credits within account quotas. Use prepaid packages for optional thorough analysis.