DigitalOcean incident: Intermittent errors impacting some Serverless Inference models in ATL1

Affected components

• Agent Runtime

1. resolvedApr 23, 2026, 23:51 UTC

   This incident has been resolved.

2. investigatingApr 23, 2026, 22:26 UTC

   As of 21:53 UTC, our Engineering team is investigating reports of increased internal errors for models Llama 3.3 70B, GPT OSS 120B, GPT OSS 20B, Qwen3 32B and Deepseek R1 70B hosted in the ATL1 region, impacting Serverless Inference. At this point, users with models hosted in ATL1 may experience intermittent errors when using Serverless Inference. We apologize for the inconvenience and will share an update once we have more information.

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.

• Snyk: Snyk recurring tests showing slow performanceMinor · Apr 21, 2026, 18:58 UTC
• Inngest: Degraded performance for REST API (runs/events data)Minor · Apr 23, 2026, 20:06 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