> For the complete documentation index, see [llms.txt](https://docs.console.zenlayer.com/welcome/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.console.zenlayer.com/welcome/ai-gateway/ai-gateway-integration.md).

# AI Gateway Integration

AI Gateway can be used as a **centralized intermediary backend** for various AI-powered applications.

Instead of connecting applications directly to individual AI providers, AI Gateway acts as a unified access layer that routes requests, enforces usage policies, and provides observability.

This approach allows organizations to manage AI usage consistently across different tools and environments.

## Prerequisites

Before you begin, make sure you have:

* An active [**AI Gateway instance**](/welcome/ai-gateway/create-an-ai-gateway.md)
* An AI Gateway **API Access key**
* Access to [**API docs**](https://docs.console.zenlayer.com/api-reference/compute/aig)
* (Optional) Postman or another API testing tool

### Authentication

All requests to AI Gateway require authentication using your API key.

Include the API key in the request header:

```
Authorization: Bearer YOUR_API_KEY
```

### Unified API Endpoint

AI Gateway exposes a unified API endpoint for all supported models.

```
POST https://gateway.theturbo.ai/vi
```

## Supported Application Types

AI Gateway can be integrated with a wide range of third-party applications that support custom API endpoints and API keys, including:

### **AI Chat Applications**

End-user chat interfaces for interacting with large language models.

* ChatGPT-web-midjourney-proxy
* NextChat
* Lobe Chat
* ChatGPT Friend (uTools Plugin)
* Chatbox
* Cherry Studio
* ChatWise

### **AI-Powered IDEs**

Development environments with built-in AI capabilities for coding assistance.

* Cursor

### **AI Coding Assistants**

Standalone AI tools designed specifically for code understanding, generation, and refactoring.

* Claude Code
* Continue
* OpenAI Codex
* OpenCode

### **AI Command-Line Tools**

CLI-based tools that enable developers to interact with AI models from the terminal.

* Gemini CLI

### **Internal Tools and Custom Applications**

In-house tools or custom-built applications that require AI capabilities via a unified API backend.

Most of these applications require only minimal configuration—such as setting an API base URL and API key—to route all AI requests through AI Gateway.