Elevated errors for OpenAI model requests
xAI reported elevated errors for requests to OpenAI models. The issue affected Automations, Cloud Agents, CLI, Cursor IDE (Desktop), and third-party models. xAI resolved the incident after 34 minutes.
State
Resolved
Started
Lasted
34 min
Worst impact
Degraded
Timeline
3 updatesInvestigating
32 min 94%
Monitoring
2 min 6%
Updates
Times in UTCAs posted by xAI
This incident has been resolved.
We're seeing recovery and are continuing to monitor. We'll share another update soon.
We're investigating elevated errors affecting requests to OpenAI models. Some users may see failed or incomplete responses. Other models are unaffected and can be used in the meantime. We'll share another update as soon as we have more information.
Affected components
5xAI in the last 90 days
Full historyIncidents in 90 days
55
Days with an incident
33
Median duration
50 min
This incident
31% shorter than the median
Other xAI incidents
All incidentsxAI·Grok Bot is currently degraded
Grok Bot is degraded. xAI reports that the incident is resolved. The outage lasted 1 hour and 17 minutes.
xAI·Computer use in Grok Bot fails for users in a few regions.
Computer use in Grok Bot fails for users in a few regions. xAI identified the issue and applied a fix. The issue is resolved and the failure lasted 14 minutes.
xAI·composer-2.5 degraded
xAI reports degraded Composer 2.5 requests. The issue affected Automations, Bugbot, Cloud Agents, CLI, Cursor IDE (Desktop), and Cursor IDE (iOS). xAI resolved the issue after 50 minutes.
xAI·Degraded Performance - Grok Bot
Grok Bot had degraded performance. xAI reports that the issue is resolved. The outage lasted 1 hour and 15 minutes.
xAI·3 "Slow clones from GH due to Github degradation"
Slow clones from GitHub affected Bugbot and Cloud Agents. xAI reports that this incident is resolved. The incident lasted 1 hour and 12 minutes.
Follow xAI
Your coding agent knows when xAI is down, and tells you when a failure is theirs, not yours. You can also get xAI 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 "xai" and tell me if xAI 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=xai/feed subscribe https://outages.live/feed.xml?providers=xaiFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane