PII Redactor API
Mask emails, phones, IBANs, cards, and EU IDs with reversible tokens before LLM calls.
Detect prompt injection, redact reversible PII placeholders before LLM prompts leave your VPC, catch RAG hallucinations, and scan LLM outputs in sub-millisecond edge compute.
| Endpoint | Capability | Tier | Action |
|---|---|---|---|
POST /v1/pii-redactor |
Mask emails, phones, IBANs, cards, and EU IDs with reversible tokens | Live | Try live → |
POST /v1/prompt-guard |
Detect prompt injections, role hijacks, and encoded jailbreaks | Live | Try live → |
POST /v1/pii-redactor/restore |
Statelessly restore reversible [PII_*] placeholder tokens | Live | Docs |
POST /v1/hallucination-diff |
Catch unsupported numbers, dates, and entities vs RAG sources | All-Access | Docs |
POST /v1/prompt-cache-budgeter |
Estimate tokens, cache prefix keys, and LLM API cost savings | All-Access | Docs |
POST /v1/llm-output-guard |
Scan and sanitize LLM outputs for prompt leaks, beacons, XSS, and policy hits | All-Access | Docs |
Mask emails, phones, IBANs, cards, and EU IDs with reversible tokens before LLM calls.
Catch prompt injections, role hijacks, and encoded jailbreaks in user inputs and RAG chunks.
Fast first filter to catch unsupported numbers, dates, and names in LLM answers vs RAG sources.
Estimate tokens, optimize message order for prompt caching, and calculate LLM API costs.
Scan and sanitize LLM outputs for prompt leakage, Markdown beacons, XSS, and policy violations.