One content moderation API.
Every provider.
Stop rewriting integrations. One moderation endpoint routes to OpenAI, Mistral, Azure, Llama Guard and more — with pre-filtering, custom rules, batch endpoints and a DSA-ready audit trail.
Free self-hosted · No credit card · OpenAPI reference
Same request, any provider
Switch from openai/omni-moderation-latest to
mistral/mistral-moderation-2411 with one field.
Scores come back in one standardized format with thresholds you control.
- ✓Standardized moderation endpoints — single-text, batch (up to 10K items), same schema everywhere.
- ✓Pre-filter — block obvious spam and forbidden words before any billable provider call.
- ✓Dual thresholds — auto-approve, grey zone → human review, auto-reject.
- ✓BYOK + fallback — your keys, automatic routing if a provider is slow.
# Moderate text with any provider — same request, same 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",
"model": "openai/omni-moderation-latest",
"categories": ["hate", "harassment", "sexual", "violence", "self-harm", "spam"],
"threshold": 0.5
}'
# Response (standardized across providers)
{
"flagged": false,
"results": [{ "category": "hate", "score": 0.02, "flagged": false }],
"usage": { "provider": "openai", "latency_ms": 243 }
}Why teams pick a unified API
A raw provider score is not a moderation system.
| Capability | Single-provider API | OpenModeration API |
|---|---|---|
| Providers | 1 (lock-in) | 10 — OpenAI, Mistral, Azure, Llama Guard, Perspective, Hive… |
| Response format | Proprietary per vendor | Standardized scores + flagged verdict |
| Pre-filtering | No — every call billed | Yes — save 10-30% on provider costs |
| Custom rules | DIY | Forbidden words, thresholds, LLM charter |
| Review + audit | DIY | Dashboard, team roles, DSA export |
| Docs | Vendor docs | OpenAPI reference → |
Start from your stack
Migrate in under an hour, or moderate social comments with no code.
Content moderation API — FAQ
What is a content moderation API?
A content moderation API scores user content (hate, harassment, sexual, violence, spam, PII…) so your app can auto-approve, flag or reject it. OpenModeration unifies 10 providers behind one endpoint with a standardized response format.
Which moderation API is best for enterprise compliance?
For regulated platforms, pick a multi-provider setup: OpenAI for English accuracy, Mistral or Azure for EU languages and compliance, plus a full audit trail. OpenModeration routes per request and logs every decision for DSA reports.
How much does a moderation API cost?
OpenAI charges ~$0.10 per 1K short texts; Mistral €0.24/1K requests; Azure $0.50-$1.00/1K records. OpenModeration is free to self-host — managed cloud starts at €99/month for 10K requests, and pre-filtering cuts 10-30% of billable calls.
Can I migrate from OpenAI text-moderation-latest?
Yes. Replace openai.moderations.create with one POST /v1/moderation call using model openai/omni-moderation-latest. Keep your OpenAI key (BYOK), then add fallback providers without rewriting code.
Can I define custom moderation rules?
Yes. Three tools: forbidden words (instant block), category thresholds (auto-approve / review / reject), and a plain-language community charter enforced by LLMs for custom categories.
Where is the full API reference?
The interactive reference lives at api.openmoderation.com/docs (OpenAPI). Start here for concepts and comparisons, then copy the curl example into your stack.
One integration. Every moderation provider.
Get an API key, copy the curl example, and moderate your first text in minutes — with audit trails from day one.
No credit card required
Questions? contact@openmoderation.com