Word-list chat filters break the moment someone types with spaces, or a slur spelled with a , or a perfectly innocent word that happens to contain a banned substring.
You end up in an endless arms race patching your blocklist.
An AI model reads the meaning of a message, so it catches obfuscated toxicity and stops false-flagging harmless phrases.
One server-side call The reply is one word, so it's cheap: with Cortex you're billed on output tokens only, and repeated messages are served from cache for free — so moderating your whole chat costs a fraction of a Robux.
You pay in Robux, no credit card, and the key stays server-side.
Tips Give the model your game's context ("kids' game", "PvP trash-talk is fine") so it matches your tolerance.
Cache identical messages — spammers repeat themselves.
Log verdicts so you can tune the prompt.
Free open beta and open-source kit: https://github.com/cortex-rbx/roblox-ai-kit · demo: https://cortex-rbx.github.io