Quick Start

Quick Start

From zero to your first AI call in about two minutes.

1. Get a free API key

Register at api.aipowergrid.io/register — OAuth (Google / GitHub / Discord), wallet connect, or just a username. Your key is shown once; store it somewhere safe.

export AIPG_API_KEY="your-key-here"

2. Check what’s online

The Grid runs on community workers, so the live model list changes as workers connect and disconnect. Always start here:

curl https://api.aipowergrid.io/v1/models

An empty data array means no streaming workers are connected right now — chat requests will return 503 until one comes online. Image generation runs on a separate worker pool and keeps working either way.

3. Make your first call

The API is OpenAI-compatible — any OpenAI client works. Pick a model from the step-2 list:

curl -N https://api.aipowergrid.io/v1/chat/completions \
  -H "Authorization: Bearer $AIPG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grid/llama-3.3-70b-versatile",
    "messages": [{"role": "user", "content": "Explain AI Power Grid in one sentence."}],
    "stream": true
  }'

Python (pip install openai):

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.aipowergrid.io/v1",
    api_key="your-key",
)
 
stream = client.chat.completions.create(
    model="grid/llama-3.3-70b-versatile",   # use a model from /v1/models
    messages=[{"role": "user", "content": "Hello, Grid!"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

JavaScript (npm install openai):

import OpenAI from 'openai';
 
const client = new OpenAI({
  baseURL: 'https://api.aipowergrid.io/v1',
  apiKey: 'your-key',
});
 
const stream = await client.chat.completions.create({
  model: 'grid/llama-3.3-70b-versatile',
  messages: [{ role: 'user', content: 'Hello, Grid!' }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

4. Generate an image

curl https://api.aipowergrid.io/v1/images/generations \
  -H "Authorization: Bearer $AIPG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a lighthouse in a thunderstorm, cinematic"}'

Returns a URL to the finished image (typically 10–60s depending on worker load).

Where next

IntroductionGenerate Images & Chat