Deepgram Voice AI incident
Downstream third-party provider outage (OpenAI LLMs)
Deepgram Voice AI experienced a major incident on October 22, 2025 affecting Voice Agent API: Downstream Providers, lasting 7d 5h. The incident has been resolved; the full update timeline is below.
Affected components
Update timeline
- identified Oct 22, 2025, 05:45 PM UTC
A service degradation and partial outage began at approximately 16:44 UTC.
- identified Oct 22, 2025, 06:07 PM UTC
We're seeing elevated error rates (500 Internal Server Error) with OpenAI models in the Voice Agent API. Our team is actively investigating and communicating with OpenAI to find a path to resolution, and a path to mitigation in the short term. Our metrics show degraded service for 4o-mini, 4.1-mini, 4.1 nano, 4.1, and possibly other OpenAI models. We are continuing to monitor, investigate, and work with OpenAI to resolve. As a workaround, we recommend switching to a different model or provider.
- identified Oct 23, 2025, 06:20 PM UTC
We are continuing to see elevated error rates with OpenAI models in the Voice Agent API workflow. We have reached out and communicated with OpenAI to help resolve.
- identified Oct 24, 2025, 05:47 PM UTC
We are still continuing to see increased errors using the OpenAI models in the Voice Agent API workflow. We have reached out and communicated with OpenAI to help resolve.
- identified Oct 27, 2025, 11:31 PM UTC
We are still continuing to see increased errors using the OpenAI models in the Voice Agent API workflow. We have reached out and communicated with OpenAI to help resolve.
- resolved Oct 29, 2025, 10:02 PM UTC
As of 19:28 UTC OpenAI's LLMs are no longer returning 500 errors. We are still in conversation with OpenAI about what happened.