Resolved
Cloudflare · degraded service
Intermittent 500 errors for backend services on Replicate
Started 24 Sep 20:40 UTC, resolved 24 Sep 22:34 UTC: it lasted 1 h 54 min.
1 h 54 min
How long it lasted, from the provider's times
2Updates posted
6Other incidents at the same timeWhat it affected
As the provider names itWhat the provider posted
Newest first- 24 Sep 22:34 UTCResolvedThe impacted backend has been redeployed, and all related services should now be back up and running. There may be some increased latency as they continue to come online.
- 24 Sep 20:40 UTCInvestigatingWe have a backend component that entered an unexpected reboot, causing issues for services downstream.
Around it
From the sources ChangeIntel reads; a match in time is not a causeElsewhere at the same time
- Cloudflare Cloudflare One Clients are incorrectly challenged on some sites
- OpenAI Elevated Error Rates on GPT-6 Astra Pro
- Cloudflare Delays Starting Cloudflare Workers Builds
- Cloudflare Browser isolation session data sync issues
- GitHub Disruption with billing information updates
- Cloudflare Network Performance Degradation — Asia-Pacific
Earlier incidents in the 14 days before
- Cloudflare: Cloudflare Access updates delayedService incident · 24 Sep
- Cloudflare: Customers using BYOIP can have issues updating their BGP prefixes, including advertising or withdrawing prefixes.Service incident · 24 Sep
- Cloudflare: Elevated Errors with any / all in http_response_cache_settingsService incident · 23 Sep
- Cloudflare: Intermittent authentication errors for API and R2Service incident · 23 Sep
- Cloudflare: Increased Errors for Durable ObjectsService incident · 23 Sep
What changed
First observed 14 Oct 2026No field changes in the recorded history.
Cite this recorded revision to keep the same title, summary, facts and links when the page changes.
A day selects the latest observation by the end of that UTC day; today's selection can change until midnight. History starts when this installation records it.
Keep track
- Service status now: every provider ChangeIntel reads, with ongoing incidents first.
- Status RSS feed: new and ended incidents as they happen.
- Everything about Cloudflare: its changes, known issues and incidents on one timeline.