Skip to main content
This guide walks you through building and deploying a Hello World app on fal Serverless. By the end, you will have a working app running on cloud infrastructure with a persistent URL, a Playground for browser-based testing, and client SDK code you can copy into any project. The entire process takes about two minutes. The workflow you will learn here is the same one you will use for every fal app, from simple utilities to production AI models. You write a Python class, test it with fal run, deploy it with fal deploy, and call it with the fal client SDK. Once you are comfortable with this loop, the Deploy Your First Image Generator tutorial shows how to apply it to a real Stable Diffusion XL model.

​
Before You Start

You’ll need:
  • Python - we recommend 3.11
  • A fal account (sign up is free)

​
Step 1: Install the CLI

pip install fal

​
Step 2: Authenticate

Get your API key from the fal dashboard and authenticate: 
fal auth login
This opens your browser to authenticate with fal. Once complete, your credentials are saved locally.

​
Step 3: Create Your First App

Create a file called hello_world.py with this simple app: 
import fal

class MyApp(fal.App):
    @fal.endpoint("/")
    def run(self) -> dict:
        print("Processing Hello World request...")
        return {"message": "Hello, World!"}

​
Step 4: Test Your App Locally

Run your app to test it: 
fal run hello_world.py::MyApp
This starts your app and prints two URLs: a direct HTTP endpoint and a web playground. By default, fal run uses public auth mode so you can test without an API key.
Use --auth private if you want to require API key authentication during development. See Authentication Modes for details.
Once you see Application startup complete, test it with curl using the URL from the output: 
curl $FAL_RUN_URL -H 'Content-Type: application/json' -d '{}'

{"message": "Hello, World!"}
You can also use the playground URL to test through a browser interface.

​
Step 5: Deploy Your App

Once you are satisfied, deploy to create a persistent URL: 
fal deploy hello_world.py::MyApp
This deploys your app to fal’s infrastructure with runners managed automatically based on demand. The output includes your app’s endpoint ID and persistent URL.

​
Step 6: Call Your Deployed App

Once deployed, you can call your app from any Python or JavaScript application using the fal client SDK. 
pip install fal-client

import fal_client

result = fal_client.subscribe("your-username/hello-world", arguments={})
print(result)
# {"message": "Hello, World!"}
Replace your-username/hello-world with the endpoint ID shown after deploying. See Calling Your Endpoints for all calling patterns including async queue, streaming, real-time, and webhooks.

​
Next Steps

From here, the Deploy Your First Image Generator tutorial applies the same workflow to a real Stable Diffusion XL model. To understand how apps are structured and how runners start up and shut down, read App Lifecycle. For all the ways to call your deployed app, including async queue, streaming, real-time, and webhooks, see Calling Your Endpoints.