fal 1.74.0

fal is an easy-to-use Serverless Python Framework

fal

fal is a serverless Python runtime that lets you run and scale code in the cloud with no infra management.

With fal, you can build pipelines, serve ML models and scale them up to many users. You scale down to 0 when you don't use any resources.

For full product and platform documentation, see fal.ai/docs.

Quickstart

Install the package and authenticate:

pip install fal
fal auth login

Create a minimal app:

import fal


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

Run it on fal for testing:

fal run hello_world.py::MyApp

Deploy it to a persistent endpoint:

fal deploy hello_world.py::MyApp

Next steps

If you want to go deeper, start with:

• Quick start
• Deploy to production
• Serverless documentation

Install from source

From the repository root:

pip install -e 'projects/fal[dev]'

Contributing

Running tests

Use the smallest relevant scope first:

pytest -n auto -v projects/fal/tests/unit

Pre-commit

Run the repository hooks before opening or finishing work:

pre-commit run --all-files

Commit format

Please follow the Conventional Commits specification for commit messages.