Scroll
What is CautionLabs?
CautionLabs is a content moderation API. Send any piece of text to a single REST endpoint and get back a boolean flag for each of twelve harm categories — toxicity, hate speech, harassment, self-harm, adult content, violence, drug content, weapons, PII, spam, minor safety, and profanity — plus a top-level flagged result. It is built for developers who need automated text moderation without training their own models or running moderation infrastructure themselves.
Usage is pay-as-you-go at $0.40 USD per 1,000 requests, with no subscriptions and no rate limits. Most integrations go live in minutes: create an API key, send a POST request to /moderation with your text, and act on the returned category flags in your own application.