fal.ai model inference automation
Fire the workflow when a queued fal job completes (success or error). fal posts the completion event to whatever URL is passed as the queue submit's `webhook_url`. Wire this trigger and paste its URL into the Submit to Queue operation's Webhook URL field.
1 field
Run a model endpoint synchronously and get the result inline.
3 fields
Submit an async request to the fal queue (best for long-running jobs).
4 fields
Poll the status of a queued request.
Fetch the completed result payload of a queued request.
2 fields
Cancel a queued or in-progress request.
Initiate a file upload to fal's CDN; returns a presigned upload URL.
Search and list available model endpoints.
Retrieve current pricing data for models.
Estimate the cost of an intended model operation before running it.
Retrieve granular usage line items for the account.
Time-bucketed metrics: request counts, success/error rates, latency.
List recent requests for a specific model endpoint.
Delete stored request inputs/outputs and cached delivery files.
Wire fal into a coding agent and let it use these operations as tools.
Start building workflows in minutes with our visual builder. No code required.