StackAI had 27 outages in the last 2 years totaling 6h 27m of downtime — averaging 1.1 incidents per month.
There were 27 StackAI outages since February 27, 2026 totaling 6h 27m of downtime. Each is summarised below — incident details, duration, and resolution information.
Document conversion and other document parsing subsystems relying on it are experiencing an outage. The StackAI team is working on a resolution.
**Anthropic Model Execution Errors** We are currently investigating an issue affecting Anthropic model execution on Stack AI. Customers using workflows backed by Anthropic models may see runs fail. Our team is working to restore Anthropic model availability. As a temporary workaround, some customers may be able to route compatible workflows through Anthropic models on Amazon Bedrock, though availability and behavior may differ depending on the model, region, and workflow configuration.
This incident has been resolved.
The issue has been identified and a fix is being implemented.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are investigating elevated errors on requests to Claude Sonnet 4.6 and Haiku 4.5. We will provide an update as soon as possible.
This incident has been resolved.
The issue has been identified and a fix is being implemented.
This incident has been resolved.
We are currently investigating this issue.
The issue has been identified and a fix is being implemented.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
We are currently investigating this issue.
This incident has been resolved.
We are currently investigating this issue.
We have identified the cause and a fix is being rolled out. As of 10:22 UTC, the remaining impact is limited to Claude Opus 4.1 and Fast Mode for Claude Opus 4.6.
A fix has been implemented and we are monitoring the results.
This incident has been resolved.
Type: Incident Duration: 3 days, 10 hours and 11 minutes May 6, 15:54:50 GMT+0 - Identified - The issue has been identified and a fix is being implemented. May 6, 15:29:02 GMT+0 - Investigating - We are currently investigating this issue. May 6, 16:51:13 GMT+0 - Resolved - This incident has been resolved. May 6, 16:32:36 GMT+0 - Monitoring - A fix has been implemented and we are monitoring the results.
Type: Incident Duration: 1 day, 22 hours and 40 minutes May 4, 14:08:19 GMT+0 - Identified - The issue has been identified and a fix is being implemented. May 4, 14:45:58 GMT+0 - Resolved - This incident has been resolved. May 4, 14:27:54 GMT+0 - Monitoring - A fix has been implemented and we are monitoring the results. May 4, 13:59:17 GMT+0 - Investigating - We are currently investigating this issue.
Type: Incident Duration: 4 days, 3 hours and 52 minutes May 4, 09:14:14 GMT+0 - Identified - We are continuing to work on a fix for this issue. May 4, 08:09:58 GMT+0 - Investigating - We are continuing to investigate this issue. May 4, 09:49:29 GMT+0 - Resolved - This incident has been resolved. May 4, 08:19:01 GMT+0 - Identified - The issue has been identified and a fix is being implemented. May 4, 09:23:04 GMT+0 - Monitoring - A fix has been implemented and we are monitoring the results. May 4, 08:09:37 GMT+0 - Investigating - We are currently investigating this issue.
Type: Incident Duration: 1 day, 6 hours and 50 minutes Apr 30, 01:51:16 GMT+0 - Resolved - This incident has been resolved. Apr 30, 01:20:26 GMT+0 - Investigating - We are currently investigating this issue. Apr 30, 01:34:02 GMT+0 - Monitoring - A fix has been implemented and we are monitoring the results.
Type: Incident Duration: 1 day, 2 hours and 49 minutes Apr 29, 13:47:45 GMT+0 - Investigating - We are currently investigating this issue. Apr 29, 14:01:16 GMT+0 - Monitoring - A fix has been implemented and we are monitoring the results. Apr 29, 14:14:34 GMT+0 - Resolved - The incident is resolved. The elevated error rate was between 05:37 PT / 12:37 UTC and 06:58 PT / 13:37 UTC.
Type: Incident Duration: 3 days, 21 hours and 57 minutes Apr 28, 17:51:36 GMT+0 - Identified - We have identified an issue resulting in elevated errors on the Anthropic API, as well as issues accessing Claude.ai, including log-in paths for Claude Code. We are working to resolve these issues, and will provide an update as soon as possible. Apr 28, 19:15:52 GMT+0 - Resolved - This incident has been resolved. Apr 28, 18:59:47 GMT+0 - Monitoring - We are seeing success rates across all services return to normal, and are monitoring closely to prevent any further issues. Impact occurred from 17:34–18:52 UTC. Apr 28, 18:33:55 GMT+0 - Identified - We are continuing to work to resolve the issues preventing users from accessing Claude.ai, and causing elevated authentication errors for requests to the API and Claude Code. Apr 28, 17:41:55 GMT+0 - Investigating - We are investigating an issue preventing users from reaching Claude.ai, and will provide an update as soon as possible.
