[GenerativeAPI] - Deepseek-v4/v4.1-flash timeouts
Scaleway reports that some requests to the deepseek-v4-flash and deepseek-v4.1-flash models on the Generative API had elevated timeouts. The error rates are improving and Scaleway monitors the situation.
State
Monitoring
Started
6 d ago
2026-10-26 17:34 UTC
Ongoing for
6 days
Worst impact
Degraded
Timeline
1 updateMonitoring
6 days 100%
Updates
Times in UTCAs posted by Scaleway
Some requests to the deepseek-v4-flash and deepseek-v4.1-flash models had experienced elevated timeouts. The error rates are improving. We're monitoring the situation.
Affected components
2Scaleway in the last 90 days
Full historyIncidents in 90 days
51
Days with an incident
27
Median duration
16 h 45 min
This incident
8.9× the median
Other Scaleway incidents
All incidentsScaleway·[Container Registry] FR-PAR API unreacheable upstream request timeout.
Between 8:00 PM and 9:30 PM, requests to the Container Registry API in the FR-PAR region returned the following error: “Upstream request timeout.”
Scaleway·[fr-par] [Serverless SQL DB] Backups will be suspended on Friday and Saturday nights
Scaleway Serverless SQL DB backups do not run in the fr-par region. The impact is degraded on Serverless-Database components. Scaleway identified the cause and suspended backups on Friday and Saturday nights. Backups start again on Monday morning.
Scaleway·[NL-AMS] - 20% of client requests failed with HTTP 503 errors
October 28, 2026 – 16:14 to 16:27 UTC Approximately 20% of Serverless Containers requests in nl-ams returned HTTP 503 errors, and some active client connections may have been interrupted.
Scaleway·[fr-par-1] Latencies spikes during the day following capacity increase in one of block storage cluster
Scaleway Block Storage has latency spikes in the fr-par-1 region. This degrades Block Storage, Databases, and Instances. Scaleway identified the problem and applies a fix rack by rack. Data must be removed first, so migrations run slowly and continue through the weekend.
Scaleway·[fr-par] [Serverless SQL DB] All SQL databases are unavailable
This incident has been resolved.
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.cc/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.cc/feed.xml?providers=scaleway/feed subscribe https://outages.cc/feed.xml?providers=scalewayFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane