Issues with downstream LLM provider in Voice Agent API
Incident Lifecycle
Incident Timeline
Identified
We are seeing elevated error rates and latency when using NVIDIA Llama Nemotron Super 49B (llama-nemotron-super-49B) as the managed LLM in Voice Agent API. 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.
Apr 6, 2026 at 5:10 PM UTC
Was your business affected by this Deepgram outage?
Set up instant alerts for Deepgram — be the first to know about outages via email, Slack, Teams, or Discord.