Kilo Outage History
10 incidents recorded over the last 365 days, 9 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.
Every Recorded Kilo Incident
| Date | Incident | Duration | Status |
|---|---|---|---|
| Sep 23, 2026 | KiloPass MiniMax coding plan subscriptions issuesMinimax coding plans have been removed. Customers are advised to purchase coding plans directly from Minimax https://kilo.ai/inference/byok/minimax or to seek alternative providers | 146h 57m | Resolved |
| Sep 22, 2026 | Anthropic models temporarily unavailableThis incident has been resolved. | 2h 47m | Resolved |
| Sep 18, 2026 | Increased latency and error ratesThis incident has been resolved. | 21 min | Resolved |
| Sep 17, 2026 | Kilo AI Gateway & API DegradedFrom 07:08 UTC to approximately 07:24 UTC, the Kilo AI Gateway service and API services were degraded. During this period, requests to Kilo AI Gateway and other core API endpoints may have returned 500 Internal Server… | -469 min | Resolved |
| Aug 13, 2026 | Minor Database MaintenanceThe scheduled maintenance has been completed. | 2h 0m | Scheduled |
| Aug 12, 2026 | Kilo Cloud platform is not accessible.This incident has been resolved. | 1h 21m | Resolved |
| Aug 12, 2026 | Usage page is not showing any data for users.This incident has been resolved. | 458h 29m | Resolved |
| Aug 9, 2026 | Update to Kilo Bot for Slack DegradedWe were affected by the recent security incident at Metabase. For more details about the Metabase incident, please see this post on the Anaconda blog… | 0 min | Resolved |
| Aug 7, 2026 | Kilo Bot for Slack degradedThis incident has been resolved. | 46h 58m | Resolved |
| Aug 3, 2026 | Ling 3.0 Flash (inclusionai/ling-3.0-flash) unavailableThe upstream provider issue affecting inclusionai/ling-3.0-flash has been resolved. Requests are succeeding normally, and traffic has remained stable. We will continue to monitor the service. | 8 min | Resolved |
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 Kilo 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 Kilo 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 Kilo 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 Kilo outage in this window ran 19d 2h, against a mean recovery of 3d 1h. If you depend on Kilo 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.