LlamaIndex Outage History

36 incidents recorded over the last 365 days, 36 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 LlamaIndex status99.83% uptime history

Every Recorded LlamaIndex Incident

LlamaIndex incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Jul 30, 2026High latency for Parse APIThis incident has been resolved.12 minResolved
Jul 16, 2026Website Login IssuesThis incident has been resolved.38 minResolved
Jul 14, 2026Elevated latency for parse & extract APIsThis incident has been resolved.10 minResolved
Jul 2, 2026Degraded parsing latencyThis incident has been resolved.1h 59mResolved
Jun 24, 2026Elevated API ErrorsThis incident has been resolved.2h 6mResolved
Jun 16, 2026Degraded Parsing ThroughputThis incident has been resolved.8 minResolved
Jun 4, 2026Parse cost effective degradedThis incident has been resolved.1h 46mResolved
Jun 3, 2026Increased parse latencyThis incident has been resolved.24 minResolved
May 31, 2026Service Degradation and High LatencyThis incident has been resolved.53 minResolved
May 8, 2026Increased Parse LatencyThis incident has been resolved.55 minResolved
May 6, 2026Increased Parse LatencyThis incident has been resolved.1h 5mResolved
May 6, 2026Data Processing Delays - Parse v2Parse jobs delayed up to 30m, lasting between 11:30-13:00 UTC-162 minResolved
May 5, 2026System Degraded - Login and Job Resolution IssuesThis incident has been resolved.4 minResolved
Apr 28, 2026API connectivity issuesThis incident has been resolved.22 minResolved
Apr 21, 2026Increased latency on cost_effectiveIncrease latency from upstream provider causing slower than usual parsing on cost_effective mode in EU zone-803 minResolved
Mar 16, 2026Jobs not runningThis incident has been resolved.42 minResolved
Mar 11, 2026Increase parse v2 and extract latencyThis incident has been resolved.1h 39mResolved
Mar 10, 2026Elevated LatencyThis incident has been resolved.1h 44mResolved
Mar 6, 2026Elevated LatencyThis incident has been resolved.2h 1mResolved
Mar 3, 2026High Job LatencyThis incident has been resolved.1h 14mResolved
Mar 2, 2026System OutageThis incident has been resolved.2h 33mResolved
Mar 2, 2026EU LlamaParse partial outage - degraded accuracyThis incident has been resolved.3h 31mResolved
Mar 1, 2026Currently down in EU and NAThis incident has been resolved.2h 52mResolved
Dec 9, 2025[LlamaCloud EU] Partial outage on IndexThis incident has been resolved.10h 6mResolved
Dec 8, 2025LlamaCloud Index Retrieval Elevated Error RatesThis incident has been resolved.3h 10mResolved
Dec 2, 2025Elevated Error Rates for Extract RequestsThis incident has been resolved.22 minResolved
Dec 1, 2025Elevated Latency for LlamaExtractThis incident has been resolved.44 minResolved
Nov 6, 2025Elevated Job Error RatesThis incident has been resolved.49 minResolved
Oct 27, 2025EU degraded performance and errorsThis incident has been resolved.1h 39mResolved
Oct 20, 2025Major service degradation due to AWS outageThis incident has been resolved.13h 28mResolved
Oct 20, 2025AWS outage - some llamacloud services may be degradedThis incident has been resolved.2h 48mResolved
Oct 20, 2025AWS outage - some service may be degradatedThe incident is resolved, we will continue monitoring our service in case of regression.29 minResolved
Oct 16, 2025Service OutageThis incident has been resolved.11 minResolved
Oct 14, 2025Elevated Parsing Error Rates and LatencyThis incident has been resolved.3h 45mResolved
Sep 29, 2025Degraded Parsing ServicesThis incident has been resolved.28 minResolved
Sep 24, 2025Degraded Performance: Elevated Error RatesThis incident has been resolved.20 minResolved

How to Read This LlamaIndex 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 LlamaIndex 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 LlamaIndex outage in this window ran 13h 28m, against a mean recovery of 1h 55m. If you depend on LlamaIndex 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.