Quick Start

Make your first request in three steps: create an API key, set it in your environment, and call the chat completions endpoint.

1. Create an API key

Create a virtual API key in the nRouter dashboard. Add credits to your account if needed, then set the key in your terminal:

export NROUTER_API_KEY="sk-nrouter-…"

In PowerShell, set it for the current terminal session with:

$env:NROUTER_API_KEY = "sk-nrouter-…"

Keep the key on your server. Do not include it in browser code or commit it to source control.

2. Send your first request

Choose a language tab. Each example sends the same request to https://api.nrouter.ai/v1/chat/completions. The SDKs and cURL example read the key from NROUTER_API_KEY.

npm install @nrouter_ai/sdk

import { nRouter } from "@nrouter_ai/sdk";

const client = new nRouter(); // reads NROUTER_API_KEY from the environment
const response = await client.chat.completions.create({
  model: "nrouter/auto",
  messages: [{ role: "user", content: "Hello!" }],
});

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

A working call returns a chat completion JSON — and the same request shows up in your dashboard's request logs within seconds, with the model that answered and its exact cost.

nrouter/auto lets nRouter choose the model for each request. To choose a specific model instead, use an ID from your live model catalog.

3. Continue building

• Chat Completions API — request fields, streaming, and tool calls.
• SDK guides — setup for other languages and OpenAI-compatible clients.
• Authentication — key behavior and access control.
• Playground guide — try requests interactively.