gpuos

Integration · SDK

Use the OpenAI Node.js SDK with a self-hosted LLM

Call self-hosted models from TypeScript or JavaScript with the official openai package.

Base URL
https://gpuos.si/v1
API key
gpuos_key_… from the dashboard
Model
a catalog id, e.g. qwen3-32b

Point the client at gpuos

Install
npm install openai
TypeScript
import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://gpuos.si/v1",
  apiKey: process.env.GPUOS_API_KEY,
})

const stream = await client.chat.completions.create({
  model: "qwen3-32b",
  messages: [{ role: "user", content: "Summarize this ticket in one line." }],
  stream: true,
})
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "")

Create the key in API keys in your gpuos dashboard, and deploy the model first in Models. GET /v1/models lists what your workspace can call.

Official documentation: github.com/openai/openai-node

Questions

Does it work in serverless functions and edge runtimes?
Yes. It is a plain HTTPS API; any runtime that can reach https://gpuos.si can call your models.
Should I call gpuos from the browser?
No. Keep the gpuos key on the server, as you would with an OpenAI key, and proxy requests from your backend.

Related

Use OpenAI Node.js SDK with models on your GPUs

Free for one GPU. Connect a machine, deploy a model, then paste the base URL and your key.

Join early accessRead the quickstart