Features
A complete moderation platform. Not just an API — a full pipeline from ingestion to action.
Single Integration
One API endpoint that works the same no matter which provider you choose. Consistent results, no extra code.
One connection to all moderation providers
Submit content once, get back a clear pass/fail verdict and category scores — whether you use OpenAI, Azure, or an LLM.
Pre-built content categories
Ready-made categories covering hate, harassment, sexual content, violence, self-harm, spam, misinformation, PII, and more.
Automatic Provider Selection
Tell us your language, content type, and budget. We route each request to the best provider automatically.
Smarter Moderation Decisions
Factor in conversation context, author history, channel type, and your own policies for more accurate decisions.
Bulk Content Review
Submit up to 10,000 items at once for async processing. Get results pushed to your system when ready.
Custom Moderation Policies
Define your own categories using any LLM. Provide examples and let the model classify content your way.
Moderation Dashboard
Full web interface to manage your content moderation operations.
Access Management
Create and manage access keys. Set usage limits per key and configure provider credentials.
Team & Role Management
Easily manage your human moderators, assign roles, and set permissions without relying on your IT department.
Report Management
A centralized queue to process user reports, track resolution status, and ensure no flagged content falls through the cracks.
Activity History
Every moderation request logged with its verdict, provider, response time, and category scores.
Provider Health Monitoring
See the real-time status of all your providers: uptime, response times, and error rates.
Performance Reports
Track moderation volume, flag rates, compare provider performance, and review cost trends.
Connector Management
Connect your social platform accounts with your own credentials.
Rule Configuration
Define forbidden words, set category thresholds, and write your community charter — three simple tools, no code required.
Automated Moderation
Define your moderation rules with three simple tools: forbidden words, category thresholds, and your community charter in plain language.
Context-Aware AI Rules
Combine AI confidence scores with your community guidelines. Move beyond fragile, rigid keyword logic.
Auto-Actions
When a threshold is breached, the Action Engine steps in — hide, delete, flag, notify, or mark as spam.
Human-in-the-Loop
Seamlessly route nuanced or borderline cases to your human moderators for final, informed decisions.
Manual Review Queue
Flagged content goes to a queue for human moderators to approve or reject.
Webhook Notifications
Get real-time alerts for flagged content, batch completion, provider errors, and more.
Full Audit Trail
Every action is logged: which rule triggered, what action was taken, and the outcome.
Platform Integrations
Connect directly to social platforms to automatically ingest and moderate content.
Receive comments and posts. Automatically hide or remove content that breaks your rules.
Moderate Instagram comments and messages. Keep your profile safe from toxic or spammy content.
YouTube
Ingest video comments. Mark as spam or send to your review queue.
Use Your Own Platform Access
Bring your own platform tokens. We never store them in plaintext.
Generic Webhook Receiver
Ingest content from any platform that supports outgoing webhooks.
Generic Webhook Callback
Send moderation results to your own webhook for custom integrations.
Simple, predictable, reliable
Consistent results across every provider. One format, one integration.
Same format for OpenAI, Azure, HuggingFace, Mistral, or any LLM — no extra code to write.
Secure access keys with scoped permissions and usage limits per key.
Interactive API docs auto-generated. Try requests directly from your browser.
# Works the same way with every provider
curl -X POST https://api.openmoderation.com/v1/moderation \
-H "Authorization: Bearer om_key_..." \
-H "Content-Type: application/json" \
-d '{
"input": "Your text to moderate here",
"model": "openai/omni-moderation-latest",
"language": "en"
}'
# Response (same format, every time)
{
"id": "modr_01JXK...",
"model": "openai/omni-moderation-latest",
"results": [{
"category": "hate",
"score": 0.02,
"flagged": false
}],
"flagged": false,
"usage": {
"latency_ms": 243,
"provider": "openai"
}
}Ready to simplify your moderation stack?
Get a complete moderation platform with AI, rules, and a human review interface. No complex integrations required.