Issues with downstream LLM provider in Voice Agent API

Incident Report for Deepgram

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.
Posted Apr 06, 2026 - 17:10 UTC
This incident affects: Deepgram Public API (api.deepgram.com) (Voice Agent API: Downstream Providers).