Live  /  Scaleway  /  Incident

Scaleway: [Generative API] - [global] - GLM-5.3 timeouts

Scaleway · scaleway.comMinor incidentResolved2026-11-06 10:45 UTC
Public — what happened

Summary

Scaleway said its Generative API was returning timeout errors on every request to the glm-5.3 model, an issue it rated as minor. The company posted about the problem on 20 October 2026 at 15:31 UTC and said it was working on a solution. About ten minutes later, at 15:42 UTC, it said a fix was in place and it was watching the results. Scaleway marked the incident resolved on 6 November 2026 at 10:45 UTC and did not state a cause.

Affected

fr-par-1, fr-par-2, fr-par-3, nl-ams-1, nl-ams-2, nl-ams-3, pl-waw-1, pl-waw-2, pl-waw-3, it-mil-1, it-mil-2, it-mil-3, Generative API

As listed on Scaleway’s status page.

Timeline

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

What SquidGrid measured

SquidGrid measured 277 internet paths into Scaleway’s network during this incident. None of them ran meaningfully slower than the same paths the day before.

Independent path health

The status page is the symptom. SquidGrid measures the paths that reach Scaleway 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 Scaleway: paths off baseline right now, where on the route conditions change, and its full incident track record.

Included with any paid plan.

Open the Scaleway report →

More from Scaleway

Covered in The Squid’s Ink, Week 44, 2026, our weekly internet health report.

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

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