Black Forest Labs
AI. Source: Black Forest Labs status page.
- Incidents, last 90 days
- 9
- Median to mitigation
- 4h 39m
- Median to resolution
- 4h 51m
- p95 to resolution
- 20h 15m
- Naming an upstream provider
- 0%
- With a postmortem on the status page
- 0%
What failed, last 90 days
| A zone, region or data center became unavailable | 5 |
| A provider or third-party service this vendor depends on failed | 1 |
| A configuration change caused the failure | 1 |
| Hardware, power, cooling or another physical failure | 1 |
| Traffic surge or denial-of-service attack | 1 |
Tagged by claude-haiku-5-5 from each incident's updates. See the methodology.
Incidents per month
All recorded incidents
EU cluster increased latencies
Affected: API (api.bfl.ai), API EU (api.eu.bfl.ai)
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
investigating
We are currently investigating this issue.
-
investigating
We are continuing to investigate this issue.
-
identified
The issue has been identified and 3d party is working on a resolution. To mitigate please consider switching over to api.bfl.ai: https://docs.bfl.ai/api_integration/integration_guidelines
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
US region increased latencies
Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).
-
identified
The issue has been identified and a fix is being implemented.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Please avoid cluster specific endpoints.
Failure mode: A configuration change caused the failure. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
resolved
After the maintenance on our US3 cluster, the regional endpoint api.us3.bfl.ai is no longer valid, however we are still receiving traffic from certain users. Please ensure to only ever use the global api.bfl.ai or regional api. .bfl.ai endpoints as specified in the docs, not...
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
EU region cluster outage
Affected: API (api.bfl.ai)
Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
investigating
EU cluster outage leading to slow or failed generations - traffic has been shifted to other clusters on api.bfl.ai - customers using our European endpoint, api.eu.blf.ai, will still see impact
-
resolved
Full capacity restored to api.eu.bfl.ai
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Cluster Down - FLUX.2 [flex] Traffic Impacted
Affected: API (api.bfl.ai)
Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
identified
One of our inferencing clusters is down, which is impacting FLUX.2 [flex] traffic. The rest of our models should be unimpacted.
-
resolved
FLUX.2 [flex] restored - vendor mitigation in place with full recover observed
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Extended flux-3-video generation times
Failure mode: Hardware, power, cooling or another physical 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 currently investigating this issue.
-
identified
Cluster storage outage identified, vendor implementing fix
-
monitoring
Fix is in place and we are seeing full recovery
-
resolved
Observing full recovery.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
US4 region increased latencies
Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Regional outage - elevated response times on some calls
Failure mode: A zone, region or data center became unavailable. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
investigating
This is a minor issue isolated to a portion of our US infrastructure. We have isolated the problem and are working to restore api to full serving capacity
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Flux 3 Launch Traffic
Failure mode: Traffic surge or denial-of-service attack. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
-
identified
We are experiencing significant traffic from our Flux 3 launch and are working to serve all customers. We appreciate your understanding and are working to lower generation times and give everyone the chance to experience our new video models!
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
We have completed initial scaling and optimizations to enable more traffic through on the flux-3-video api. The BFL team are excited to see what everyone creates!
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
US3 cluster intermittent latency increase
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
-
identified
US3 has issues due to the 3d party experiencing service degradation.
-
monitoring
A fix has been implemented and we are monitoring the results.
-
identified
The issue has been identified and a fix is being implemented.
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
High demand causing degraded performance in some regions
Failure mode: Traffic surge or denial-of-service attack. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
-
resolved
Large increase in traffic to our services is causing delays in image generation. We are working to balance traffic and bring down the time it takes to receive you images!
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
High Latency
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], API (api.bfl.ai), FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max], FLUX.2, FLUX.2 [klein]
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're experiencing higher latency on our EU2 cluster. We're investigating the root cause.
-
investigating
We are continuing to investigate this issue.
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Elevated error rates
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).
-
identified
The issue has been identified and a fix is being implemented.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
EU region increased error rates in one of the clusters
Failure mode: A zone, region or data center became unavailable. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
identified
The issue has been identified and a fix is being implemented.
-
monitoring
Third party provider restoring systems after power outage.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Klein endpoint error rate
Affected: FLUX.2 [klein]
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 issue.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Moderation Outage - Increased api failures
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).
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increased error rate for /v1/flux-kontext-max
Affected: FLUX.1 Kontext [max]
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).
-
identified
The issue has been identified and a fix is being implemented.
