outages.live
Live

Mistral AI

Mistral AI is operational

Checked 2 min ago Operational

History

90 days agoToday

Incidents in 90 days

23

Days with an incident

18

Median duration

35 min

Longest incident

4 h 49 min

Components

16
Completion API Operational
90 days agoNo incidentsToday
Embedding API Operational
90 days agoNo incidentsToday
OCR API Operational
90 days agoNo incidentsToday
Agents API Operational
90 days agoNo incidentsToday
Conversations API Operational
90 days agoNo incidentsToday
Fine-Tuning API Operational
90 days agoNo incidentsToday
Audio API Operational
90 days agoNo incidentsToday
Integrations API Operational
90 days agoNo incidentsToday
Files API Operational
90 days agoNo incidentsToday
Batch API Operational
90 days agoNo incidentsToday
Workflows API Operational
90 days agoNo incidentsToday
Console Operational
90 days agoNo incidentsToday
Prompts API Operational
90 days agoNo incidentsToday
Responses API Operational
90 days agoNo incidentsToday
Skills API Operational
90 days agoNo incidentsToday
Vibe Operational
90 days agoNo incidentsToday

Past incidents

Provider status pageTimes in UTC

Oct 30, 2026

Duration4 h 49 min15:11 to 20:01Vibe Code Web and Vibe Work sessions may fail to start or resumeDegraded

Issue is solved.

Oct 23, 2026

Duration2 h 50 min09:21 to 12:11Mistral Small 4 Availability DegradationDegraded

Services have been stable for a number of hours - will continue to monitor

Oct 19, 2026

Duration37 min16:23 to 17:00Vibe Code Web sessions failingDegraded

Vibe Code Web sessions were failing between 16:15 and 16:21 UTC due to capacity issues.

Duration1 h 12 min14:20 to 15:32Vibe is experiencing high latency with GLM 5.3Degraded

The issue causing elevated latency and errors for Vibe sessions using GLM 5.3 has been resolved. Service performance has returned to normal, and we are continuing to monitor.

Oct 16, 2026

Duration26 min07:47 to 08:13Some Vibe Code Web sessions are terminating unexpectedly or are unable to startPartial outage

This incident has been resolved. Vibe Code Web sessions are now starting and running normally.

Oct 13, 2026

Duration27 min07:39 to 08:06Fixed errors on workflow APIsDegraded

Fixed the root cause.

Oct 12, 2026

Duration35 min12:45 to 13:19Total Unavailability on ML4 GLM5.2 and GLM5.3Partial outage

GLM 5.2, GLM 5.3, and Mistral Large 4 were unavailable from 2026-10-12 12:48:31 UTC to 2026-10-12 13:01:10 UTC.

Oct 8, 2026

Duration2 h 55 min12:14 to 15:09Some Vibe Code Web sessions are terminating unexpectedlyDegraded

The issue causing some Vibe Code Web sessions to terminate unexpectedly has been resolved.

Sep 29, 2026

Duration2 h 46 min12:48 to 15:34Elevated error rate on some of our servicesMajor outage

All services are now back to normal

Duration29 min07:37 to 08:06Audio speech to text degradationDegraded

The audio STT model degradation has been resolved.

Sep 22, 2026

Duration38 min09:16 to 09:53Skill creation and updates unavailablePartial outage

We have deployed a fix restoring skill creation and updates in Le Chat and AI Studio.

Duration31 min00:42 to 01:14Mistral OCR 4 is degradedDegraded

We've rolled out a fix for the degradation and availability has recovered

Sep 21, 2026

Duration19 min22:07 to 22:26[FIRING:1] mistral-small-2603 decode pods stuck rolling outDegraded

The incident has been resolved.

Duration2 h 44 min15:50 to 18:34Availability drop for Mistral OCR 4Degraded

The incident has been resolved.

Sep 20, 2026

Duration30 min09:23 to 09:53Vibe Work - Degraded output qualityMajor outage

We’ve identified the issue and rolled out a fix.

Sep 18, 2026

Duration1 h 13 min16:01 to 17:14Vibe Code Web model is experiencing failures in some existing sessionsDegraded

The incident has been resolved

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.

Prompt
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.

RSS
https://outages.live/feed.xml?providers=mistral
Slack
/feed subscribe https://outages.live/feed.xml?providers=mistral

Go from tracking outages to fixing production issues with Polylane.

Try Polylane