Fal had 23 outages in the last 2 years totaling 150h 47m of downtime — averaging 0.9 incidents per month.
There were 23 Fal outages since September 3, 2025 totaling 150h 47m of downtime. Each is summarised below — incident details, duration, and resolution information.
Type: Incident Duration: 30 minutes Affected Components: Model API Sep 4, 14:21:00 GMT+0 - Identified - Identified the issue Sep 4, 14:28:00 GMT+0 - Resolved - This incident has been resolved. Sep 4, 13:58:00 GMT+0 - Investigating - We are not processing requests calling directly to [fal.run](http://fal.run) domain.
We are currently investigating this incident.
This incident has been resolved.
Type: Incident Duration: 6 hours and 11 minutes Affected Components: Serverless API, Serverless Dashboard Jul 20, 18:30:00 GMT+0 - Identified - Serverless request metrics are appearing slower than usual. Jul 21, 00:41:03 GMT+0 - Resolved - This incident has been resolved.
We are currently investigating this incident.
We are continuing to work on a fix for this incident.
We implemented a fix and are currently monitoring the result.
This incident has been resolved.
We are currently investigating this incident.
This incident has been resolved.
We are currently investigating this incident.
This incident has been resolved.
Recent Serverless metrics data may be temporarily incomplete.
Data from the last couple of hours is available, we are working to backfill missing data.
We are currently investigating this incident.
We are continuing to work on a fix for this incident.
This incident has been resolved.
Type: Incident Duration: 40 minutes Affected Components: , Official Models, API → May 4, 11:30:00 GMT+0 - Investigating - We are currently investigating this incident. May 4, 12:10:29 GMT+0 - Resolved - This incident has been resolved.
We are currently investigating this incident.
This incident has been resolved.
Type: Incident Duration: 4 hours and 14 minutes Affected Components: Website, API, Official Models Apr 8, 05:36:09 GMT+0 - Investigating - We are currently investigating this incident. Apr 8, 09:49:24 GMT+0 - Monitoring - We implemented a fix and are currently monitoring the result. Apr 8, 09:50:38 GMT+0 - Resolved - This incident has been resolved. We are deeply sorry for the inconvenience caused and will follow up with a detailed RCA.
Type: Incident Duration: 3 hours and 14 minutes Affected Components: fal-ai/nano-banana-pro, Website, fal-ai/bytedance, fal-ai/flux, API, Official Models, fal-ai/nano-banana, fal-ai/kling-video Mar 6, 14:25:05 GMT+0 - Investigating - We are currently investigating this incident. Mar 6, 17:39:19 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 35 minutes Affected Components: fal-ai/flux, API, Official Models Feb 23, 21:13:08 GMT+0 - Investigating - We are currently investigating this incident. Feb 23, 21:48:20 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 1 hour and 39 minutes Affected Components: Website Feb 20, 06:33:57 GMT+0 - Investigating - We are currently investigating this incident. Feb 20, 08:13:14 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 8 minutes Affected Components: API, Official Models Jan 22, 01:37:20 GMT+0 - Investigating - We are currently investigating this incident. Jan 22, 01:45:03 GMT+0 - Resolved - This incident has been resolved, we are recovering Jan 22, 01:44:45 GMT+0 - Identified - We are continuing to work on a fix for this incident.
Type: Incident Duration: 12 minutes Affected Components: API, Official Models Dec 2, 20:18:03 GMT+0 - Identified - We have identified the issue and are implementing a fix Dec 2, 20:26:12 GMT+0 - Monitoring - Fix is rolled out and queues are decreasing Dec 2, 20:30:26 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 5 minutes Affected Components: API Nov 27, 02:45:34 GMT+0 - Investigating - We are currently investigating this incident. Nov 27, 02:50:27 GMT+0 - Resolved - This incident has been resolved. Please reach out to [[email protected]](mailto:[email protected]) if you experience issues with downloads of files.
Type: Incident Duration: 1 hour and 18 minutes Affected Components: API, Official Models Nov 5, 03:25:38 GMT+0 - Monitoring - We implemented a fix and are currently monitoring the result. Nov 5, 04:08:14 GMT+0 - Resolved - This incident has been resolved. Nov 5, 02:50:00 GMT+0 - Identified - We are continuing to work on a fix for this incident.
Type: Incident Duration: 8 minutes Affected Components: API, Official Models Oct 23, 23:20:00 GMT+0 - Identified - We are saw elevated levels of queuing and new runners not scheduling correctly Oct 23, 23:27:33 GMT+0 - Resolved - This incident has been resolved. Oct 24, 00:21:04 GMT+0 - Resolved - Queues have cleared
Type: Incident Duration: 5 minutes Affected Components: Official Models, API Sep 30, 05:32:08 GMT+0 - Investigating - We are currently investigating this incident. Sep 30, 05:34:53 GMT+0 - Monitoring - We implemented a fix and are currently monitoring the result. Sep 30, 05:37:06 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 13 minutes Affected Components: Official Models, API Sep 26, 02:15:00 GMT+0 - Identified - We are continuing to work on a fix for this incident. Sep 26, 02:41:15 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 1 hour and 40 minutes Affected Components: Official Models, API Sep 23, 19:20:00 GMT+0 - Identified - We are continuing to work on a fix for this incident. Sep 23, 20:59:34 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 30 minutes Affected Components: Official Models, , API → Sep 9, 19:11:50 GMT+0 - Resolved - This incident has been resolved. Sep 9, 18:41:22 GMT+0 - Investigating - We are seeing elevated errors when fetching files returned by the FAL APIs
Type: Incident Duration: 39 minutes Affected Components: Official Models, , , API → Website → Sep 3, 12:39:10 GMT+0 - Investigating - We are currently investigating this incident. Sep 3, 12:59:19 GMT+0 - Identified - We are continuing to work on a fix for this incident. Sep 3, 13:17:46 GMT+0 - Resolved - This incident has been resolved.