-
monitoring
The error rate is small, we implemented several fixes to mitigate and work on the major update to resolve the issue.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
500 error rates increase
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).
-
identified
The issue has been identified and a fix is being implemented.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Image Generation Failures (Internal Error)
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max], FLUX.2, FLUX.2 [klein]
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 medium confidence (taxonomy v0.2).
-
identified
Image generation is experience internal errors, issue has been identified and fix is underway
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Latency increase
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 medium confidence (taxonomy v0.2).
-
investigating
We are experiencing above average load and working to mitigate this.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
EU region downstream provider issues
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
investigating
We are currently investigating this issue.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Flux Kontext Pro increased latencies
Affected: FLUX .1 Kontext [pro]
Failure mode: A provider or third-party service this vendor depends on failed. 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 issue.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
EU cluster increased error rates
Failure mode: A zone, region or data center became unavailable. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
resolved
Infrastructure maintenance operation in EU2 region caused temporary disruptions to request processing, resulting in elevated error rates for approximately two hours. The issue resolved automatically and all services are operating normally.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
US api endpoint error rate
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 issue.
-
investigating
Noting that this should not affect customers using the primary global or regional endpoints noted in the Docs here: https://docs.bfl.ai/quick_start/generating_images#legacy-regional-endpoints.
-
investigating
The issue is now partially affecting traffic on the primary global/regional endpoints. We're focusing all capacity on resolving this.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Flux-2-pro increased latency
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 issue.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increased latency and error rates
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
-
resolved
Temporary disruption with a downstream provider in the moderation chain. The issue is resolved as the downstream service recovered.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Cluster component outage caused increased error rates and latency.
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).
-
resolved
A critical component in one regional cluster was failing which resulted in increased latency and error rates. A fix has been deployed to prevent this issue in the future.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
flux-kontext-v2-3k issues in US region
Failure mode: A zone, region or data center became unavailable. 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 issue.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increased latency on Flux 2 preview
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 issue.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increased latency in EU2
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 medium confidence (taxonomy v0.2).
-
investigating
We're investigating an increase in latency in a single EU cluster, EU2, for a few of our models.
-
monitoring
We've identified the issue and implemented a fix, latency is returning to normal and we'll keep monitoring.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Long Response Times
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 investigating an issue with some generations taking a longer amount of time than usual
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increased 500x error rate
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 medium confidence (taxonomy v0.2).
-
investigating
Customers experience error 500 on some endpoints. We are looking into it.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Some requests can return empty results
Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).
-
investigating
Issue is identified and we are working on a fix. This affects only Flux.2.
-
investigating
We are continuing to investigate this issue.
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increased error rate on Flux2 endpoint
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 the issue.
-
identified
The issue has been identified and fix is being worked on.
-
monitoring
A fix has been implemented and we are monitoring the results.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Auth + Credit Issues
Failure mode: Login, tokens, certificates or credentials failed. 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 encountering some authentication issues relating to Playground and Google login.
-
investigating
We noted that purchasing new credits is also encountering some issues, currently investigating.
-
investigating
Auth issues are resolved, still investigating credits purchase.
-
investigating
We are continuing to investigate this issue.
-
investigating
We are also noted an increase in 403s for certain older endpoints, we've identified the issue and are deploying a fix.
-
resolved
This incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Certain BFL services temporarily unavailable
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
-
investigating
We are currently experiencing elevated error rates on BFL Playground, Auth and Dashboard endpoints coming from one of our service providers that has a significant outage. We are investigating our options for mitigation. Thank you for your patience!
-
resolved
The Incident has been resolved on the cloud provider side, all systems operational.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
429 errors on some clusters
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 investigating an issue triggering 429 errors in some clusters.
-
monitoring
A fix has been implemented and we are monitoring now. You should be able to use the different endpoints again.
-
investigating
Investigating the same issue again
-
identified
We have resolved one issue, and are working on resolving another one only applying to some customers.
-
monitoring
A fix has been implemented and we are monitoring the situation
-
resolved
Incident has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
US2 Bad Gateway / Unresponsive
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 medium confidence (taxonomy v0.2).
-
investigating
We are investigating an issue related to the `us2` cluster returning errors in some cases.
-
investigating
We are continuing to investigate this issue.
-
identified
We have identified the issue and are working on a fix.
-
resolved
The incident has now been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Elevated Latency
Affected: FLUX 1.1 [pro], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 medium confidence (taxonomy v0.2).
-
investigating
We are investigating an issue with elevated latency.
