Is Retell AI down right now?

Retell AI uptime, last 90 days

Each bar is one UTC day, coloured by the worst state we saw on the official status page.

Recent Retell AI incidents

• Speech-to-speech calls failing due to a provider permission issue · 25 Oct 2026, 23:51 UTC

  resolved · 25 Oct 2026, 23:51 UTC

  Between 1:45 PM PDT Oct 24th and 4:50 PDT Oct 25th, a permission issue with openAI speech-to-speech model caused calls using speech-to-speech agents to fail or go silent. Access has been restored and speech-to-speech calls are working normally. Agents using the standard (cascading) setup were not affected.

  Read on status.retellai.com

• Call service disruption · 17 Sept 2026, 01:35 UTC · major

  postmortem · 17 Sept 2026, 02:30 UTC

  **Status: resolved.** All times are PST. ## Summary On September 16 at 5:37 PM we deployed a planned improvement to call handling. The improvement was not meant to be active yet, but the deployment turned it on, and it began to assign live calls to workers. This change unintentionally let two workers take the same call, and each worker then started it. The two starts interfered with each other, and the call failed. About 22% of calls were affected from 5:37 PM to 6:20 PM. We stopped the new workers, rolled the deployment back, and saw the issue resolve. ## Impact An affected call shows one of two signs: * The call ends as soon as it connects. The duration is zero or close to zero seconds. * The call connects. The agent does not speak. The call ends after a silence. A call that ran…

  resolved · 17 Sept 2026, 01:35 UTC

  The issue has been found and resolved. About 22% of calls may have been affected and been ended early, or have no audio. A postmortem will be published by EOD 09-17.

  investigating · 17 Sept 2026, 01:15 UTC

  We are aware of issues with some calls and are investigating.

  Read on status.retellai.com

• Web Calls and Phone Calls Disruption · 5 Sept 2026, 23:10 UTC · 1 h 9 min · major

  postmortem · 6 Sept 2026, 03:35 UTC

  ### Summary On September 5, a rare race condition in our custom LLM call path caused call scheduling queues across our fleet to stall. Because the failure also made containers appear underutilized, autoscaling never triggered. Between roughly 10:00 and 16:00 PST the impact grew until most containers were stuck and new calls could not be placed. ### Impact * **Web calls, outbound calls, and inbound calls** were all affected. * Inbound calls were the least affected, since they hold the highest priority in our scheduling queue. * Peak impact occurred around 16:00 PST. ### Root Cause The failure required a specific sequence of events: 1. **Stalled initialization.** If a call ended before its custom LLM websocket was established, the call's initialization never completed. The scheduling q…

  resolved · 6 Sept 2026, 00:19 UTC

  The issue affecting web, outbound, and inbound calls has been resolved. All calling services are operating normally.

  investigating · 5 Sept 2026, 23:10 UTC

  Starting at 4:10 PM, web and outbound calls began failing, while inbound calls experienced connection delays. We are actively investigating the issue and will provide an update as soon as more information is available.

  Read on status.retellai.com

• Some inbound calls failing to connect · 7 Aug 2026, 21:55 UTC · 26 min · minor

  resolved · 7 Aug 2026, 22:22 UTC

  This incident has been resolved.

  monitoring · 7 Aug 2026, 22:16 UTC

  Service should be back to normal. We are continuing to monitor to ensure stability.

  identified · 7 Aug 2026, 21:55 UTC

  Due to issues with an upstream provider, we are seeing connection issues for a portion of inbound calls. This is not widespread.

  Read on status.retellai.com