EU region cluster outage
Full capacity restored to api.eu.bfl.ai
The latest update from Black Forest Labs.
State
Resolved
Started
74 d ago
2026-08-19 19:47 UTC
Lasted
4 h 51 min
until 2026-08-20 00:39 UTC
Worst impact
Degraded
Timeline
2 updatesInvestigating
4 h 51 min 100%
Updates
Times in UTCAs posted by Black Forest Labs
Full capacity restored to api.eu.bfl.ai
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
Affected components
1Black Forest Labs in the last 90 days
Full historyIncidents in 90 days
9
Days with an incident
8
Median duration
4 h 51 min
This incident
About the median
Other Black Forest Labs incidents
All incidentsBlack Forest Labs·EU cluster increased latencies
This incident has been resolved.
Black Forest Labs·US region increased latencies
This incident has been resolved.
Black Forest Labs·Please avoid cluster specific endpoints.
After the maintenance on our US3 cluster, the regional endpoint api.us3.bfl.ai is no longer valid, however we are still receiving traffic from certain users.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 cluster specific ones like api.us3.bfl.ai, to avoid using internal domains that may be removed at any time. https://docs.bfl.ai/api_integration/integration_guidelines#api-endpoints-overview
Black Forest Labs·Cluster Down - FLUX.2 [flex] Traffic Impacted
FLUX.2 [flex] restored - vendor mitigation in place with full recover observed
Black Forest Labs·Extended flux-3-video generation times
Observing full recovery.
Follow Black Forest Labs
Your coding agent knows when Black Forest Labs is down, and tells you when a failure is theirs, not yours. You can also get Black Forest Labs incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "blackforestlabs" and tell me if Black Forest Labs has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.live/feed.xml?providers=blackforestlabs/feed subscribe https://outages.live/feed.xml?providers=blackforestlabsFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane