fal

The wire to fal.ai's fast, pre-warmed media endpoints: call a model by id, control the queue, get the file back. fal is the fast-media path — latency-optimized image (FLUX, Seedream, SD), audio (TTS, music), and video (Veo, Wan, Kling, Hailuo) endpoints you invoke by id with FAL_KEY.

You own the mechanics: auth, call mode, queue states, webhook signatures, file I/O, per-call cost.

When NOT to use

You want…	Go to
Which model / what to generate / art direction / multi-provider media pipeline	`ai-media`
The same kind of models on Replicate (`replicate.run` / predictions)	`replicate` — images-specifically `replicate-images`
Renting a raw GPU pod you SSH into to train or custom-serve	`runpod`
Deploying your own Python function as an autoscaling endpoint	`modal`
Cheap hosted LLM text/chat completions	`together-fireworks`
The generic provider-agnostic webhook receiver/verifier pattern	`webhooks`

Rule: if you are not invoking a fal endpoint id with FAL_KEY, you are in the wrong skill.