DigitalOcean incident: Elevated 5xx “context canceled” errors impacting serverless inference

Affected components

• Agent Runtime

1. resolvedApr 28, 2026, 19:33 UTC

   All services are operating normally. We will continue to monitor the system to ensure ongoing reliability. Thank you for your patience while we worked to resolve this issue.

2. monitoringApr 28, 2026, 19:00 UTC

   Service for Serverless Inference has been restored. We’ve implemented tighter rate limits to help prevent recurrence and are closely monitoring system performance. Some users may still experience intermittent latency as we complete final stabilization efforts. Our team remains actively engaged to ensure full recovery. We appreciate your patience and will provide further updates as needed.

3. identifiedApr 28, 2026, 15:59 UTC

   We have identified an issue affecting our service and are currently working to implement a fix. Our team is actively investigating and taking the necessary steps to restore normal operations as quickly as possible. We appreciate your patience and will provide updates as soon as more information becomes available.

4. investigatingApr 28, 2026, 13:45 UTC

   Serverless inference customers are experiencing elevated 5xx errors, including “context canceled” responses. This may result in intermittent request failures. Our team is actively investigating and will provide updates as more information becomes available.

What APIStatus.watch saw

Our 5-minute checks didn't record a change in DigitalOcean'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.

• 1Password: Login and Sync IssuesCritical · Apr 27, 2026, 14:54 UTC
• Elasticsearch: Missing Metrics in Cloud Console — US East (us-east-1)Major · Apr 28, 2026, 14:46 UTC
• Miro: Some users experienced issues with AI featuresMajor · Apr 28, 2026, 15:14 UTC
• Amplitude: Amplitude web application not loadingMajor · Apr 28, 2026, 18:50 UTC
• Snyk: Snyk recurring tests showing slow performanceMinor · Apr 21, 2026, 18:58 UTC
• Mux: Mux Data Pipeline Latency for EU CustomersMinor · Apr 28, 2026, 16:05 UTC
• Akamai: Intermittent Edge Delivery Delays in Chennai, IN (MAA) RegionMinor · Apr 28, 2026, 16:42 UTC
• Linode: Service Issue - Connectivity Issues - Chennai (IN-MAA)Minor · Apr 28, 2026, 17:17 UTC
• LaunchDarkly: Issues with Observability Alert NotificationMinor · Apr 28, 2026, 18:34 UTC
• ReadMe: Creating branches is resulting in 500 errorsMinor · Apr 28, 2026, 18:38 UTC

How often does DigitalOcean have incidents?

DigitalOcean reported 20 incidents in the last 90 days, 3 of them major or critical. A typical incident lasted 5h 35m. See DigitalOcean's uptime and incident history