capabilities.work

What you can do with fal

Every task in plain language. Pick one, and we can help you get access.

19 things you can do

fal

fal (Features and Labels, Inc.) is a generative media platform providing the world's fastest API for running image, video, audio, and multimodal generative AI models. Through a unified queue-based REST API at https://queue.fal.run, plus realtime WebSocket and SSE streaming surfaces, fal serves 1,000+ production models — including FLUX, Veo 3, Kling, Wan, Seedream, Nano Banana, and Stable Diffusion

Works with AI assistants 8 multi-step recipes

Recipes: multi-step jobs

Queue Inference
Run a generative model through the fal queue and return its output.Serverless App Discovery
Enumerate Serverless apps and load detail for the first match.Serverless App Files Inspection
Verify a Serverless app, then browse its persistent /data files.Set And Verify Serverless Secret
Write a Serverless secret and confirm its name is registered.Submit And Conditionally Cancel
Submit a job and cancel it if it is still running, otherwise return its result.Upload Asset Then Run Inference
Register an input asset on the fal CDN and feed its URL into a model.Upload, Run Image-To-Image With Webhook
Register a reference image and queue an image-to-image job with a callback.Webhook-Backed Submission
Queue a job with a completion webhook and confirm acceptance.

Artificial Intelligence Management

Queue a generation job on a hosted modelCancel a queued or running inference jobCheck the status of a queued inference jobFetch the output of a completed inference job

Configuration & Secrets Management

Create or replace a serverless secretList secret names available to serverless apps

Model Inference

Stream a model's output as it generates

Other things you can do

Start an asset upload to the CDNList the organization's serverless appsGet a serverless app's details and scalingList files on the persistent data volume