---
title: fal.ai
summary: Fast AI inference for image and video generation, with optimized cold-start times.
---

# fal.ai

Fast AI inference for image and video generation, with optimized cold-start times.

## What it does

Connects an agent to fal.ai. Agents can run a model, submit a generation request, and get its result, covering image and video generation models like Flux, SDXL, and Kling with fast cold-start times.

## Setup

1. Get an API key from your fal.ai account settings.
2. Go to **Settings → Integrations → fal.ai** and paste in the key.
3. Assign the connection to an agent.

## Credentials needed

A fal.ai API key. It's encrypted at rest and never shown again after saving.

## Typical use

An agent that generates an image quickly as part of a larger, time-sensitive task, where a fast turnaround matters more than trying every available model.

## Related

- [Integrations Guide](/en/docs/guides/integrations-guide): the full catalog and security model these connections share
- [Replicate](/en/docs/integrations/replicate): a broader alternative with more community models