Use any model, from any provider
— with just one API.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.LLM_GATEWAY_API_KEY,
	baseURL: "http://localhost:4002/v1"
});

const response = await client.chat.completions.create({
  model: "gpt-5",
  messages: [
    { role: "user", content: "Hello, how are you?" }
  ]
});

console.log(response.choices[0].message.content);