fal
AI. Source: fal status page.
- Incidents, last 90 days
- 2
- Median to mitigation
- 24m
- Median to resolution
- 24m
- p95 to resolution
- 30m
- Naming an upstream provider
- 0%
- With a postmortem on the status page
- 0%
What failed, last 90 days
| The text does not say enough to tell | 1 |
| Network, DNS, routing or connectivity failure | 1 |
Tagged by claude-haiku-5-5 from each incident's updates. See the methodology.
Incidents per month
All recorded incidents
Investigating slowness and reduced traffic
Affected: Serverless API, Model API
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
fal.run is unreachable for synchronous requests
Affected: Model API
Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are not processing requests calling directly to [fal.run](http://fal.run) domain.
-
identified
Identified the issue
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Request Metrics Lag
Affected: Serverless API, Serverless Dashboard
Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
identified
Serverless request metrics are appearing slower than usual.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Degraded outbound DNS from runners
Affected: Serverless API, Model API
Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
identified
We are continuing to work on a fix for this incident.
-
monitoring
We implemented a fix and are currently monitoring the result.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Elevated API error rates
Affected: Serverless API, Model API
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Experiencing Issues with Request Recording and Metrics
Affected: Serverless API, Serverless Dashboard
Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
identified
Recent request data and metrics may be incomplete.
-
resolved
Data from the last couple of hours is available, we are working to backfill missing data.
Excerpts are shortened. Read the full incident on fal's status page.
High latency
Affected: Official Models, API →
Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
identified
We are continuing to work on a fix for this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Errors and high latency
Affected: Official Models, API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Model APIs are degraded and file downloads are not working
Affected: Official Models, Website → API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Degradation
Affected: Official Models, Website → API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
monitoring
We implemented a fix and are currently monitoring the result.
-
resolved
This incident has been resolved. We are deeply sorry for the inconvenience caused and will follow up with a detailed RCA.
Excerpts are shortened. Read the full incident on fal's status page.
Errors and high latency
Affected: fal-ai/nano-banana-pro, fal-ai/bytedance, fal-ai/flux, Official Models, fal-ai/nano-banana, fal-ai/kling-video, Models → API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
monitoring
We implemented a fix and are currently monitoring the result.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Website & Persistent Data Volume Issues
Affected: fal-ai/nano-banana-pro, fal-ai/bytedance, fal-ai/flux, Official Models, fal-ai/nano-banana, fal-ai/kling-video, Website → API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Errors and high latency
Affected: fal-ai/nano-banana-pro, fal-ai/bytedance, fal-ai/flux, Official Models, fal-ai/nano-banana, fal-ai/kling-video, Website → API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Errors and high latency
Affected: fal-ai/nano-banana-pro, fal-ai/bytedance, fal-ai/flux, Official Models, fal-ai/nano-banana, fal-ai/kling-video, Website → API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
High latency and errors on FLUX models
Affected: fal-ai/flux, Official Models, API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
REST API and Web Platform is having DNS issues (does not affect inference services)
Affected: Website →
Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Degraded performance
Affected: Official Models, API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
identified
We are continuing to work on a fix for this incident.
-
resolved
This incident has been resolved, we are recovering
Excerpts are shortened. Read the full incident on fal's status page.
Specific models are experiencing high queue time
Affected: Official Models, API →
Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
identified
We have identified the issue and are implementing a fix
-
monitoring
Fix is rolled out and queues are decreasing
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Investigating issues with file access
Affected: API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
resolved
This incident has been resolved. Please reach out to [support@fal.ai](mailto:support@fal.ai) if you experience issues with downloads of files.
Excerpts are shortened. Read the full incident on fal's status page.
Request queuing
Affected: Official Models, API →
Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
identified
We are continuing to work on a fix for this incident.
-
monitoring
We implemented a fix and are currently monitoring the result.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Request queuing and runner failures
Affected: Official Models, API →
Failure mode: Orchestration, control plane, service discovery or load balancing failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
identified
We are saw elevated levels of queuing and new runners not scheduling correctly
-
resolved
This incident has been resolved.
-
resolved
Queues have cleared
Excerpts are shortened. Read the full incident on fal's status page.
Some models are returning errors, investigating
Affected: Official Models, API →
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are currently investigating this incident.
-
monitoring
We implemented a fix and are currently monitoring the result.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Some models are experiencing queuing
Affected: Official Models, API →
Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
identified
We are continuing to work on a fix for this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Degraded performance and large queues on specific models
Affected: Official Models, API →
Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
identified
We are continuing to work on a fix for this incident.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.
Degraded file storage
Affected: Official Models, API →
Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
investigating
We are seeing elevated errors when fetching files returned by the FAL APIs
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on fal's status page.