Live / DigitalOcean / Incident
DigitalOcean: Llama-4-Maverick Model Availability
DigitalOcean · digitalocean.comMinor incidentResolved2026-07-23 12:37 UTC
Public — what happened
Summary
DigitalOcean reported a minor incident on July 23, 2026, in which the llama-4-maverick model could not be used through its Serverless Inference service. The company said people trying to use that model might receive HTTP 500 errors, and its engineers began looking into the problem at 11:16 UTC. DigitalOcean did not give a cause, and it marked the issue as resolved at 12:37 UTC the same day.
Affected
Inference
Timeline
- Started — 2026-07-23 11:16 UTC
- Investigating — 2026-07-23 11:16 UTC
- Resolved — 2026-07-23 12:37 UTC · 1h 20m after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach DigitalOcean against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for DigitalOcean: paths off baseline right now, where on the route conditions change, and its full incident track record.
Included with any paid plan.
Open the DigitalOcean report →
More from DigitalOcean