[GAPI] - [GLOBAL] - Increased error rate for model DeepSeek v4.1 Flash 1017
Scaleway reports more errors for the model DeepSeek v4.1 Flash 1017. The Generative API is degraded. Scaleway is investigating the problem.
State
Investigating
Started
Ongoing for
55 min
Worst impact
Degraded
Timeline
1 updateInvestigating
55 min 100%
Updates
Times in UTCAs posted by Scaleway
DeepSeek v4.1 Flash 1017 presents elevated error rates. We are investigating to fix the problem.
Affected components
2Scaleway in the last 90 days
Full historyIncidents in 90 days
80
Days with an incident
43
Median duration
15 h 5 min
This incident
94% shorter than the median
Other Scaleway incidents
All incidentsScaleway·[IAM] - Cannot add or update organization-level policy rules
Scaleway reports that users cannot add or update IAM policy rules with organization-level permission sets. The incident is resolved. It lasted 67 minutes.
Scaleway·[Generative API] - [global] - GLM-5.3 timeouts
Scaleway reports that the glm-5.3 model returns timeout errors on requests. This affects the Generative API and the Elements Generative API product. Scaleway is investigating the issue and works to fix it.
Scaleway·[VPS] - Paris - servers stuck in maintenance
Scaleway Dedibox VPS instances in Paris do not work when they stay in the vps.states.maintenance status. Scaleway reports that the incident is resolved. The incident lasted from 13 November 2026 to 16 November 2026.
Scaleway·[Transactional Email] - world - Delayed email delivery to Microsoft domains (Outlook/Hotmail)
Scaleway Transactional Email delivery to Microsoft consumer domains (Outlook and Hotmail) was delayed. All sending pools were affected. Scaleway reported the incident as resolved on 2026-11-16. The incident lasted about 3 days and 14 hours.
Scaleway·[Network] [DC3]- Room S45 rack D14 - Public switch reboot
Scaleway reports a public switch reboot in room S45, rack D14 at DC3. This issue affects Dedibox public connectivity in DC3. Scaleway resolved the incident after 18 hours and 52 minutes.
Follow Scaleway
Your coding agent knows when Scaleway is down, and tells you when a failure is theirs, not yours. You can also get Scaleway incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "scaleway" and tell me if Scaleway has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.live/feed.xml?providers=scaleway/feed subscribe https://outages.live/feed.xml?providers=scalewayFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane