Name: nRouter Platform
Price: 5.21 USD

The official nRouter Node.js / TypeScript SDK with automatic metadata parsing, streaming, prompt templates, and multi-turn memory.

The official nRouter Node.js SDK (@nrouter_ai/sdk) provides first-class TypeScript types, automatic x-nr-* header parsing, client-side conversation memory, server-side prompt templating, and full compatibility with both OpenAI and Anthropic models.

Installation

Install the official package from npm:

npm install @nrouter_ai/sdk

Or with pnpm / yarn / bun:

pnpm add @nrouter_ai/sdk
# or
yarn add @nrouter_ai/sdk
# or
bun add @nrouter_ai/sdk

Authentication & Setup

Export your virtual API key in your environment:

export NROUTER_API_KEY="sk-nrouter-your-key-here"

Initialize the client with automatic environment resolution:

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

const client = new nRouter(); // reads NROUTER_API_KEY automatically

async function main() {
  const response = await client.chat.completions.create({
    model: "gpt-5.4-mini",
    messages: [{ role: "user", content: "Hello from TypeScript!" }],
  });

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

  // Inspect auto-captured response metadata
  if (client.lastResponse) {
    console.log(`Cost: $${client.lastResponse.cost}`);
    console.log(`Request ID: ${client.lastResponse.requestId}`);
  }
}

main();

Core Capabilities & Examples

Topic	Example File	Description
Quickstart	`quickstart.ts`	First-run TypeScript starter
Complete Showcase	`node.ts`	Multi-turn memory, prompt templates, conflict resolution
Vercel AI SDK	`vercel_ai.ts`	Integration with Vercel AI SDK (`@ai-sdk/openai`)
E2E Suite	`demo_e2e_suite.js`	Certified end-to-end multi-language test

1. Streaming Responses

Stream tokens in real-time with Server-Sent Events (SSE):

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

const client = new nRouter();

const stream = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  messages: [{ role: "user", content: "Write a short poem about distributed systems." }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content || "";
  process.stdout.write(content);
}
console.log();

2. Multi-Turn Conversation Memory

Use createMemory() to maintain client-side message history without header leaks:

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

const client = new nRouter();
const memory = createMemory({ maxMessages: 10 });

memory.add("user", "My name is Alice and I am building an AI agent.");
const first = await client.nr.chat({
  model: "gpt-5.4-mini",
  messages: memory.messages(),
});
memory.add("assistant", client.nr.text(first));

memory.add("user", "What is my name and what am I building?");
const second = await client.nr.chat({
  model: "gpt-5.4-mini",
  messages: memory.messages(),
});
console.log(client.nr.text(second));

3. Server-Side Prompt Templates

Combine dashboard prompt templates with user variables:

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

const client = new nRouter();

const response = await client.nr.chat(
  promptTemplate("tmpl_onboarding_v1", { user_role: "Tech Lead", plan: "Enterprise" }, {
    model: "gpt-5.4-mini",
    messages: [{ role: "user", content: "Show me my workspace dashboard." }],
  })
);

console.log(client.nr.text(response));

4. Plain OpenAI Client Drop-in

If you prefer standard openai package without additional wrappers:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.NROUTER_API_KEY,
  baseURL: "https://api.nrouter.ai/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  messages: [{ role: "user", content: "Hello!" }],
});

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

TypeScript / Node.js SDK