Type: Incident Duration: 20 hours and 10 minutes Apr 28, 13:29:56 GMT+0 - Investigating - We are currently investigating this issue. Apr 28, 13:50:06 GMT+0 - Resolved - The incident has now been resolved. The timeline for the elevated errors was 6:22 PT / 13:22 UTC -> 6:39 PT / 13:39 UTC.
Type: Incident Duration: 2 days, 2 hours and 17 minutes Apr 25, 01:45:32 GMT+0 - Monitoring - We have identified an issue in Claude Code version 2.1.120 that causes a crash when resuming a prior session via the --resume or --continue flags. Auto-update will move affected clients back to 2.1.119 on next check, but you can always run `claude install 2.1.119`. Apr 25, 02:35:50 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 2 days, 10 hours and 34 minutes Apr 25, 01:35:55 GMT+0 - Investigating - We are investigating elevated errors for requests to Claude Opus 4.7. We will provide an update as soon as possible. Apr 25, 02:34:30 GMT+0 - Resolved - The issue affecting requests to Claude Opus 4.7 has been resolved. Impact occurred from 01:24–01:59 UTC. Apr 25, 02:15:52 GMT+0 - Monitoring - A fix has been deployed for Claude Opus 4.7 and we are seeing success rates at normal levels. We are continuing to monitor, and ensure no further recurrence.
Type: Incident Duration: 1 day, 15 hours and 1 minute Apr 24, 03:34:28 GMT+0 - Resolved - This incident has been resolved. Apr 24, 03:15:59 GMT+0 - Monitoring - A fix has been implemented and we are monitoring the results. Apr 24, 03:09:21 GMT+0 - Identified - The issue has been identified and a fix is being implemented. Apr 24, 02:55:59 GMT+0 - Investigating - We are continuing to investigate this issue. Apr 24, 02:55:26 GMT+0 - Investigating - We are currently investigating this issue.
Type: Incident Duration: 1 hour and 51 minutes Affected Components: Web Application Apr 16, 14:38:02 GMT+0 - Investigating - We are currently investigating this incident. Apr 16, 15:52:13 GMT+0 - Identified - Impact mitigated for prior platform service degradation. Monitoring performance. Apr 16, 16:28:47 GMT+0 - Monitoring - We implemented a fix and are currently monitoring the result. Apr 16, 16:29:20 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 1 hour and 17 minutes Affected Components: API, Web Application Apr 9, 16:22:45 GMT+0 - Identified - We pushed a fix and see a decrease in failure rates. We will continue our investigations to fully resolve this incident. Apr 9, 17:39:30 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 1 hour and 38 minutes Affected Components: API, Web Application Apr 9, 13:04:23 GMT+0 - Investigating - The StackAI platform is experiencing degraded avilability. We are currently investigating this incident. Apr 9, 13:23:11 GMT+0 - Identified - We are continuing to work on identifying the root cause for this incident. Apr 9, 13:58:40 GMT+0 - Monitoring - We implemented a fix and are seeing service recovery. We are continuing to monitor the situation. Apr 9, 14:42:15 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 4 hours and 45 minutes Affected Components: Web Application Apr 1, 19:54:06 GMT+0 - Monitoring - We are currently monitoring the situation and awaiting a provider fix. Apr 2, 00:39:12 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Duration: 27 minutes Affected Components: API, Web Application Mar 17, 15:08:02 GMT+0 - Identified - Some features of the Execute StackAI Project node may be degraded. We have identified the issue and are working on a fix. Mar 17, 15:34:40 GMT+0 - Resolved - This incident has been resolved.
Type: Incident Affected Components: API, Web Application Mar 17, 15:05:37 GMT+0 - Resolved - We have identified the issue and are pushing a temporary fix.
Type: Incident Duration: 1 hour and 4 minutes Affected Components: API, Web Application Mar 4, 13:30:19 GMT+0 - Identified - We are encountering an issue with our database provider. Mar 4, 13:43:19 GMT+0 - Monitoring - We have pinpointed the issue and are waiting to confirm resolution. Mar 4, 14:34:19 GMT+0 - Resolved - This incident has been resolved.