Mistral Small 4 Server-side errors
Mistral Small 4 had intermittent server-side errors. Mistral AI reported the incident as resolved after 3 hours and 22 minutes.
State
Resolved
Started
Lasted
3 h 22 min
Worst impact
Degraded
Timeline
5 updatesInvestigating
2 h 21 min 70%
Resolved
18 min 9%
Monitoring
44 min 22%
Updates
Times in UTCAs posted by Mistral AI
The partial outage has been resolved.
We have implemented a fix and are actively monitoring model health.
We are investigating partial degradation affecting mistral-small-2603, causing intermittent server-side errors. We are actively working to identify and resolve the issue.
The incident has been resolved.
We are experiencing server-side errors on Mistral Small 4 and are actively investigating.
Mistral AI in the last 90 days
Full historyIncidents in 90 days
25
Days with an incident
21
Median duration
38 min
This incident
5.4× the median
Other Mistral AI incidents
All incidentsMistral AI·OCR 4.1 Server-side errors
Mistral AI reports server-side errors and higher latency on the OCR models OCR 3, OCR 4.1, and OCR-2512. Mistral AI reports that the incident is resolved. The incident lasted 94 minutes.
Mistral AI·Vibe Work is experiencing errors with GLM 5.3
Vibe Work had errors with GLM 5.3 and GLM 5.2. Mistral AI identified the issue and monitored the fix. The outage is resolved and lasted 24 minutes.
Mistral AI·Vibe Code Web and Vibe Work sessions may fail to start or resume
Vibe Code Web and Vibe Work sessions did not start or resume. Mistral AI reported that the issue is resolved. It lasted from 30 October 2026 to 2 November 2026.
Mistral AI·Vibe Code Web and Vibe Work sessions may fail to start or resume
Issue is solved.
Mistral AI·Mistral Small 4 Availability Degradation
Services have been stable for a number of hours - will continue to monitor
Follow Mistral AI
Your coding agent knows when Mistral AI is down, and tells you when a failure is theirs, not yours. You can also get Mistral AI 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 "mistral" and tell me if Mistral AI 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=mistral/feed subscribe https://outages.live/feed.xml?providers=mistralFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane