Live  /  Replicate  /  Incident

Replicate: Delayed scaling due to node failure

Replicate · replicate.comMinor incidentResolved2026-08-10 21:45 UTC
Public — what happened

Summary

Replicate reported a minor incident on 2026-08-10 in which some models were slow to scale up, which the company attributed to a node failure. The issue began at 21:05 UTC and was marked resolved at 21:45. In its final update, Replicate said the affected models had been scaling normally for over half an hour and that no backlog of waiting predictions remained.

Timeline

Source of record: provider status page. Summary written by SquidGrid from the provider’s published updates; times in UTC.

Independent path health

The status page is the symptom. SquidGrid measures the paths that reach Replicate against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.

🔒 Sign in to see
Customers get the live Provider Assessment Report for Replicate: its full incident track record, what tends to break, and recent public reports of problems.

Included with any paid plan.

Open the Replicate report →

More from Replicate

The full archive is on the Replicate status & history page.

Related: Replicate status & history. SquidGrid is not affiliated with Replicate.