Previous incidents

The issue is resolved and all services have returned to normal.

The issue has been resolved upstream and documentation is available once again, we'll continue monitoring to ensure stability.

BYO SIP registration has been re-enabled during scheduled maintenanc and we were able to successfully place outbound calls

There will be reactive maintenance on SIP outbound dialing infrastructure, US region

Status: Scheduled

What is affected: Our SIP infrastructure provider will upgrade the web server/API that controls outbound dialing, as part of remediating the root cause of today's incident. Inbound calls are not affected.

When: Tuesday, October 6, 21:00–21:15 PT (04:00–04:15 UTC, Oct 7)

What to expect: This work is not expected to be customer-impacting or noticeable. Outbound calls may briefly stall duri...

The issue has been resolved and calls are completing as expected.

New number provisioning has been restored as of 3:00 AM PT today. Creating Vapi phone numbers is working normally again. Thank you for your patience.

Our login provider has recovered and the Vapi dashboard is fully operational again.

On Sunday, September 13, 2026, from 8:24 a.m. to 10:55 a.m. Pacific Time, Vapi Chat experienced a service disruption on both daily and weekly channels.

During this period, requests to /session and /session/{id} timed out or returned HTTP 504 (Gateway Timeout) and 500 (Internal Server Error) responses, affecting chat session creation, retrieval, and management.

Service was restored at 10:55 a.m. Pacific Time. All other services, including voice calls, were unaffected on both channels.

Incident Report available at https://drive.google.com/file/d/1ORxSZb8NYgVlmPoqnUEdTmlIua3NSl_k/view

We are investigating an issue affecting webhook behavior for a subset of web calls. Calls using private credentials and dashboard call flows are unaffected. We are deploying a fix and will provide another update once validation is complete.

Our documentation vendor has resolved their issue and Vapi documentation is now fully available.

We have identified the root cause of this issue and implemented a fix. We've seen a full recovery across our systems and are continuing to monitor for any regressions.