New AI Incident Response, Multi-Region Agents, and Custom-Domain Status Pages — May 2026
Monitor Features overview Vendor status Uptime & synthetic checks Certificate lifecycle Operate Incident management Live demo
By goal Replace your stack Why ServiceAlert Competitor comparisons Alternatives directory By signal Reliability hub   · Uptime rankings   · SLA compliance Outage map
Services
Check & scan SSL security grader Status checker DNS lookup Response time WHOIS lookup Calculators SLA calculator Downtime calculator Embed Status badges All tools →
Pricing
Guides Help center Uptime monitoring RUM & analytics Teams & shared monitors Developer API reference Status badges Learn Blog Outage reports FAQ Changelog
Dashboard

Deepgram Outage History

Uptime record, past incidents, and downtime history for Deepgram.

Checking current status...
65.9% uptime over 91 days
99.9% ✗ 99.5% ✗ 99% ✗ 95% ✗

90-Day Trend

Feb 25May 25

Monthly Uptime

Month Uptime Days Tracked Days with Issues
May 2026 84% 25 4
April 2026 40% 30 18
March 2026 77.4% 31 7
February 2026 60% 5 2

Uptime is calculated from daily worst-status snapshots. A day with any non-operational status counts as a day with issues.

Daily Status (Last 91 Days)

Feb 24 Today
Operational Degraded Partial Outage Major Outage Maintenance No Data

Incident History

May 2026
Degraded API Performance

Started: May 22, 5:59 PM

monitoring
Some API requests may have experienced increased latency and elevated error rates for approximately 30 minutes starting at 16:40 UTC on May 22, 2026. The issue has been identified and is being resolved.
May 22, 5:59 PM
Voice Agent third-party provider instability (ChatGPT 4o)
minor

Started: May 11, 4:35 PM

identified
We are currently observing elevated error rates from our downstream third-party provider, OpenAI specifically with the ChatGPT 4o model. Deepgram infrastructure, including our canaries, remains healthy.
May 11, 4:35 PM
April 2026
Voice Agent third-party provider instability (Claude Sonnet 4.5)
minor

Started: Apr 24, 5:45 AM

investigating
We are currently observing elevated error rates from our downstream third-party provider, Anthropic specifically with the Claude Sonnet 4.5 model. Deepgram infrastructure, including our canaries, remains healthy.
Apr 24, 5:45 AM
Voice Agent third-party provider instability (Google Gemini LLMs)
minor

Started: Apr 21, 3:59 PM

identified
We are currently observing elevated error rates from our downstream third-party provider, Google Gemini LLMs. Deepgram infrastructure, including our canaries, remains healthy; however, Voice Agent customers using bring-your-own (BYO) Gemini LLMs may experience degraded performance or intermittent failures on LLM think requests. We are monitoring the situation and tracking the provider’s status at https://aistudio.google.com/status. We will provide further updates as more information become...
Apr 21, 3:59 PM
Issues with downstream LLM provider in Voice Agent API

Started: Apr 17, 8:56 PM

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.
Apr 17, 8:56 PM
Outbound networking issues affecting STT PreRecorded API requests with callbacks, TTS Batch (HTTP) requests with callbacks, and Voice Agent API BYO 3rd party providers (LLM and TTS)
minor

Started: Apr 10, 5:27 PM

monitoring
A network infrastructure fix was implemented at 18:15 UTC and the behavior was immediately resolved. We are continuing to monitor carefully.
Apr 10, 7:09 PM
identified
A networking incident was identified which resulted in failed callbacks on STT PreRecorded API requests and TTS Batch requests. The issue also affected Voice Agent API sessions with LLM and TTS providers. We have identified a fix and are monitoring traffic. The source of the issue is being investigated.
Apr 10, 5:27 PM
Issues with downstream LLM provider in Voice Agent API
minor

Started: Apr 6, 5:10 PM

identified
We are seeing elevated error rates and latency when using NVIDIA Llama Nemotron Super 49B (llama-nemotron-super-49B) as the managed LLM in Voice Agent API. 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.
Apr 6, 5:10 PM
March 2026
Voice Agent API Degraded Service
minor

Started: Mar 20, 4:53 PM

investigating
There is an ongoing OpenAI 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.
Mar 20, 4:53 PM
Voice Agent API Degraded Performance
minor

Started: Mar 18, 4:48 PM

identified
We are continuing to work on a fix for this issue.
Mar 18, 5:19 PM
identified
There is an ongoing OpenAI 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.
Mar 18, 4:48 PM
View live status for Deepgram Browse all services