We started checking Deepgram on November 2, 2026, which is 5 days ago. Everything below covers that period, not the full 90 days a longer-tracked service would show.
Email me when Deepgram reports an incident on its status page, and again when it reports it resolved.
01
The last 24 hours
What happened most recently, on one time axis: our own probe readings by surface, how many people reported a problem, and what Deepgram's own status page declared. Below it, any public chatter we saw about Deepgram and the extra probe it triggered.
The last 24 hours on one axis: what our probes read for each surface we check, how many people reported a problem, and what Deepgram's own status page declared. Three records side by side; none of them changes another.
Our probes, web
Our probes, api (primary)
Unverified user reportsNo reports about Deepgram in the last 24 hours, which is not evidence that nothing is wrong.
Deepgram's status pageNo incident declared in the last 24 hours.
24h ago18h ago12h ago6h agonow
Each check cell is the worst reading across every region in that quarter hour: one region that did not answer colours the cell, never an average. An amber cell is a reading that answered, but at three times or more its 7-day median for three checks running: slow is not down, and we say which. A filtered reading stays neutral, because a refused check is not a failed check. Report bars count reports as submitted; we do not check who sent them, and they never change our reading. The status-page lane is Deepgram's own declaration, shown as they made it.
Third-party chatter, labeled
Public posts from the last hour that mention Deepgram next to an outage word (“down”, “outage”, “not working”). This is what other people said in public, collected by keyword: not something we measured, and not the user reports above. It never affects the verdict.
No matching public posts in the last hour from the sources we watch.
02
Checks passing by region
Checks passing is the checks that passed, divided by every check we attempted, per region. Not interpolated, not smoothed, and never computed for a region with zero recorded samples.
Region
Checks passing
Probes recorded
US-East
100.00%
447
US-West
99.71%
348
Europe
100.00%
317
Asia-Pacific
100.00%
193
Their declared record
Deepgram's own incident history, taken from their public status feed. This is their account of what happened, not our check reading.
Elevated errors from authentication services at one datacenterMinor incident
Oct 29, 2026, 3:17 PM UTC to Oct 29, 2026, 4:12 PM UTC (55 min)resolved
their latest update (Oct 29, 2026, 4:12 PM UTC): Between 15:17 and 15:45 UTC on October 29, an issue with authentication services at one of our US datacenters caused some API requests and Voice Agent sessions to fail with 5xx errors, and some transcription callbacks sent from that datacenter to carry an invalid Dg-Token header.…
Elevated Latency and Errors for Batch STTMinor incident
Oct 22, 2026, 7:27 PM UTC to Oct 22, 2026, 9:53 PM UTC (2h 25m)resolved
their latest update (Oct 22, 2026, 9:53 PM UTC): Between 19:27 and 21:53 UTC on October 22, some pre-recorded (batch) requests intermittently had elevated latency, and some timed out. This incident is resolved. All systems are operational.
Elevated 5xx ErrorsPartial outage
Oct 22, 2026, 4:00 PM UTC to Oct 23, 2026, 11:00 AM UTC (18h 59m)resolved
their latest update (Oct 23, 2026, 11:00 AM UTC): Between 16:00 and 17:09 UTC on October 22, some API requests returned 5xx errors because of an issue with authentication services at one of our datacenters. This incident is resolved. All systems are operational.
Elevated 503 errors for bath Flux TTS requestsMinor incident
Oct 14, 2026, 7:29 PM UTC to Oct 14, 2026, 9:00 PM UTC (1h 31m)resolved
their latest update (Oct 14, 2026, 9:00 PM UTC): This issue has been resolved.
Elevated 503 errors for Aura-2 TTSMinor incident
Oct 13, 2026, 5:58 PM UTC to Oct 13, 2026, 6:09 PM UTC (11 min)resolved
their latest update (Oct 13, 2026, 6:09 PM UTC): This issue has been resolved.
Elevated error rates for Flux TTSMinor incident
Oct 8, 2026, 2:58 AM UTC to Oct 8, 2026, 4:25 AM UTC (1h 27m)resolved
their latest update (Oct 8, 2026, 4:25 AM UTC): We experienced 2 bursts of elevated error rates between 02:58 - 03:16 UTC and 03:53 - 04:18 UTC. The issue is now resolved.
Elevated errors for Flux TTSMinor incident
Oct 5, 2026, 9:55 AM UTC to Oct 5, 2026, 11:55 AM UTC (2h)resolved
their latest update (Oct 5, 2026, 11:55 AM UTC): This incident has been resolved.
Elevated errors for Flux TTSMinor incident
Oct 3, 2026, 3:52 PM UTC to Oct 3, 2026, 5:52 PM UTC (2h 1m)resolved
their latest update (Oct 3, 2026, 5:52 PM UTC): This incident has been resolved.
Elevated API errorsMinor incident
Sep 30, 2026, 7:29 PM UTC to Sep 30, 2026, 7:39 PM UTC (10 min)resolved
their latest update (Sep 30, 2026, 7:39 PM UTC): Between 19:29 and 19:39 UTC, some API requests failed with HTTP 500 errors or timed out. This happened in two short bursts of about 1-2 minutes each, during a planned update to our authentication service. Services have recovered automatically and this issue is resolved.
Elevated Latency and Errors for Batch STT (US)Minor incident
Sep 28, 2026, 5:53 PM UTC to Sep 28, 2026, 5:53 PM UTC (0 min)resolved
their latest update (Sep 28, 2026, 5:53 PM UTC): An issue affecting some of our pre-recorded transcription servers slowed request processing. As requests took longer to complete, some customers saw elevated latency or received 429 errors. We identified and mitigated the issue, service has returned to normal.
Showing the 10 most recent of 50 incidents Deepgram has declared in the history we hold.
These entries are Deepgram's own declarations, taken from their public status feed, shown separately from our own check readings. Their page publishes what they choose to publish: an incident missing here means they did not declare one, not that nothing happened, and an incident here is their account, not our measurement. Neither record ever changes the other.
Deepgram's own status feed works, so its declared incidents are the record and our probe events are not listed or counted. Our check results by region are above, as a reading beside the statement.
Full detail on what a probe does and does not prove is in the methodology page.