Overview

Protect your Azure OpenAI Service deployments with LockLLM's transparent proxy layer. Route all Azure OpenAI requests through LockLLM for automatic prompt injection scanning without modifying your application logic. Compatible with all GPT models hosted on Microsoft Azure infrastructure, providing enterprise-grade security for Azure AI deployments.

The integration maintains Azure OpenAI's complete API interface, including all deployment-specific features, private networking, and compliance requirements. Your existing code works exactly as before, with added security protection layer.

How it Works

Update your Azure OpenAI client's endpoint URL to route through the LockLLM proxy. All requests are intercepted, prompts are scanned for security threats in real-time, and safe requests are forwarded to your Azure deployment. Malicious prompts are blocked before reaching the model.

The proxy adds 150-250ms overhead and operates transparently. All standard Azure OpenAI features including streaming, function calling, content filtering, and private endpoints work without modification.

Supported Models

All Azure OpenAI Service models are supported through the proxy:

GPT-5.2 and GPT-5 series
GPT-4 Turbo and GPT-4
GPT-3.5 Turbo
All vision-enabled models
Custom fine-tuned deployments
Regional deployment variants

Quick Start

Update your Azure OpenAI client configuration to route through the proxy:

const client = new AzureOpenAI({
  endpoint: 'https://api.lockllm.com/v1/proxy/azure/your-resource',
  apiKey: process.env.AZURE_OPENAI_API_KEY,
  apiVersion: '2024-02-15',
  deployment: 'your-deployment',
  defaultHeaders: {
    'X-LockLLM-Key': process.env.LOCKLLM_API_KEY
  }
})

// All requests are automatically scanned
const response = await client.chat.completions.create({
  messages: [{ role: 'user', content: userInput }]
})

Python Example

from openai import AzureOpenAI

client = AzureOpenAI(
    azure_endpoint="https://api.lockllm.com/v1/proxy/azure/your-resource",
    api_key=os.environ["AZURE_OPENAI_API_KEY"],
    api_version="2024-02-15",
    default_headers={
        "X-LockLLM-Key": os.environ["LOCKLLM_API_KEY"]
    }
)

# Automatic security scanning
response = client.chat.completions.create(
    model="your-deployment",
    messages=[{"role": "user", "content": user_input}]
)

Features

Automatic Scanning: All prompts scanned without code changes
Enterprise Security: Compatible with Azure security requirements
Deployment Support: Works with all Azure deployment configurations
Content Filtering: Preserves Azure's built-in content filters
Private Endpoints: Compatible with Azure private networking
Compliance Ready: Maintains Azure compliance certifications

Configuration

Configure security behavior using request headers:

X-LockLLM-Key: Your LockLLM API key (required)

Getting Started

Generate API keys in the dashboard, update your client configuration with the proxy endpoint, and start making secure requests. Visit the documentation for complete setup guides, examples, and Azure-specific best practices.