Voice Agent third-party provider instability (Google Gemini LLMs)

What to do

• Check whether you use Deepgram Voice Agent API: Downstream Providers. 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 10d 2h it lasted.

  Anything that failed between 2026-04-21 15:59 UTC and 2026-05-01 18:21 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

1. identifiedApr 21, 2026, 3:59 PM UTC

   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 becomes available or if we observe broader impact.

   provider

2. resolvedMay 1, 2026, 6:21 PM UTC

   This incident has been resolved.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.