Connect NUFI to your code

Want to call NUFI from a script, an internal tool, or an integration? Create an API key in the console and use it with anything that speaks the OpenAI API format. This guide gets you from zero to a first working request.

What you'll need

Access to the console at console.nufi.me (you sign in at the app first — the console reads the same login).
A way to run curl, or an OpenAI-compatible SDK in your language.

Steps

Sign in at the app, then open the console from the avatar menu (bottom-left) → Console, or go straight to console.nufi.me.

The developer console

Open the API keys tab, click Generate, give the key a name (e.g. laptop), and copy it — the full key is shown once.

Note the base URL and a model name: the endpoint is https://api.nufi.me/v1 and a model is e.g. qwen2.5-7b.

Make your first request. From the command line:

curl https://api.nufi.me/v1/chat/completions \
  -H "Authorization: Bearer sk-nufi-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen2.5-7b",
    "messages": [{"role": "user", "content": "hello"}]
  }'

Or from Python with the OpenAI SDK:

from openai import OpenAI

client = OpenAI(base_url="https://api.nufi.me/v1", api_key="sk-nufi-…")
print(client.chat.completions.create(
    model="qwen2.5-7b",
    messages=[{"role": "user", "content": "hello"}],
).choices[0].message.content)

Watch usage and budget in the console's Usage tab — every call is logged with model, time, and tokens spent.

What you get

Programmatic access to NUFI from your own code, with the same OpenAI-compatible parameters you already know (stream, tools, temperature, max_tokens).

Make it better

Keep keys secret — use environment variables, never commit them to git.
One key per app so you can revoke it cleanly when you retire the app.
Rotate keys periodically, and set tight per-key budgets for unattended scripts.

API keys

Full reference: generate, use, revoke, budgets, and best practices.

Overview

How NUFI fits together.