Service

Adversarial Fuzzer

FULL PLAN ONLY

Real generational prompt-mutation red-teaming against an HTTP model endpoint you supply. Targets are restricted to public addresses (no probing internal infrastructure); scoring is a documented refusal-phrase heuristic, not a verified jailbreak oracle.

No per-call charge -- unlimited under your subscription

Worked example

This service has no operations beyond health checks right now.

Try it live in your dashboard → See pricing →