Perspective
FreeDeprecatedNot yet verified
Google Jigsaw's ML classifier scoring toxicity, insults and threats in text; shutting down Dec 2026.
Example request
curl -s -X POST 'https://commentanalyzer.googleapis.com/v1alpha1/comments:analyze?key=$API_KEY' -H 'Content-Type: application/json' -d '{"comment":{"text":"hello"},"requestedAttributes":{"TOXICITY":{}}}'Free tier, in plain English
Free to use, quota-based per project, but new quota/API key requests stopped being accepted after February 2026.
Alternatives in Moderation
PurgoMalumDetects and censors profanity/obscenity in text, including leetspeak substitutions, keyless.FreeSightengineDetect nudity, violence, weapons, hate symbols, AI-generated images and offensive text in user uploads.FreemiumTisaneFlags hate speech, cyberbullying and other abusive text across 35 languagesFreemium
All 4 Moderation APIs →