Fal.ai Integration

Fast image/video generation inference for AI product features.

Fal.ai specializes in low-latency inference for diffusion and generative media models. If your product needs image or video generation alongside the kit's text LLM features, Fal's API is a common pairing, called from a background worker like any other long-running job.

Setup in 4 steps

1Add FAL_KEY to your .env
2Install the fal-client Python package
3Wrap generation calls in a Celery task — most generation jobs take several seconds
4Use the kit's existing job-status endpoint pattern to let clients poll for results

What's included

Sub-second to low-second latency for many diffusion model endpoints
Pairs naturally with the kit's existing async job/status pattern
Good option when a product needs both text (via the LLM layer) and image/video generation
Usage can be metered the same way as LLM tokens for billing purposes

Code example

example.py

# app/tasks/fal_task.py
import fal_client

@celery.task
def generate_image_fal(job_id: str, prompt: str):
    result = fal_client.subscribe(
        "fal-ai/flux/dev",
        arguments={"prompt": prompt},
    )
    update_job_result(job_id, output=result["images"][0]["url"])

Full documentation: /docs/llm-providers

Fal.ai integration pre-wired and ready.

FastAPI AI Kit ships with Fal.ai configured out of the box. No manual setup required.

Ready to ship your AI backend this weekend?

Join developers who skipped weeks of boilerplate and went straight to building.

Read the docs

No subscriptions · One-time payment · Lifetime updates