Developer guides
Keep personal data out of your LLM calls.
Code-first guides for keeping personal data and secrets out of OpenAI, Anthropic, Gemini and LiteLLM requests, with Python and TypeScript examples.
- Developer guide · OpenAIHow to keep personal data out of your OpenAI API callsWhat OpenAI retains from API traffic, and three working ways to mask personal data before the request leaves: your own code, Presidio, or a masking gateway.7 min read
- Developer guide · AnthropicHow to mask personal data before it reaches the Claude APIAnthropic's API retention and residency terms as of October 2026, then three ways to mask personal data in Claude requests: your own code, Presidio, or a gateway.6 min read
- Developer guide · Google GeminiHow to mask personal data in Gemini API requestsHow Google treats Gemini API data on the free and paid tiers, and three ways to mask personal data before a generateContent call: your own code, Presidio, or a gateway.6 min read
- Developer guide · LiteLLMPII masking in a LiteLLM proxy with the Maskflare guardrailInstall the Maskflare guardrail in a LiteLLM proxy, configure pre_call masking and post_call restoring, choose a fail policy, and compare it with LiteLLM's built-in Presidio guardrail.6 min read
- Developer guide · Reversible maskingHow to restore masked personal data in LLM responsesHow reversible masking works end to end: random and deterministic tokens, restoring in streams and JSON, multi-tenant safety, the 30-day token life, and fail-open versus fail-closed.6 min read
See it on your own data
Try Maskflare free.
Bring your hardest prompts.
28-day free trial or 10,000 requests, whichever comes first. Point one app at the gateway or enroll a few laptops,
and watch what gets masked. Or talk to us first.
- SOC 2 Type II: In progress
- ISO 27001: In progress
- EU hosting by default · on-premises available
- Prompts and files never stored
- Never used to train AI models
- GDPR · nDSG · DPA available
- Trust center →