Langfuse Outage History

46 incidents recorded over the last 365 days, 46 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.

Live Langfuse status100.00% uptime history

Every Recorded Langfuse Incident

Langfuse incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Oct 22, 2026[EU] Infrastructure MaintenanceMaintenance has started8 minResolved
Oct 21, 2026Slow trace data retirival across API and UI in EUshould be finally resolved58 minResolved
Oct 20, 2026Degraded performance in Halo (Langfuse Assistant)Issue with Langfuse Halo (assistant) is fixed.47 minResolved
Oct 20, 2026Degraded data serving in EUHave been stable25 minResolved
Oct 19, 2026Degraded public API performanceProblematic workload was identified and isolated.44 minResolved
Sep 30, 2026Degraded ingestion for 20 projectsAll projects ingesting as normal6h 20mResolved
Sep 23, 2026Elevated error rates in In App AgentThe issue has been resolved.6 minResolved
Sep 16, 2026OTEL ingestion queue delay over 10 minutes in USIssue is resolved and OTEL ingestion pipeline is back to regular ingestion speed.1h 11mResolved
Sep 14, 2026Delayed Ingestion for non v4 SDKsThe incident has been resolved.3h 18mResolved
Sep 8, 2026OTEL Ingestion Delay exceeds 10 minutesOTEL ingestion latency spike is resolved1h 34mResolved
Sep 2, 2026Degraded OTEL ingestion in US regionCompletely back to normal53 minResolved
Aug 25, 2026Performance degradation on ingestion pathIssue resolved. Latency is back to normal levels.1h 4mResolved
Aug 25, 2026Latency degradation on legacy ingestion queueIssue resolved since 12:30. Legacy ingestion pipeline is fully operational.3h 26mResolved
Aug 21, 2026[Triggered] [TEST] [HIPAA] OTEL Ingestion Delay exceeds 10 minutesWe're investigating degraded performance in the ingestion flow6 minResolved
Aug 20, 2026[Triggered] [TEST] [PROD-EU] OTEL Ingestion Queue Delay Status Page (10 minutes)We're investigating degraded performance in the ingestion flow1 minResolved
Aug 20, 2026[Triggered] [TEST] [PROD-EU] OTEL Ingestion Queue Delay Status Page (10 minutes)We've successfully resolved the incident.1 minResolved
Aug 20, 2026Evaluations are delayed in EUAll is back to normal1h 49mResolved
Aug 19, 2026Longer v3 -> v4 propagation delayBack to normal propagation delay2h 33mResolved
Aug 18, 2026Degraded LLMaJ execution in EUSteady throughput for the last 30 minutes. Delay < 5min.1h 18mResolved
Aug 15, 2026prod-us: Delayed ingestion for prod-usWe incurred a temporary delay on the legacy ingestion path for v4. This delay has been resolved. OTEL ingestion has not been impacted.36 minResolved
Aug 12, 2026Latency increase eval execution up to 40 minutes is resolvedThe issue is resolved now1h 40mResolved
Aug 3, 2026[US] Ingestion DelaysThis issue is resolved and we're back to regular processing times.38 minResolved
Jul 14, 2026502 BAD Gateway errors on UIWe resolved the performance bottleneck. All APIs are responding as expected as of now.1h 6mResolved
Jul 2, 2026[EU] Elevated latencies and error ratesThe issue has been resolved.20 minResolved
Jun 26, 2026[EU] Elevated ingestion timesThe incident has been resolved.18 minResolved
Jun 16, 2026Elevated API and tracing latency in the US regionAll latencies are back to normal36 minResolved
Jun 10, 2026Ingestion delayWe scaled our ingestion and are processing data in time.28 minResolved
Jun 8, 2026Database upgrdaeUpgrade successfully resolved.0 minResolved
Jun 8, 2026Our media API returns 500 errorsWe scaled our infrastructure and are processing media uploads without errors.57 minResolved
Jun 2, 2026[EU] Elevated latencies in UIThis issue has been resolved.1h 11mResolved
Jun 1, 2026[EU] Elevated error rates and delayed insertsThe underlying incident with our infrastructure (https://statuspage.incident.io/clickhousecloud/incidents/01KT1G25S9PBKM7VJEB146680G) has been resolved.2h 19mResolved
May 28, 2026[US] Delayed LLM as a judge evaluationWe've fully caught up and process LLM as a judge in realtime again.59 minResolved
May 27, 2026LLM as a Judge execution is delayedWe have scaled our infra to drain the queue backlog. Evals are executed without delay again.1h 18mResolved
May 26, 2026Delayed LLM as a judge executionThe queue backlog has been fully processed for legacy trace and dataset targeted evals. There is no longer a delay for eval executions.3h 42mResolved
May 13, 2026[EU] Elevated latencies and timeoutsLatencies and error rates have recovered.14 minResolved
May 8, 2026Errors and latencies on ingestion APIsThe underlying issue was resolved.1h 16mResolved
May 5, 2026Delayed OTEL ingestionAll data is processed in time.26 minResolved
Apr 29, 2026[EU + US] Elevated errors for API readsWe've reverted a bad patch and see recovery. All routes should work as expected.4 minResolved
Apr 14, 2026Delayed "fast preview"The issue has been resolved and we're back to the usual processing times.8h 56mResolved
Mar 17, 2026[US] Ingestion DelaysThe backlog was processed and ingestion delays are below 30 seconds again.13 minResolved
Mar 16, 2026[EU] Elevated Evaluation Execution LatenciesWe've adjusted scaling in the system and currently see a delay of below 5min for LLM as a judge executions.24 minResolved
Mar 12, 2026[EU] Elevated ingestion delaysThe issue has been resolved.18 minResolved
Mar 11, 2026Slow Traces APIWe scaled our systems. APIs should respond fast again.19 minResolved
Feb 25, 2026Delayed execution of LLM-as-a-judgeWe are now processing all llm as a judge executions in time.3h 2mResolved
Jan 21, 2026[EU, US, HIPAA] Elevated 403 rates across Prompt APIsFor the past 40min, we observed elevated rates of 403 errors across Langfuse Cloud APIs, mainly the prompt API route. As a follow-up to previous CloudFlare incidents…-1369 minResolved
Dec 10, 2025[EU] Elevated latencies and request timeoutsWe narrowed the issue down to intermittent problems within our internal networking stack and elevated delays that caused cascading failures. In the meantime, we've added capacity as this reduces the likelihood of this…2h 54mResolved

Hear about the next one while it is open

Everything above is a record written after the fact. We can email you when the next Langfuse incident opens instead, at the point where knowing still changes what you do.

Free, no password, no card. Unsubscribe in one click.

How to Read This Langfuse Incident Log

Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Langfuse acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.

Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.

The longest single Langfuse outage in this window ran 8h 56m, against a mean recovery of 1h 21m. If you depend on Langfuse in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.