✨ Now supporting OpenAI, Anthropic, and more

A privacy gateway for LLMs

Mask PII, route safely, and audit every token before your data reaches OpenAI, Anthropic, or your own models.

Free tier available • Enterprise ready • SOC 2 Type II

Masking & Redaction

Deterministic & ML-assisted detection of PII, PHI, and sensitive data with reversible masking.

Smart Routing

Route requests by content type, sensitivity, region, latency, and cost optimization.

Audit & Compliance

Complete audit trails, detailed logs, and compliance reporting for GDPR, HIPAA, and more.

Trusted by developers at leading companies

How It Works

Privacy-first AI gateway

Your applications stay exactly the same. Just point your OpenAI API calls to Reduxy, and we handle the rest.

Your App

OpenAI API calls

Reduxy Gateway

PII masking, routing, audit

LLM Providers

OpenAI, Anthropic, etc.

Quick Start

OpenAI-compatible API

Drop-in replacement for OpenAI's API. Use our SDK or change one URL to get instant PII protection.

from reduxy import Client

# Initialize client (connects to https://api.reduxy.ai by default)
client = Client(api_key="your_reduxy_api_key")

# Make a chat completion request with automatic PII detection
response = client.chat.completions.create(
    messages=[
        {"role": "user", "content": "Hello! How are you today?"}
    ],
    model="gpt-4o"
)

print(response)

Key Features

OpenAI-style API compatibility
Python SDK for easy integration
Zero-copy masking with vault
Complete audit trails
Features

Enterprise-grade privacy controls

Comprehensive data protection, intelligent routing, and compliance features built for modern AI applications.

PII Detection

Detect emails, SSNs, credit cards, phone numbers, IP addresses, and custom patterns with high accuracy.

Reversible Masking

Vault-based token replacement that allows unmasking for authorized roles and use cases.

Smart Routing

Route requests based on content sensitivity, latency requirements, cost optimization, and regional compliance.

Audit Trails

Complete request/response logging with PII detection metadata and export capabilities for compliance.

Policy Engine

Configurable rules for detection patterns, masking strategies, and routing decisions per tenant.

Multi-Provider

Support for OpenAI, Anthropic, Azure OpenAI, Google Vertex AI, and custom model endpoints.

Ready to secure your AI data?

Start with our free tier or talk to our team about enterprise deployment options.

No credit card required • Free tier available • Enterprise support