Issues with downstream LLM provider in Voice Agent API
Feb 23, 17:58 UTCFeb 24, 14:28 UTC
Duration
20h 30m
Impact
Informational
Root cause
Not disclosed
Deepgram, 90 days
19 incidents
Affected
Voice Agent APIVoice Agent API: Downstream ProvidersDeepgram Public API (api.deepgram.com) - Voice Agent APIDeepgram Public API (api.deepgram.com) - Voice Agent API: Downstream Providers
Final update
The upstream Anthropic incident affecting Claude models has been resolved and error rates have returned to normal. Voice Agent functionality should now be operating as expected.
Timeline
- Resolved · Feb 24, 14:28 UTC
The upstream Anthropic incident affecting Claude models has been resolved and error rates have returned to normal. Voice Agent functionality should now be operating as expected.
- Identified · Feb 23, 17:58 UTC
There is an ongoing Anthropic outage that is affecting our Voice Agent. 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. The incident started at Feb 17, 2026 - 20:15 UTC
More from Deepgram
Full historyElevated errors for Flux streaming STT and Voice Agent sessionslasted 6h 33mElevated errors from authentication services at one datacenterlasted 55mElevated Latency and Errors for Batch STTlasted 2h 25mElevated 5xx Errorslasted 18h 59mElevated 503 errors for bath Flux TTS requestslasted 1h 31mElevated 503 errors for Aura-2 TTSlasted 11m