-
investigating
We are continuing to investigate this issue.
-
monitoring
A fix has been put in place, we are monitoring.
-
resolved
The issue has been resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Elevated Latency
Affected: FLUX.1 Fill [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 seeing elevate latency on multiple endpoints.
-
resolved
The incident has been resolved
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Latency increase on some endpoints
Affected: FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 an issue on FLUX.1 Kontext about a latency increase.
-
monitoring
A fix has been implemented and we are monitoring
-
resolved
The incident has been resolved now.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increase latency
Affected: FLUX 1.1 [pro]
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 investigating an issue with FLUX 1.1 [pro]
-
investigating
We are continuing to investigate this issue.
-
resolved
The incident is now resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Kontext Max slow down
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 issue.
-
investigating
We are continuing to investigate this issue.
-
monitoring
A fix has been implemented and we're monitoring the situation
-
resolved
The incident has been resolved
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increase Latency on our clusters
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 medium confidence (taxonomy v0.2).
-
investigating
We are currently investigating an latency increase issue on our clusters.
-
resolved
The incident has been resolved
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Global Outage
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
Names an upstream provider: Azure.
Started during Azure: Azure Front Door – Connectivity issues across multiple regions.
-
identified
Azure is currently experience issues resulting in a full outage in our image generation services. We are awaiting a status update from them.
-
identified
We have implemented a mitigation to the problem. Please use regional endpoints for now: `https://api.eu2.bfl.ai` and `https://api.eu4.bfl.ai/`
-
monitoring
A fix has been implemented. Please use the global endpoint: https://api.bfl.ai. DNS cache needs to be flushed. Regional endpoints: api.us.bfl.ai and api.eu.bfl.ai are not functional at the moment.
-
monitoring
A fix has been implemented. Please use the global endpoint: https://api.bfl.ai. Regional endpoints are also now operational: `api.eu.bfl.ai`, and `api.us.bfl.ai`
-
monitoring
A fix has been implemented. Please use the global endpoint: https://api.bfl.ai. Regional endpoints are also now operational: `api.eu.bfl.ai`, and `api.us.bfl.ai` As part of our cloud-outage mitigation, we’ve temporarily moved delivery to the following Azure Blob endpoints....
-
identified
Apologies, false status update
-
resolved
Our third party had resolved their issue be we kept monitoring closely, we trust the stability now.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Increased Latency of US1 Cluster
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, Finetuning, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 medium confidence (taxonomy v0.2).
-
investigating
We have seen an increase in latency on the US1 cluster and are investigating.
-
resolved
We identified and resolved the issue.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
US1 Slowdown
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, Finetuning, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 medium confidence (taxonomy v0.2).
-
identified
Our US1 cluster is experiencing some scaling issue, resulting in some requests taking longer to process. We're working on a fix.
-
monitoring
Issue has been brought under control, we're monitoring the fix.
-
resolved
Scaling is stable again.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Intermittent Connection Issues
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, Finetuning, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
-
identified
Due to a critical third party dependency we rely on for load balancing experiencing issues, customers within certain regions are experiencing an increase in latency and timeouts.
-
resolved
The third party has declared their incident resolved.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Cluster outage leading to enhanced latency
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, Finetuning, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).
-
monitoring
A fix has been implemented and we are monitoring the results.
-
monitoring
A critical external dependency outage has been identified, and triaged
-
monitoring
We are continuing to monitor for any further issues.
-
resolved
The critical external dependency has become stable again.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.
Degraded performance
Affected: FLUX 1.1 [pro], FLUX.1 [pro], FLUX.1 [dev], FLUX 1.1 [pro] Ultra, FLUX.1 Fill [pro], FLUX.1 Canny [pro], FLUX.1 Depth [pro], FLUX .1 Kontext [pro], FLUX.1 Kontext [max]
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 medium confidence (taxonomy v0.2).
-
investigating
We are currently experience degraded performance, you may face higher latency or timeouts. We are working on it.
-
investigating
We are still investigating the issue.
-
investigating
We are continuing to investigate the issue and are checking several potential root causes. Higher latency and occasional errors are still to be expected.
-
investigating
We’ve narrowed the problem down to a single issue. Our team is working on a fix, and performance may still be degraded in the meantime. We’ll provide another update once the fix is deployed.
-
monitoring
We have identified the issue, implemented a fix and are now monitoring the results
-
resolved
This incident has been resolved now.
Excerpts are shortened. Read the full incident on Black Forest Labs's status page.