> ## Documentation Index
> Fetch the complete documentation index at: https://docs.palico.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Gateway

> AI Gateway is a service that let's you use with different LLM models from a single endpoint

Some notable AI Gateway are:

* <a target="_blank" href="https://portkey.ai/">
    Portkey
  </a>
* <a target="_blank" href="https://cloud.google.com/vertex-ai">
    GCP Vertex
  </a>
* <a target="_blank" href="https://aws.amazon.com/bedrock/">
    AWS Bedrock
  </a>

For this guide, we'll use Portkey as our AI Gateway.

## Setup Portkey

You can setup Portkey <a target="_blank" href="https://github.com/Portkey-AI/gateway">locally</a>, or use the hosted version at <a target="_blank" href="https://portkey.ai">portkey.ai</a>. Once you have Portkey setup, continue with the following steps.

### Add Portkey to your project

```bash theme={null}
npm install portkey
```

## Using Portkey to call OpenAI models

```typescript theme={null}
const handler: Chat = async ({ userMessage }) => {
  const { userMessage } = content;
  // Create Portkey client
  const portkey = new Portkey({
    Authorization: "Bearer sk-xxxxx",
    provider: "openai",
  });
  // Call the API
  const response = await portkey.chat.completions.create({
    messages: [{ role: "user", content: userMessage }],
    model: "gpt-3.5-turbo",
  });
  return {
    message: response.choices[0].message.content,
  };
};
```

## Using Portkey to call any LLM model with App Config

To be able to easily swap different LLM models in your application, you can use [App Config](/guides/feature_flag) along with Portkey. This will allow you to use any LLM model without changing your code and just updating the AppConfig.

```typescript {9, 13, 18} theme={null}
import { Portkey } from "portkey";

interface AppConfig {
  model: string;
  provider: string;
}

const handler: Chat = async ({ userMessage, appConfig }) => {
  const { model, provider } = appConfig;
  // highlight-start
  const portkey = new Portkey({
    Authorization: "Bearer sk-xxxxx",
    provider: provider,
    // ...additional authorization params
  });
  const response = await portkey.chat.completions.create({
    messages: [{ role: "user", content: userMessage }],
    model: model,
  });
  // highlight-end
  return {
    message: response.choices[0].message.content,
  };
};
```

Using AppConfig to swap LLM models allows you to easily run experiments with different variations of your applications locally, or run A/B tests in production without changing your code.