Event-driven channels

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

2 channels across 1 AsyncAPI spec · Provider profile

Channels

{app_id}/realtime

Bi-directional WebSocket channel for realtime inference. Clients send one input message per generation step and receive zero or more partial or final output frames per step. The default path is `/real

fal Event-Driven APIs
{model_id}/requests/{request_id}/status/stream

Server-Sent Events stream of queue status updates for a single submitted request. The connection remains open and emits one event per state change until the request reaches `COMPLETED`. Enable runner

fal Event-Driven APIs