Node.js

Norlen is OpenAI-compatible, so the official openai SDK in Node.js works by pointing baseURL at Norlen.

npm install openai

Configuration

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.norlen.io/v1",
  apiKey: process.env.NORLEN_API_KEY,
});

Chat

const resp = await client.chat.completions.create({
  model: "qwen3.6-35b",
  messages: [{ role: "user", content: "Hello, Norlen!" }],
});
console.log(resp.choices[0].message.content);

Streaming

const stream = await client.chat.completions.create({
  model: "qwen3.6-35b",
  messages: [{ role: "user", content: "Count to five." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Embeddings

const resp = await client.embeddings.create({
  model: "qwen3-embedding",
  input: ["first text", "second text"],
});
console.log(resp.data[0].embedding.slice(0, 5));

Images

Image generation uses a different base URL (app.norlen.io/api/v1) and does not go through the SDK — use fetch:

const r = await fetch("https://app.norlen.io/api/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.NORLEN_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ model: "qwen-image", prompt: "A lighthouse at dawn", size: "1024x1024" }),
});
const { data } = await r.json();
const buffer = Buffer.from(data[0].b64_json, "base64");
await import("node:fs/promises").then((fs) => fs.writeFile("imagem.png", buffer));