Move from OpenAI or OpenRouter to LLMTR in 5 minutes

This guide is for developer teams moving an existing OpenAI-compatible client to the LLMTR gateway and verifying the first paid top-up flow.

1. Change the base URL

Point your OpenAI-compatible client to the LLMTR gateway.

export OPENAI_BASE_URL="https://llmtr.com/v1"
export OPENAI_API_KEY="llmtr-your_key"

You can keep the same SDK and change only base_url, apiKey, and model.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  baseURL: process.env.OPENAI_BASE_URL
});

const response = await client.chat.completions.create({
  model: "llmtr/turkce-llama-3-8b",
  messages: [{ role: "user", content: "Hello" }]
});

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

2. Create an API key

Open API Keys in the dashboard and store the new key only as a server-side environment variable. The raw key is shown once.

3. Send the first request with a free model

Choose a chat model marked as free in the model catalog, or send the first request from Playground. This verifies that the gateway and usage-record flow work with zero balance.

4. Top up $5

Start a $5 top-up on Billing. The backend preview shows credit added, 6% platform margin, USD charge amount, and approximate TRY estimate before checkout.

Credit added	Platform margin	Amount charged
$5.00	$0.30	$5.30

After payment completes, the balance should update and the receipt link should appear in transaction history.

5. Pre-production check

• Is the API key stored server-side?
• Does the selected model’s data policy fit your team requirements?
• Does the free-model request appear in usage?
• After the $5 top-up, are balance, transaction history, and receipt correct?
• Is the OpenAI/OpenRouter fallback plan and canonical model ID list documented?

References: Node.js SDK, Billing, Security.