Deepgram: Issues with downstream LLM provider in Voice Agent API
Anthropic outage, Feb 4, 2026 · 8 vendors, 8 incidents
Deepgram’s incident blames Anthropic as the cause. (hop 1, posted +13 min vs Anthropic’s own post)
“…0 UTC / 8:20 PT and 16:55 UTC / 8:55 PT We are currently seeing elevated error rates from Anthropic models. To avoid downtime, please define multiple LLM providers (https://developers.deepgram.com/doc…”
Swipe sideways to see the whole diagram.
Mermaid source
flowchart LR
root["Anthropic<br/>posted 16:39 UTC"]:::root
h1["Within an hour<br/>2 vendors, 2 blamed Anthropic<br/>Cursor, Deepgram"]:::blames
root --> h1
me["Deepgram (this incident)<br/>posted +13 min"]:::me
h1 --- meFull event: timeline, evidence and all vendors →
Detected automatically from incidents that started together and named the same provider. A link means one vendor’s incident named another, not a confirmed cause.
Affected components: Deepgram Public API (api.deepgram.com) - Voice Agent API: Downstream ProvidersVoice Agent API: Downstream ProvidersDeepgram Public API (api.deepgram.com) - Voice Agent APIVoice Agent API
Timeline of updates
- identified
We are currently seeing elevated error rates from Anthropic 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-Anthropic think provider. The incident started at 16:34 UTC
- resolved
The downstream provider indicated the issue was resolved. There was an outage between 16:20 UTC / 8:20 PT and 16:55 UTC / 8:55 PT
Impact, status and times are the vendor’s own, as last archived. View on stspg.io (opens in new tab).