- Level
- confirmed
- Worst impact
- Degraded
- Components
- Voice Agent API
- Down Index
- 23of 100
What to do
Check whether you use Deepgram Voice Agent API. Check your stack
Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.Confirm your retries, queues and scheduled jobs caught up after the 4h 1m it lasted.
Anything that failed between 2026-02-17 16:15 UTC and 2026-02-17 20:16 UTC may need a replay.Subscribe to Deepgram's feed to hear about the next one first. RSS feed
https://down.guide/feed?provider=deepgram works in Slack (/feed subscribe), Discord feed bots and any RSS reader.
Updates from Deepgram 2
- 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.
provider
- resolved
As of 10:00 UTC, the issues from OpenAI models is being resolved.
provider
Reports count in aggregate; nothing about you is shown.
Corrections
None so far.
Something wrong on this page? Report an error or send us a note. Every fix is listed here.
Questions about DWN-1fef31713d
Is Deepgram still down?
No, this incident was resolved 2026-02-17 20:16 UTC. For Deepgram's live state, see https://down.guide/deepgram.
How long did it last?
4h 1m, from 2026-02-17 16:15 UTC to 2026-02-17 20:16 UTC, by the times Deepgram posted.
What was affected?
Deepgram named Voice Agent API.
What caused it?
Deepgram hasn't published a root cause. If it does, it shows here.
Where does this come from?
Deepgram's official status page, https://status.deepgram.com, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.