Deepgram Voice AI incident
Issues with downstream LLM provider in Voice Agent API
Resolved after 4 hours 1 minute, affecting Voice Agent API, on February 17, 2026.
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 14:40 UTC.
Affected components
Update timeline
- investigating Feb 17, 2026, 04:15 PM UTC
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 14:40 UTC.
- resolved Feb 17, 2026, 08:16 PM UTC
As of 10:00 UTC, the issues from OpenAI models is being resolved.
Your product runs on more than Deepgram Voice AI
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