Issues with downstream LLM provider in Voice Agent API

Event timeline

How this incident unfolded, from the official status page.

1. Resolved

   9 months ago

   Deepgram

   This incident has been resolved.

2. Investigating

   9 months ago

   Deepgram

   We are continuing to investigate this issue.

3. Investigating

   9 months ago

   Deepgram

   We are currently seeing elevated error rates from OpenAI models. To avoid downtime, please define multiple LLM providers (https://developers.deepgram.com/docs/voice-agent-llm-models#using-multiple-llm-providers) in your Voice Agent configuration, including at least one non-OpenAI think provider. The incident started at 16:30 UTC.