One content moderation API.
An AI that keeps improving.
Write the integration once. One moderation endpoint backed by our own moderation AI, cross-checked by other models on delicate cases, with pre-filtering, custom rules, batch endpoints and an audit trail ready for the DSA.
Free plan · No credit card · OpenAPI reference
Same request, better AI over time
Our engine is model-agnostic: when a better or cheaper AI model comes out, we plug it in. Your request does not change, and scores come back in one standardized format with thresholds you control.
- ✓Standardized moderation endpoints. Single-text and batch calls (up to 10K items) share the same schema.
- ✓Pre-filter. Obvious spam and forbidden words are blocked before any AI call.
- ✓Dual thresholds. Clear cases are approved or rejected automatically, and the grey zone is reviewed by our team.
- ✓Cross-checked AI. On delicate cases, other AI models arbitrate the decision before it is applied.
# Moderate text — one request, one standardized response
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",
"categories": ["hate", "harassment", "sexual", "violence", "self-harm", "spam"],
"threshold": 0.5
}'
# Response (standardized format)
{
"flagged": false,
"results": [{ "category": "hate", "score": 0.02, "flagged": false }],
"usage": { "latency_ms": 243 }
}Why teams pick OpenModeration
A raw model score is not a moderation system.
| Capability | Raw model API | OpenModeration API |
|---|---|---|
| AI engine | One model (lock-in) | Our own AI, cross-checked by other models; better models plugged in as they come out |
| Response format | Proprietary per vendor | Standardized scores + flagged verdict |
| Pre-filtering | No | Yes, obvious spam is blocked before any AI call |
| Custom rules | DIY | Forbidden words, thresholds, plain-language rules applied by AI |
| Review + audit | DIY | Doubtful cases handled by our team, real-time dashboard, DSA export |
| Docs | Vendor docs | OpenAPI reference → |
Start from your stack
Migrate in under an hour, or moderate social comments with no code.
Migrate from OpenAI
Swap text-moderation / omni-moderation calls for one endpoint with written reasons.
Compare with Mistral Moderation
A single model versus our cross-checked AI, rules and audit trail.
No-code moderation platform
Just connect your pages: we take care of the rest, and you see every decision in real time.
Content moderation API: FAQ
What is a content moderation API?
A content moderation API scores what users post (hate, harassment, sexual, violence, spam, PII…) so your app can approve, flag or reject it automatically. OpenModeration runs its own moderation AI behind one endpoint, cross-checks delicate cases with other AI models and always returns the same response format.
Which moderation API is best for enterprise compliance?
For regulated platforms, look for written reasons, a full audit trail, EU hosting and human review of doubtful cases. OpenModeration covers all four: delicate cases are cross-checked by other AI models, doubtful cases are handled by our team, and every decision is logged for DSA reports.
How much does a moderation API cost?
OpenAI's moderation endpoint is free, Mistral sets its own price for its moderation model, and Azure AI Content Safety bills per 1,000 text records after a free tier of 5,000 records a month. OpenModeration has a free plan up to 1,000 comments analysed a month. The managed cloud Pro plan starts at €99/month for 10,000 comments.
Can I migrate from OpenAI text-moderation-latest?
Yes. Replace openai.moderations.create with one POST /v1/moderation call. You get standardized scores, written reasons and an audit trail, and when we plug in a better AI model, nothing changes in your code.
Can I define custom moderation rules?
Yes, with three tools. Forbidden words block a comment instantly. Category thresholds decide between auto-approve, review and reject. Your own rules, written in plain language, are applied by our AI for your own categories.
Where is the full API reference?
The interactive reference lives at api.openmoderation.com/docs (OpenAPI). This page covers concepts and comparisons. From there, copy the curl example into your stack.
One integration, an AI that keeps improving.
Get an API key, copy the curl example, and moderate your first text in minutes, with an audit trail from day one.
No credit card required · DSA-compliant · GDPR-compliant
Questions? contact@openmoderation.com