Better content moderation,
for modern companies
Moderation API is an AI content moderation API and review platform for text, images, video and audio, with custom rules and support for 120+ languages.
Everything you need for trust & safety at scale: Detection, Review, User Management, and Compliance, in one platform.
Protecting 1000+ product teams
Your rules,
enforced by AI.
Powerful detection from day one.
Then fine-tune with your own rules and data.
Write your guidelines.
Describe what you want moderated the way you'd tell a new hire. Our models apply your rules with explanation and confidence — no prompt engineering required.
Hey, you seem really cool. Want to continue this on WhatsApp? My number is +1 555...
Use 20+ battle-tested models.
Drop in production-ready detection trained on billions of labels.
Moderate any data type.
Build custom logic.
Build if/then rules that combine user signals, content scores, and trust levels into instant actions.
120+ languages, one API.
Conversation intelligence.
Conversation history is considered with every decision - so the same sentence isn't treated the same way in every situation.
Content moderation is hard to get right - which is why Moderation API is great. It covers almost anything out of the box, but also gives you the tools to fit your specific workflow.
You've added AI moderation... Now what?
AI moderation is the easy part. We've built all the hard parts.
Hey, I can get you those for way cheaper, just DM me on Instagram.
Live in minutes.
One endpoint, every language, every stack.
Compliance, handled.
Plug-and-play user reporting.
Give your users a complete reporting flow - hosted report pages, email notifications, and audit trails. DSA compliant out of the box.
What the best product teams says about Moderation API
It’s a big improvement from OpenAI. Brilliant platform for moderating across all our media types - text, audio, and images!
We're using Moderation API and super happy with it. So much so that we're doubling our quota. It's become a core part of how we keep our platform safe as we scale.
We needed a moderation solution that could handle 50+ languages and scale with our global market. Moderation API delivered on both.
Moderation API has been a huge help with helping to keep corporate information within our secure environment. Moderation API has made being aware of sensitive conversations within our Slack application easy.
The moderation API plugin has been game-changing for my company. We no longer have to spend hours a week moderating comments on our articles. Chris has been a pleasure to work with and he’s helped us every step of the way. 100% recommend!
As a CPAAS platform, we deal with messages at massive scale. Moderation API handles our peak traffic without breaking a sweat, and the custom models let us fine-tune for specific context.
It’s a big improvement from OpenAI. Brilliant platform for moderating across all our media types - text, audio, and images!
Moderation API has been a huge help with helping to keep corporate information within our secure environment. Moderation API has made being aware of sensitive conversations within our Slack application easy.
We're using Moderation API and super happy with it. So much so that we're doubling our quota. It's become a core part of how we keep our platform safe as we scale.
The moderation API plugin has been game-changing for my company. We no longer have to spend hours a week moderating comments on our articles. Chris has been a pleasure to work with and he’s helped us every step of the way. 100% recommend!
We needed a moderation solution that could handle 50+ languages and scale with our global market. Moderation API delivered on both.
As a CPAAS platform, we deal with messages at massive scale. Moderation API handles our peak traffic without breaking a sweat, and the custom models let us fine-tune for specific context.
Built for platforms
that can't afford to be slow or wrong.
Frequently asked questions
The questions we are asked most often, answered.
What is Moderation API?
Moderation API is an AI content moderation API and review platform for text, images, video and audio, with custom rules and support for 120+ languages. It is a product in its own right, not a moderation endpoint bundled with a general-purpose LLM API: alongside the models you get a review queue, author moderation and a rules engine.
What content types can it moderate?
Text, images, video and audio. Quota is counted in units, where one unit is one message: text costs 1 unit, audio 2 and images 3. Video starts at 3 and rises with length and the number of models you enable. You can mix media types on the same plan.
Which languages are supported?
More than 120, with no separate configuration per language. The same models and your own rules apply whatever language the content arrives in.
How much does it cost, and is there a free tier?
There is a free Hobby plan with 100 messages a month and no credit card. Paid plans start at $79 a month for Basic, which includes a larger monthly quota and pay-as-you-go beyond it. See pricing for the current plans and rates.
How fast is the API?
Responses are returned in real time on the same request, so the API can sit in front of a live chat rather than run after the fact. TODO: Rasmus to confirm — there is no published latency figure (for example a median or 95th-percentile response time in milliseconds) anywhere on the site or in the docs, so none is quoted here.
Where is data hosted, and is it GDPR compliant?
The EU is the default region. Moderation API is GDPR and CCPA compliant and DSA compliant out of the box, and a signed data processing agreement is available — see the DPA. SOC 2 Type II is in progress. Enterprise plans can choose a custom region.
How long is content retained?
Moderated content stays available in your review queues and dashboard for one month on Basic and three months on Growth. Enterprise plans set their own retention window.
Can I set my own rules?
Yes. You can write guidelines in plain language and have the AI enforce them, build conditions in the rules engine, add allow and block wordlists, and train custom models on your own examples when the ready-made models do not catch what you care about.
Is there a human review queue?
Yes. Flagged content lands in a review queue where your own moderators can act on it, with author moderation for repeat offenders, a Casebook for grouped cases, and digest notifications. Reviews can also be handled from Slack.
How do I integrate it?
Call one HTTPS endpoint from any stack, or use the official Node.js and Python SDKs. Webhooks push results back to you, and there are ready-made integrations for Discord, Slack, WordPress, Discourse, Shopify, Zendesk and Zapier. The documentation has quickstarts.
