Quickstart Guide: Make Your First Parallel AI API Call

Prerequisites

All you need is a Parallel AI account and a terminal (or any HTTP client). No SDK installation is required to follow this guide — though we’ll show you a Python example too.

Create your Parallel AI account

Head to https://web.parallellabs.app/signup and sign up using your Google account or email address.Once you’re in, you’ll land on your company dashboard. If this is your first time, a default company workspace is created for you automatically.

Generate a Company API Key

In your dashboard, navigate to the Integrations page from the left sidebar.
Find the API Keys section and click Generate New Key.
Give your key a descriptive name (e.g. my-first-key).
Copy the key immediately — it won’t be shown again after you close the dialog.

Store your API key somewhere safe, such as a password manager or secrets vault. If you lose it, you’ll need to generate a new one.

You’ll pass this key in the X-API-Key header on every request. See the Authentication guide for all supported header formats.

List your agents

With your key in hand, make your first live API call. This request retrieves all agents in your company:

curl -X GET "https://api.parallellabs.app/api/v0/agents" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json"

If your account is brand new, you’ll see an empty list — that’s expected:

{
  "items": [],
  "total": 0,
  "pages": 1,
  "hasNext": false
}

A 200 OK response confirms that your key is valid and your connection to the API is working correctly.

Replace YOUR_API_KEY with the key you copied in the previous step. Keep this pattern in mind — every request to the Parallel AI API uses the same X-API-Key header.

Create your first chat completion

Parallel AI exposes an OpenAI-compatible /chat/completions endpoint. Use it to run a completion against any supported model:

cURL
Python (openai library)

curl -X POST "https://api.parallellabs.app/api/v0/chat/completions" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Because Parallel AI’s chat completions endpoint is OpenAI-compatible, you can use the official openai Python package with no changes other than the base_url:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.parallellabs.app/api/v0",
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Install the library first if you haven’t already:

pip install openai

The API returns a standard OpenAI-format response object with the model’s reply inside choices[0].message.content.

You can swap "gpt-4o-mini" for any model supported on the platform. Refer to the API Reference for the full list of available models.

You're ready — explore what's next

You’ve authenticated, listed your agents, and run a live chat completion. Here’s where to go from here:

Build AI Agents

Create multi-channel agents for web, email, SMS, and voice — and connect them to your Knowledge Base.

Full API Reference

Explore every endpoint available in the Parallel AI REST API with request and response schemas.

Get Started

Core Features

Integrations

Platform

Quickstart Guide: Make Your First Parallel AI API Call

Prerequisites

Build AI Agents

Full API Reference

​Prerequisites

Build AI Agents

Full API Reference

Prerequisites