LiveKit: Elevated inference errors — US East
Timeline of updates
- investigating
We are investigating a period of elevated error rates and timeouts (08:47:00-08:53:35 UTC) for LiveKit Inference requests in our US East region. Service has since recovered and inference requests are completing normally. We are continuing to investigate the cause and confirm the full scope and duration of impact. A further update will follow.
- resolved
Between 08:47 and 08:54 UTC, the service that routes LLM, STT and TTS requests through LiveKit Inference in our US East region was unavailable, causing inference requests from agents in that region to fail or time out. Sessions depending on those responses may have degraded or ended prematurely. Replacement capacity came online at 08:54 UTC and request volumes returned fully to normal levels by 09:02 UTC. We have confirmed no further impact since then. The cause was a loss of capacity during automated infrastructure maintenance. We have identified fixes to prevent a recurrence.
Archive proof
Rewindex commits each version of an incident it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert. That proves this record existed by then and has not been changed since, by anyone, Rewindex included.
How the archive is checked, and what it cannot prove.
First version captured 17:03 UTC
In the 2026-10-19 checkpoint, timestamped by FreeTSA and DigiCert on Oct 20, 00:41 UTC. Record hash
13d0139a3ddf340c…
Impact, status and times are the vendor’s own, as last archived. View on stspg.io (opens in new tab).