Cloudflare incident: Intermittent 500 errors for backend services on Replicate

Affected components

• Replicate

1. resolvedSep 24, 2026, 22:34 UTC

   The 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.

2. investigatingSep 24, 2026, 20:40 UTC

   We have a backend component that entered an unexpected reboot, causing issues for services downstream.

What APIStatus.watch saw

Our 5-minute checks didn't record a change in Cloudflare's overall status around this incident. Smaller or regional incidents often leave a provider's overall status green.

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• OVHcloud: [EU-WEST-PAR][Network] - Public network incident notificationMajor · Sep 23, 2026, 14:28 UTC
• OVHcloud: [EU-WEST-PAR][Containers & Orchestration] - Managed Kubernetes Service incident notificationMajor · Sep 23, 2026, 14:57 UTC
• Twilio: Voice Call Failures from a Subset of Twilio Phone Numbers to Hong KongMinor · Sep 12, 2026, 00:16 UTC
• Twilio: SMS Delivery Receipt Delays from a Subset of Twilio Short Codes to Liberty Mobile Puerto RicoMinor · Sep 20, 2026, 17:47 UTC
• Twilio: Voice Call Post Dial Delay from Twilio Phone Numbers to Jazz PakistanMinor · Sep 21, 2026, 06:10 UTC
• Akamai: Increased latency during upstream provider maintenance in Singapore, Hong Kong, and JapanMinor · Sep 22, 2026, 00:30 UTC
• Akamai: Origin Server Connectivity Issues with Elevated Errors in APAC RegionMinor · Sep 22, 2026, 14:28 UTC
• Hugging Face: Slower downloads in the Asia-Pacific regionMinor · Sep 22, 2026, 18:48 UTC
• Twilio: Voice Call Failures From a Subset of Twilio Phone Numbers to NorwayMinor · Sep 23, 2026, 15:02 UTC
• Twilio: Voice Call Failures From a Subset of Twilio Phone Numbers to Vodafone in the United Kingdom of Great Britain and Northern IrelandMinor · Sep 23, 2026, 19:34 UTC

How often does Cloudflare have incidents?

Cloudflare reported 38 incidents in the last 90 days, 1 of them major or critical. A typical incident lasted 1h 28m. See Cloudflare's uptime and incident history