AI moderation API that detects toxicity, hate, threats, sexual content, self-harm and spam in 26 languages
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
IT
Pricing model
Freemium
Free trial
Pricing
Bring your own key: free. Managed credits: pay per token at list price, 5% fee when purchasing credits. Top-ups start at $5.
Free during the beta: 120 messages per minute per API key, up to 10 active API keys, all categories and custom rules included, usage dashboard included. No credit card required. Paid plans with higher limits coming after beta.
Key features
Routes 119 models from 21 vendors
No markup on tokens at list price
Metered receipt for every request
Join spend to merged pull requests
Drop-in OpenAI SDK compatibility
Prompts not stored
Reads conversation context up to 10 previous messages
Custom rules written in plain language, up to 10 per request
Block specific types of slurs separately: racial, xenophobic, antisemitic, homophobic, transphobic or ableist
Spam and flood detection per user and channel
Usage dashboard showing requests and flags
No message storage - messages checked and discarded immediately
Single HTTP call API with response in milliseconds
Works with Discord, Twitch, Telegram, Minecraft, games, forums and websites
Answers Perspective API requests for easy migration
What makes it different
Single endpoint for all frontier AI models
Exact receipts at list price with no token markup
Spend tied to shipped code
Understands conversation context to distinguish jokes from attacks, unlike keyword filters
Custom rules in plain language for each community's unique policies
No messages stored - privacy by design with GDPR compliance
Drop-in replacement for Perspective API which shuts down December 31, 2026