Skip to main content
New to RAXE? Start with the Quickstart and learn how detection works.

Installation

Basic Usage

basic.py

How It Works

  1. User sends request through RaxeOpenAI
  2. RAXE scans the prompt before calling OpenAI
  3. If threat detected → RaxeBlockedError raised
  4. If safe → Request forwarded to OpenAI
  5. Response returned normally

Benefits

Save Money

Threats blocked before API call - no wasted tokens

Zero Code Changes

Just change the import statement

Full Compatibility

All OpenAI features work normally

Automatic Protection

Every request scanned automatically

Error Handling

error_handling.py

Configuration

config.py

Streaming Support

streaming.py

All Messages Scanned

The wrapper scans all messages in the conversation:
multi_turn.py

Migration Guide

migration.py

Async Support

async.py

What’s Next

Production Checklist

Deploy RAXE safely to production

Async SDK

High-throughput scanning with async support