Overview

Secure your OpenAI API integration with LockLLM's transparent proxy layer. Route all OpenAI requests through LockLLM for automatic prompt injection scanning without modifying your application logic. Compatible with GPT-5.2, GPT-5, and all OpenAI models including legacy versions.

The integration preserves OpenAI's complete API interface, including streaming responses, function calling, vision capabilities, and all advanced features. Your existing code continues to work exactly as before, with added security protection.

How it Works

Update your OpenAI client's base 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 OpenAI. Malicious prompts are blocked before reaching the model.

The proxy adds 150-250ms overhead and operates transparently. All standard OpenAI features including streaming, JSON mode, function calling, and vision work without modification.

Supported Models

All OpenAI models are supported through the proxy:

GPT-5.2 (latest flagship model)
GPT-5 series
GPT-4 Turbo and GPT-4
GPT-3.5 Turbo
All vision-enabled models
Fine-tuned custom models

Quick Start

Update your OpenAI client configuration to route through the proxy:

const client = new OpenAI({
  baseURL: 'https://api.lockllm.com/v1/proxy/openai',
  apiKey: process.env.OPENAI_API_KEY,
  defaultHeaders: {
    'X-LockLLM-Key': process.env.LOCKLLM_API_KEY
  }
})

// All requests are automatically scanned
const response = await client.chat.completions.create({
  model: 'gpt-5.2',
  messages: [{ role: 'user', content: userInput }]
})

Python Example

from openai import OpenAI

client = OpenAI(
    base_url="https://api.lockllm.com/v1/proxy/openai",
    api_key=os.environ["OPENAI_API_KEY"],
    default_headers={
        "X-LockLLM-Key": os.environ["LOCKLLM_API_KEY"]
    }
)

# Automatic security scanning
response = client.chat.completions.create(
    model="gpt-5.2",
    messages=[{"role": "user", "content": user_input}]
)

Features

Automatic Scanning: All prompts scanned without code changes
Full Model Support: Works with all GPT models and variants
Streaming Support: Compatible with streaming responses
Function Calling: Preserves function/tool calling capabilities
Vision Support: Works with image inputs and GPT-4 Vision
JSON Mode: Compatible with structured output features

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 URL, and start making secure requests. Visit the documentation for complete setup guides, examples, and best practices.