Is Deepgram down?
Right now
No. Deepgram is operational.
No incidents reported.
Read from status.deepgram.com · every 120s
For agents
proceed
Proceed.
GET upbutler.com/status/deepgram/status.agent.json
MCP: upstream_status {"service":"deepgram"}
Speech to text and voice agent APIs.
What Deepgram reports
Operational
Taken as is from Deepgram's own status page API. Incident titles and component names below are theirs.
Open status.deepgram.comUpButler's independent probe
There is no keyless endpoint of Deepgram that says anything useful, so UpButler does not probe it. To check your own Deepgram account, add a monitor with your key: it is yours alone and catches what a shared probe cannot.
Deepgram components
13 operational
Deepgram Public API (api.deepgram.com)
- Batch APIOperational
- Streaming APIOperational
- TTS APIOperational
- Voice Agent APIOperational
- Voice Agent API: Downstream ProvidersOperational
- DG Whisper CloudOperational
Documentation
- Developer DocumentationOperational
- Deepgram WebsiteOperational
On-Premise
- License ValidationOperational
- Usage APIOperational
Developer Console / Management APIs
- Developer ConsoleOperational
- API PlaygroundOperational
- Management APIsOperational
Deepgram incidents, last 90 days
6 finished incidents seen since UpButler started tracking on 2026-10-10. A typical one lasted 1 h 27 min; the longest 2 h 1 min.
| Started (UTC) | Incident | Impact | Lasted |
|---|---|---|---|
| Elevated error rates for Flux TTS | minor | 1 h 27 min | |
| Elevated errors for Flux TTS | minor | 2 h | |
| Elevated errors for Flux TTS | minor | 2 h 1 min | |
| Elevated API errors | minor | 10 min | |
| Elevated Latency and Errors for Batch STT (US) | minor | under a minute | |
| Elevated latency on Flux STT (US) | minor | 4 min |
Tell your outage from Deepgram's
Declare that your project depends on Deepgram. When one of your monitors fails while Deepgram has an incident that began around the same time, UpButler tags your incident "likely upstream" with their incident linked, says so in the alert and the AI report, and tells your on-call agent not to change code.
npx upbutler init finds the dependency from your env var names and packages. The catalog, dependencies and upstream-aware incidents are on every plan, including Free.
# upbutler.yaml
dependencies:
- deepgramcurl -s https://upbutler.com/status/deepgram/status.agent.json{
"schema": "upbutler.upstream-status/v1",
"service": "deepgram",
"verdict": "proceed",
"status": "operational",
"reason": "No incidents reported",
"retryAfterSec": null,
"incident": null,
"probe": null
}Questions
- Is Deepgram down right now?
- No. As of 2026-10-10 05:11 UTC, Deepgram is operational. This page reads the status again every 2 minutes.
- Where does this status come from?
- From Deepgram's own status page API at https://status.deepgram.com. UpButler reads it once for everyone (not once per visitor) every 120 seconds with conditional requests, and shows it unchanged: incident titles and component names are Deepgram's words.
- How can my agent or app check Deepgram status?
- Fetch https://upbutler.com/status/deepgram/status.agent.json: a small JSON document with a verdict (proceed, retry, fallback or pause) and retryAfterSec. No key is needed. The same answer is an MCP tool, upstream_status {"service":"deepgram"}, on https://upbutler.com/mcp/public.
- How do I know whether an outage is mine or Deepgram's?
- Add "deepgram" to the dependencies of your UpButler workspace. When one of your monitors fails while Deepgram has an incident that began around the same time, your incident is tagged "likely upstream" with their incident linked, and your on-call agent is told not to change code.
More in ai models and tooling
UpButler is not affiliated with Deepgram. Status and incident text belong to Deepgram and are read from their public status source; the probe result is UpButler's own measurement.