AssemblyAI incident
Expected responses from LLM Gateway using Claude models
Resolved after 3 hours 5 minutes, affecting LLM Gateway, on November 24, 2025.
We have continued to see good performance since releasing the earlier fix and are now marking this issue as resolved.
Affected components
Update timeline
- investigating Nov 24, 2025, 10:39 PM UTC
We are currently investigating an issue with LLM Gateway that is causing unexpected responses when using Claude models. This issue is not affecting LLM Gateway requests using other models. We are working to identify and resolve the root cause of these issues.
- identified Nov 25, 2025, 12:22 AM UTC
We have identified the root cause of this issue and are working to release a fix.
- monitoring Nov 25, 2025, 01:15 AM UTC
We have released a fix that has resolved the unexpected responses we were seeing when Claude models were used. Everything is working normally now, but we will continue to monitor traffic to ensure continued good performance.
- resolved Nov 25, 2025, 01:45 AM UTC
We have continued to see good performance since releasing the earlier fix and are now marking this issue as resolved.
Your product runs on more than AssemblyAI
Add the vendors you depend on and get one message when any of them reports trouble. Free for 3 vendors, no card.
Amazon Web Services