In this guide, we’ll cover:

✅ How to set up OpenRouter with Node.js
✅ Example code to call a free model
✅ How to manage your API key
✅ Limitations & best practices
✅ How tokens work in free vs. paid models

1️⃣ Get Your OpenRouter API Key

1. Go to OpenRouter.

2. Sign up with your email or GitHub/Google account.

3. Head to the API Keys section.

4. Copy your API key and save it in a .env file.

Example .env file:

OPENAI_API_KEY=your-openrouter-api-key

⚠️ Even though it’s free, keep your key secret — don’t commit it to GitHub.

2️⃣ Set Up Your Node.js Project

Install dependencies:

npm install dotenv node-fetch

Project structure:

📂 gen-ai
 ┣ 📂 src
 ┃ ┗ index.js
 ┣ .env
 ┣ package.json

3️⃣ Example Code for a Free Model

Here’s a working index.js example:

import dotenv from "dotenv"; // Loads environment variables from .env file
import fetch from "node-fetch"; // Imports fetch for making HTTP requests

dotenv.config(); // Initializes dotenv to use environment variables

async function main() {
  // Sends a POST request to OpenRouter's chat completions endpoint
  const response = await fetch(
    "https://openrouter.ai/api/v1/chat/completions",
    {
      method: "POST", // HTTP method
      headers: {
        Authorization: `Bearer ${process.env.OpenAI_API_KEY}`, // Authenticates using API key from .env
        "Content-Type": "application/json", // Specifies JSON payload
        // "HTTP-Referer": "<YOUR_SITE_URL>", // Optional: site URL for OpenRouter rankings
        // "X-Title": "<YOUR_SITE_NAME>", // Optional: site name for OpenRouter rankings
      },
      body: JSON.stringify({
        model: "deepseek/deepseek-chat-v3.1:free", // Specifies the model to use
        messages: [
          //   { role: "system", content: "You are a helpful assistant." }, // Optional system prompt
          //   { role: "user", content: "What is the capital of France?" }, // Example user prompt
        ],
      }),
    }
  );

  // Parses the JSON response from the API
  const completion = await response.json();
  // Logs the assistant's reply to the console
  console.log(completion.choices[0].message.content);
}

main(); // Runs the main function

Run the project:

node src/index.js

Output:

The capital of France is Paris.

4️⃣ Limitations & Best Practices

• Free models may have restrictions → slower response times, limited requests per day.

• Always check rate limits on OpenRouter before scaling.

• Prefer paid models (like GPT-4, Claude, Gemini) for production apps.

• Structure your code → keep API calls in separate utility files for maintainability.

5️⃣ Understanding Tokens (Free vs. Paid Models)

OpenAI and OpenRouter bill based on tokens, not words.

👉 A token is a chunk of text (roughly 4 characters in English).
Example: ChatGPT is awesome! → 4 tokens (Chat, GPT, is, awesome!).

6️⃣ How to Calculate Tokens in Node.js

Install the token encoder:

npm install js-tiktoken

Example usage:

import { encoding_for_model } from "js-tiktoken";

const encoder = encoding_for_model("gpt-4");

const text = "ChatGPT is amazing!";
const tokens = encoder.encode(text);

console.log("Token count:", tokens.length);

Output:

Token count: 4

👉 Always track token usage in paid models to estimate cost and avoid surprises.