PII Redaction - Portkey (Prisma AIRS AI Gateway) Docs

Fetch the complete documentation index at: /docs/llms.txt
Use this file to discover all available pages before exploring further.
Replace any sensitive data in requests with standard identifiers
Can I customize the redaction patterns?
How does the system handle multiple instances of the same type of PII?
Does this feature impact request latency?
Can I use this feature with any LLM?
Does this feature work on both input and output?
Can I combine multiple PII redaction methods?
Was this page helpful?