Quickstart

This guide takes you from nothing to a working API call that’s answered by a model running on your own device. Most of the time goes into the first model download.

You need: a Mac with Apple silicon (M1 or later) and an email address or Google account.

1. Create your account

   Go to app.getnodea.com/signup. Sign up with an email and password, or choose continue with Google. If you used email, click the confirmation link we send you, then log in. More about accounts →

2. Create your organization

   After you log in for the first time, you’re asked to set up your organization. Enter a name (for example, your company or team) and click Continue. You become the organization’s first Admin, and you land on the Get started page in the web console.

   Note

   If a teammate already uses Nodea, ask them to invite you instead. You’ll join their organization and skip this step.

3. Add a model

   A new organization has no models yet. Open Models in the console, click Add models, and add one. A small model such as a 1B–3B parameter Llama or Qwen is a good first choice: it downloads quickly and fits on almost any device. More about models →

4. Install the app and sign in

   On the Get started page, click Download for Mac, install Nodea, and sign in with the same account. Your device joins your organization, downloads the model and starts serving it. When the app says This Mac is serving the network, you’re ready. More about the app →

5. Create an API key

   Open API keys in the console and click Create API key. Give it a name, then copy the key. It’s shown only once. More about API keys →

6. Send your first request

   Use the model’s name exactly as it appears on the Models page.

   curl

   export NODEA_API_KEY="<your API key>"
   
   curl https://api.getnodea.com/openai/v1/chat/completions \
     -H "Authorization: Bearer $NODEA_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
       "model": "bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",
       "messages": [{"role": "user", "content": "Hello!"}]
     }'

   Python

   # pip install openai
   import os
   from openai import OpenAI
   
   client = OpenAI(
       base_url="https://api.getnodea.com/openai/v1",
       api_key=os.environ["NODEA_API_KEY"],
   )
   
   completion = client.chat.completions.create(
       model="bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M",
       messages=[{"role": "user", "content": "Hello!"}],
   )
   print(completion.choices[0].message.content)

   Node

   // npm install openai
   import OpenAI from 'openai';
   
   const client = new OpenAI({
     baseURL: 'https://api.getnodea.com/openai/v1',
     apiKey: process.env.NODEA_API_KEY,
   });
   
   const completion = await client.chat.completions.create({
     model: 'bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M',
     messages: [{ role: 'user', content: 'Hello!' }],
   });
   console.log(completion.choices[0].message.content);

   The Get started page ticks off each step on its own, including this one when your first request arrives.

Next steps

• Invite your team: every device that joins adds capacity.
• Stream responses for chat-style interfaces.
• Read the API reference to see which OpenAI parameters are supported.