Issues with downstream LLM provider in Voice Agent API

Incident Report for Deepgram

Resolved

As of 10:00 UTC, the issues from OpenAI models is being resolved.
Posted Feb 17, 2026 - 20:16 UTC

Investigating

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.
Posted Feb 17, 2026 - 16:15 UTC
This incident affected: Deepgram Public API (api.deepgram.com) (Voice Agent API).