Live

[GLOBAL][AI & Machine Learning] - AI Endpoint Incident Notification

Partial outageOfficial update
0

The AI Endpoint component of OVHcloud AI & Machine Learning has a partial outage. OVHcloud reports that the service was fully restored at 07:12 UTC on 20/11/2026 and that monitoring is in place. The incident started at 06:25 UTC.

State

Monitoring

Started

Ongoing for

2 h 21 min

Worst impact

Partial outage

Timeline

2 updates
06:5307:2908:0408:3909:14
Partial outageUpdate postedTimes in UTC

Investigating

1 h 36 min 69%

Monitoring

44 min 31%

Updates

Times in UTC

As posted by OVHcloud

Monitoring

We would like to inform you that our service has been fully restored as of 20/11/2026 07:12 UTC. Monitoring is still in place to ensure long-term stability. Please find the details of this incident below : Start time : 20/11/2026 06:25 UTC Impacted Service(s) : AI Endpoints service was temporarily unavailable. Customers Impact : Customers may have experienced API errors when calling AI Endpoints models. We apologize for any inconvenience caused and appreciate your understanding.

Investigating

We are currently investigating an incident affecting our AI & Machine Learning offering, which is causing temporary availability issue on AI Endpoint . Here are some supplementary details : Start time : 20/11/2026 06:25 UTC Impacted Service(s) : The AI Endpoints is temporarily unavailable. Customers Impact : Customers may temporarily experience unavailability when using the AI endpoints. Ongoing Actions : Our teams are investigating to determine the origin of the incident and fix it. We will keep you updated on the progress and resolution. We apologize for any inconvenience caused and appreciate your understanding.

Affected components

1
AI & Machine Learning || AI Endpoint

OVHcloud in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

180

Days with an incident

90

Median duration

1 h 45 min

This incident

1.3× the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

7 days
median 1 h 45 min
90 days agoToday

Other OVHcloud incidents

All incidents

OVHcloud·[EU/US/APAC][Infrastructure] - Backbone incident notification

Some links between Europe and APAC and between North America and APAC have packet loss on the OVHcloud backbone infrastructure. OVHcloud reports that it identified the cause as a network equipment issue. OVHcloud teams are working to restore service.

Partial outage

OVHcloud·[Global][Identity, Security & Operations] - Logs Data Platform incident notification

We would like to inform you that the incident affecting our Identity, Security & Operations offering has now been resolved. Please find the details of this incident below : Start time : 19/11/2026 17:31 UTC End time : 19/11/2026 20:50 UTC Impacted Service(s) : The OpenSearch API of the Logs Data Platform service was temporarily unavailable. Customers Impact : Customers were temporarily unable to query or access their logs through the OpenSearch API. Log ingestion remained unaffected. Root Cause : This incident was caused by a network equipment issue. We thank you for your understanding and patience throughout this incident.

Resolved

OVHcloud·[US-WEST-OR][Storage] - Cloud Archive incident notification

The Cloud Archive service in the US-WEST-OR region has an increased error rate. Storing or retrieving archived data may fail. OVHcloud reports the root cause as identified.

Partial outage

OVHcloud·[BHS-CHI][Infrastructure] - Backbone incident notification

OVHcloud reports increased latency on the Backbone link between BHS and CHI. OVHcloud states that the incident is resolved. The incident lasted from 19:41 UTC to 20:38 UTC.

Resolved

OVHcloud·[Global][Collaborative Solutions] - Zimbra incident notification

OVHcloud Zimbra mailbox access, webmail, email delivery, and operations had a partial outage. OVHcloud reports that the incident is resolved. It lasted 3 hours and 4 minutes, from 14:30 to 17:34 UTC.

Resolved

Follow OVHcloud

Your coding agent knows when OVHcloud is down, and tells you when a failure is theirs, not yours. You can also get OVHcloud 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 "ovhcloud" and tell me if OVHcloud 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=ovhcloud
Slack
/feed subscribe https://outages.live/feed.xml?providers=ovhcloud

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane