DigitalOcean outage: Anthropic reported outage that's impacting access to their Serverless Inference models

Affected components

• Agent Runtime

1. resolvedMay 15, 2026, 02:00 UTC

   As of the current time, our Engineering team has confirmed that the issue with Serverless Inference has been resolved. The root cause of the issue was an outage with our provider, Anthropic, which affected users of Sonnet 4.6 and Opus 4.7 models. According to Anthropic's status page (https://status.claude.com/incidents/8z7l5zcy0v3b), they have resolved the outage. If you continue to experience problems, please open a ticket with our Support team. We apologize for any inconvenience this may have caused.

2. identifiedMay 15, 2026, 01:23 UTC

   According to Anthropic's status page (https://status.claude.com/incidents/8z7l5zcy0v3b), they have identified the root cause and are actively working on a fix. At this time, users may continue to experience errors when attempting to use Sonnet 4.6 and Opus 4.7 models. We will provide another update once Anthropic has implemented a fix and service is restored.

3. monitoringMay 15, 2026, 01:21 UTC

   As of the current time, our Engineering team is aware of an ongoing incident with our provider, Anthropic, that is impacting Serverless Inference. The outage is affecting all users attempting to use Sonnet 4.6 and Opus 4.7 models. According to Anthropic's status page (https://status.claude.com/incidents/8z7l5zcy0v3b), they are currently experiencing an outage that is causing this disruption. We apologize for the inconvenience 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.

• Confluent Cloud: Elevated error rates and latency on produce and consume operations on AWS us-east-1 AZ4Major · May 8, 2026, 01:14 UTC
• New Relic: UI and Data Irregularities - US RegionMajor · May 15, 2026, 00:06 UTC
• Linode: [DirtyFrag] Linux Privilege Escalation VulnerabilityMinor · May 8, 2026, 13:40 UTC
• Linode: [Fragnesia] Linux Privilege Escalation VulnerabilityMinor · May 13, 2026, 21:02 UTC
• Amplitude: Slower realtime processingMinor · May 14, 2026, 21:42 UTC
• Mixpanel: Query API degraded performanceMinor · May 14, 2026, 23:17 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