outages.live
Live
Stability AIIncident · 2026-09-14 16:33 UTC

Investigating elevated 500s for generation endpoints

ResolvedOfficial update

🟢 This incident has been resolved. All systems are now operating normally. We apologize for any inconvenience this may have caused and thank you for your patience.

The latest update from Stability AI.

State

Resolved

Started

48 d ago

2026-09-14 16:33 UTC

Lasted

4 h 8 min

until 2026-09-14 20:41 UTC

Worst impact

Partial outage

Timeline

4 updates
16:3317:3518:3719:3920:41
Partial outageUpdate postedTimes in UTC

Investigating

19 min 8%

Identified

1 h 3 min 26%

Monitoring

2 h 45 min 67%

Updates

Times in UTC

As posted by Stability AI

Resolved2026-09-14 20:41 UTC

🟢 This incident has been resolved. All systems are now operating normally. We apologize for any inconvenience this may have caused and thank you for your patience.

Monitoring2026-09-14 17:55 UTC

✅ A fix has been implemented for the issue affecting API Platform, Brand Studio, and Stable Audio suite of products, and we are currently monitoring the results to ensure stability. We’ll continue to keep a close eye and provide a final update once we confirm everything is fully operational.

Identified2026-09-14 16:52 UTC

⚠️ We have identified the cause of the issue affecting the outages in our API Platform, Brand Studio, and Stable Audio suite of products. We are working on a fix and will provide an update shortly.

Investigating2026-09-14 16:33 UTC

🚧 We are currently investigating reports of elevated 500s affecting our generation API endpoints. Our engineering team is actively working to identify the root cause. We will provide another update as soon as we have more information. Thank you for your patience.

Stability AI in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

1

Days with an incident

1

Median duration

4 h 8 min

This incident

About the median

Follow Stability AI

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

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane