Incidents and maintenance reported on status page for Vapi https://status.vapi.ai/ en https://status.vapi.ai/maintenance/1108915 Fri, 30 Oct 2026 15:52:38 -0000 https://status.vapi.ai/incident/1108915#9f3c5a145f89be64302bafea699b2db9ed208a96590abd1b1ea75613c25de34a Maintenance We will be performing scheduled maintenance on the SIP infrastructure to ensure performance and reliability. Connected calls may be interrupted for 5-10 minutes. However, the platform will be able to take new calls throughout the maintenance period. https://status.vapi.ai/maintenance/1095047 Tue, 20 Oct 2026 09:07:49 -0000 https://status.vapi.ai/incident/1095047#c482e99c82b867a2f76b2f03754dd6d6477a01d0f98bc5e4130b5cb53cfb0c83 Maintenance Maintenance completed https://status.vapi.ai/maintenance/1095047 Tue, 20 Oct 2026 09:07:49 -0000 https://status.vapi.ai/incident/1095047#873658c934e347b6e63d5a2e75dd606559184a1d6cb23368bfc95534c522276c Maintenance Australia SBC was rebooted successfully with less than a minute of interruption. https://status.vapi.ai/maintenance/1095049 Tue, 20 Oct 2026 04:15:07 -0000 https://status.vapi.ai/incident/1095049#94977996a8fb8236b67b3ce43880d704cc3778e6e22011f923c5cad99634a092 Maintenance Maintenance completed https://status.vapi.ai/maintenance/1095049 Tue, 20 Oct 2026 04:15:07 -0000 https://status.vapi.ai/incident/1095049#603ae74c81349637166c0e6f91b798931ea4de5a0f93793a08030193ca8d5180 Maintenance SIP maintenance complete with limited to no impact on calls. We will continue to monitor for the next two hours to confirm. https://status.vapi.ai/maintenance/1095049 Tue, 20 Oct 2026 04:15:00 -0000 https://status.vapi.ai/incident/1095049#cbdb2f6168e250e01081f2d350b4706b137c8bd5f4bebac69069b7c5fe42bffa Maintenance Maintenance ended https://status.vapi.ai/maintenance/1095049 Mon, 19 Oct 2026 22:22:02 -0000 https://status.vapi.ai/incident/1095049#23728b9dc4648e5d85ecfdc4fb7f4f44e397d548fd9e1c6799c9066573757956 Maintenance We will be installing SIP monitoring probes to the SIP infrastructure which will disrupt in progress calls for 5 minutes. https://status.vapi.ai/maintenance/1095047 Mon, 19 Oct 2026 22:19:05 -0000 https://status.vapi.ai/incident/1095047#1578c46c585f1078855b3935c7803a34e27caf092f5f02bf30a612fc4445a0d3 Maintenance Calls will be disrupted for approximately 5 minutes due to an SBC restart. We will monitor calls once the server is restarted. https://status.vapi.ai/maintenance/1091231 Mon, 19 Oct 2026 05:00:00 -0000 https://status.vapi.ai/incident/1091231#6cd29ad1976555000f80ea4a7a4905f37476c53e3bad96054ac82cb0346315d1 Maintenance Maintenance completed https://status.vapi.ai/incident/1092161 Fri, 16 Oct 2026 15:01:33 -0000 https://status.vapi.ai/incident/1092161#249fdb7036e56aa02990d76dd4ac5771069545cb3e55e31ccb025116a6435568 Incident The issue is resolved and all services have returned to normal. https://status.vapi.ai/incident/1092161 Fri, 16 Oct 2026 14:41:00 -0000 https://status.vapi.ai/incident/1092161#b35df4cb5c5cd8db1bb01d70961ce4b30ccf6900789b0e3724be97f0a97a649a Incident We've found the root cause and starting to see recovery. Daily API success rate is increasing and dashboard is loading. We will continue to monitor. https://status.vapi.ai/incident/1092161 Fri, 16 Oct 2026 14:35:18 -0000 https://status.vapi.ai/incident/1092161#022e91c178a659fa675f7d811521b6ca4bb8fd6ae4a78e369896f4c1be92ec52 Incident We have identified the impact is specific to API on Daily. Call creation is a separate service which is not impacted. https://status.vapi.ai/incident/1092161 Fri, 16 Oct 2026 14:12:30 -0000 https://status.vapi.ai/incident/1092161#c3675f3578008012ed6903e9a77fd9b85d7392b1ab7fe52442762f312836b440 Incident Vapi dashboard is currently not loading. We are investigating the incident and affected services. https://status.vapi.ai/maintenance/1091231 Thu, 15 Oct 2026 15:44:39 -0000 https://status.vapi.ai/incident/1091231#7ed06b130b1d8d7a3684fa9b73b02a9cf7b3e6e9ebd74190b664b6e642c4cc36 Maintenance We will be updating servers to increase resiliency. During this maintenance period, some in-progress calls may be disrupted. However new calls will still be answered. https://status.vapi.ai/maintenance/1072370 Wed, 14 Oct 2026 06:00:35 -0000 https://status.vapi.ai/incident/1072370#36aa6ac1dca7d6bc7c137fccdf755ce0db0e3073a35665645cefad9d1b12731e Maintenance Maintenance completed https://status.vapi.ai/maintenance/1088586 Tue, 13 Oct 2026 04:25:12 -0000 https://status.vapi.ai/incident/1088586#f3d9b021e4eef01e1612ef9c3697c33c503e15b37c68237350e1a5df7f976c3a Maintenance Maintenance completed https://status.vapi.ai/maintenance/1088586 Tue, 13 Oct 2026 04:25:12 -0000 https://status.vapi.ai/incident/1088586#87401ac2ac514ed07165849c45bdaa6c7bf5bda5d2ac4872cdcc330b505ea607 Maintenance The monitoring server was successfully upgraded. We will continue to monitor. PCAP files are available for registered calls. https://status.vapi.ai/maintenance/1088586 Tue, 13 Oct 2026 00:56:00 -0000 https://status.vapi.ai/incident/1088586#fbbfdcec79424c9a044d28d6ddd0639fff24c3c29fbb0faac61a625778bddc77 Maintenance We are doing an emergency upgrade to add capacity for the SIP monitoring server. During the period PCAP files will not be saved. https://status.vapi.ai/incident/1088347 Mon, 12 Oct 2026 18:03:26 -0000 https://status.vapi.ai/incident/1088347#4a89fd46f0f229edf15525b15b8ce5115f6d887b376eeca31a343ccd867e1b6d Incident The issue has been resolved upstream and documentation is available once again, we'll continue monitoring to ensure stability. https://status.vapi.ai/incident/1088347 Mon, 12 Oct 2026 17:54:29 -0000 https://status.vapi.ai/incident/1088347#cdc4da7fb62bb00edf5984d6fa0b25154a9f34ff17550c36028aedbb85239715 Incident Our documentation is unavailable due to an upstream outage, we're tracking status closely ([Fern](https://status.buildwithfern.com/) -> [Vercel](https://www.vercel-status.com/) -> [GitHub](https://www.githubstatus.com/)) and will notify once service is restored https://status.vapi.ai/maintenance/1087717 Mon, 12 Oct 2026 04:25:32 -0000 https://status.vapi.ai/incident/1087717#6eea5069dcfd4de797b35aa31fd0e5442be6059a8f947f6db7fdea489c639023 Maintenance Maintenance completed https://status.vapi.ai/maintenance/1087717 Mon, 12 Oct 2026 04:25:32 -0000 https://status.vapi.ai/incident/1087717#e9a5b5645324596af5a05abb7f09600ed056a44c8c0c37318bc8ff3d46431750 Maintenance Outbound API server upgrade was successful. Outbound call is operational. We will continue to monitor for the next 2 hours. https://status.vapi.ai/maintenance/1087717 Mon, 12 Oct 2026 03:05:56 -0000 https://status.vapi.ai/incident/1087717#2627492f39c7744cf75ebdd0e00f9af6c73abb394319d2ad817cff2bd3381813 Maintenance We will be upgrading the API server related to outbound calling. Outbound calling will be unavailable for approximately 30 minutes for new outbound call requests. We will validate for the remainder of the window to confirm calls are connecting normally, and update this page when connectivity returns and maintenance is complete. https://status.vapi.ai/maintenance/1108911 Sun, 11 Oct 2026 04:15:00 -0000 https://status.vapi.ai/incident/1108911#37846dfeed54a4c3f8d9c63017578b8a864755c265e4ee1e9d8195f7eccfa0db Maintenance Maintenance completed https://status.vapi.ai/maintenance/1108911 Sun, 11 Oct 2026 04:00:00 -0000 https://status.vapi.ai/incident/1108911#c43406f975154bffb4db1d506e3a1024efacf72459910016fe303bbbee681352 Maintenance We will be performing scheduled maintenance on the SIP infrastructure to ensure performance and reliability. Connected calls may be interrupted for 5-10 minutes. However, the platform will be able to take new calls throughout the maintenance period. https://status.vapi.ai/maintenance/1086357 Sat, 10 Oct 2026 04:15:01 -0000 https://status.vapi.ai/incident/1086357#21777561ed2216f2966535e26490b2ef1fd9be8b5f0c94276d334a007503178a Maintenance Maintenance completed https://status.vapi.ai/maintenance/1086357 Sat, 10 Oct 2026 04:15:01 -0000 https://status.vapi.ai/incident/1086357#c0c3b2a5960e2ee9929e95d8d5f382e418486b1ffba69a4675a96acfd7196de5 Maintenance Upgrade was successful. The API was unavailable for approximately one minute and is successfully sending outbound calls. Will continue to monitor health for the next 2 hours. https://status.vapi.ai/maintenance/1086357 Fri, 09 Oct 2026 23:51:50 -0000 https://status.vapi.ai/incident/1086357#7d95c92ca26c86cbd3bc9add11862ff17ce4d5ebc31e88b95ba049214cc353e3 Maintenance What is affected: Outbound calling When: Tonight, Friday, October 9, 21:00–21:15 PT (04:00–04:15 UTC, October 10). What to expect: Non-Campaign Outbound calls may briefly stall or fail to connect during the patch over a 5-10 minute period. We will validate the remainder of the window to confirm calls connect normally, and update this page when connectivity returns and maintenance is complete. Action needed: None. https://status.vapi.ai/incident/1085254 Fri, 09 Oct 2026 14:47:07 -0000 https://status.vapi.ai/incident/1085254#9652b438b927a265e845d7b8f14a58e04608c75d9930c9d1803060b8ea413008 Incident BYO SIP registration has been re-enabled during scheduled maintenanc and we were able to successfully place outbound calls https://status.vapi.ai/maintenance/1085325 Fri, 09 Oct 2026 04:15:17 -0000 https://status.vapi.ai/incident/1085325#910abc401a48d80b6dfe2516cc249892fcd5114ee4e95800a28b3b5a3de538a7 Maintenance Maintenance completed https://status.vapi.ai/maintenance/1085325 Fri, 09 Oct 2026 04:15:17 -0000 https://status.vapi.ai/incident/1085325#83ba94286ff49183874fdd5a6ab3970f1d84a6782806a14d31af00ace9c58285 Maintenance Maintenance ended. BYO SIP trunk registration has been restored. https://status.vapi.ai/incident/1085254 Thu, 08 Oct 2026 20:08:00 -0000 https://status.vapi.ai/incident/1085254#d845a3d5f5d9ae03a04dd4b19d7c5dc62736cf02d06354cf6f507e00bd9f18af Incident Cause Identified: applying a vendor software update to re-enable the functionality. The patch will be deployed during the dedicated maintenance window 21:00–21:15 PT on October 8 (04:00–04:15 UTC on October 9). https://status.vapi.ai/maintenance/1085325 Thu, 08 Oct 2026 20:04:17 -0000 https://status.vapi.ai/incident/1085325#48ddaf92546f17b7116a105d06d255b8dbb8ddc34928e1cf732b8459dbd0862a Maintenance Users report error when registering BYO SIP trunk. A recent upgrade depreciated the functionality. Applying a vendor software update to re-enable the functionality. https://status.vapi.ai/incident/1085254 Thu, 08 Oct 2026 18:57:00 -0000 https://status.vapi.ai/incident/1085254#999c0e939932d4f479f78dd6c3b3110f0c5aecf8c835147dc64d2fd71922b692 Incident We're continuing to investigate failures when creating BYO SIP trunks. Next update within 30 minutes, or sooner if the status changes. https://status.vapi.ai/incident/1085254 Thu, 08 Oct 2026 18:27:00 -0000 https://status.vapi.ai/incident/1085254#105aa1370714ed763a07ad546cfb7e54bf43a70fb53f9db23ffc34b49fe5f5a0 Incident We're seeing failures when creating BYO SIP trunks. Existing trunks and calls on them aren't affected. Our team is actively investigating and we'll post an update as soon as we have more information. https://status.vapi.ai/maintenance/1084518 Thu, 08 Oct 2026 04:10:38 -0000 https://status.vapi.ai/incident/1084518#2c7ace91f3857b531016d6ae87426ce80eb30b1c32591f2d8dfcbb1b8d229b5d Maintenance Maintenance completed https://status.vapi.ai/maintenance/1084518 Thu, 08 Oct 2026 04:10:38 -0000 https://status.vapi.ai/incident/1084518#950ed4100f969f70addeed6d24591649eff10b2c7954ec0f3a726fc00edd1d01 Maintenance The patch to the outbound server was applied and tested in approximately 5 minutes with no downtime. We will continue monitoring over the next few hours. https://status.vapi.ai/maintenance/1084518 Wed, 07 Oct 2026 23:56:12 -0000 https://status.vapi.ai/incident/1084518#df009c08e0554dc5ab91dba080b387630471dc6266160ea958a74dc66bb44169 Maintenance Status: Scheduled What is affected: We will apply a software patch to the web server/API that controls outbound dialing through our US SIP infrastructure. When: Tonight, Wednesday, October 7, 21:00–21:15 PT (04:00–04:15 UTC, Thursday, October 8). What to expect: Non-Campaign Outbound calls may briefly stall or fail to connect during the patch over a 5-10 minute period. We will validate for the remainder of the window to confirm calls are connecting normally and update this page when connectivity returns and maintenance is complete. Action needed: None. https://status.vapi.ai/maintenance/1083557 Wed, 07 Oct 2026 04:32:22 -0000 https://status.vapi.ai/incident/1083557#d74fb5998e8f4e1d927b8eda0e7c73bbc4a64b343da1d7ab22c5982ab9f55b89 Maintenance Maintenance completed https://status.vapi.ai/maintenance/1083557 Wed, 07 Oct 2026 04:32:22 -0000 https://status.vapi.ai/incident/1083557#9d2667959550b7929ec42faec9a36e2c2ae870f0bd17b9f2fb37b9f2a2c1ab49 Maintenance Maintenance was successfully complete. We verified that all servers are operating normally. https://status.vapi.ai/maintenance/1083557 Wed, 07 Oct 2026 00:16:59 -0000 https://status.vapi.ai/incident/1083557#c8bcf8a1c7dfe89b1e83282acbbd0aabe0d0a3c9db6e3a02ada132d171950499 Maintenance This maintenance period is a reactive patch, as our SIP infrastructure provider will upgrade the web server/API that controls outbound dialing to remediate the root cause of today's incident. Inbound calls are not affected. When: Tuesday, October 6, 21:00–21:15 PT (04:00–04:00 UTC, Oct 7) What to expect: This work is not expected to be customer-impacting or noticeable. Outbound calls may briefly stall during the window; any impact should last less than 15 minutes. Action needed: None https://status.vapi.ai/incident/1083466 Wed, 07 Oct 2026 00:09:00 -0000 https://status.vapi.ai/incident/1083466#54a72f4cff0a63999a8bad1b03ab135978332339e84a856b777208df57dafe29 Incident 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 during the window; any impact should last less than 10 minutes. Action needed: None https://status.vapi.ai/incident/1083466 Tue, 06 Oct 2026 21:29:00 -0000 https://status.vapi.ai/incident/1083466#4c06c68c90101b6cda2247a05970e3f30620881bae825c73f8bdca90ed783196 Incident The root cause has been identified, and the issue has been resolved, with downtime experienced between 1:55 and ending at 2:07 https://status.vapi.ai/incident/1083466 Tue, 06 Oct 2026 21:04:00 -0000 https://status.vapi.ai/incident/1083466#3c6dfdfb397a9c7dbca5439765afc71a8395a90b7c24008be9995cc33100481b Incident Outbound SIP Server downtime from 1:55 to 2:07, impacting outbound calls and call transfers. Currently seeing recovery, and the team is monitoring closely. https://status.vapi.ai/incident/1080062 Fri, 02 Oct 2026 12:33:00 -0000 https://status.vapi.ai/incident/1080062#151c18d534084e43e742ce85c0033a266b1e3ff70f24ec50c86f8db8bcb9ea02 Incident The issue has been resolved and calls are completing as expected. https://status.vapi.ai/incident/1080062 Fri, 02 Oct 2026 12:23:00 -0000 https://status.vapi.ai/incident/1080062#3bce4e8e290dfc8a97283bd9d9b5b8133612bc034911ae0a22ebbbb1a9c3c90b Incident We have identified the root cause of the issue and the services are recovering. We are monitoring and will update shortly. https://status.vapi.ai/incident/1080062 Fri, 02 Oct 2026 12:12:00 -0000 https://status.vapi.ai/incident/1080062#64dd1677c176d16fd3da34156418166ed830ac52db5643c844db4b2e6a384979 Incident Calls currently failing for SIP and Vapi member outbound. We are investigating root cause and will update shortly. https://status.vapi.ai/incident/1077399 Wed, 30 Sep 2026 16:01:00 -0000 https://status.vapi.ai/incident/1077399#528bf4584276d611a3a751cea7bd2e78e37343d83840849120c2535c8f36281c Incident 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. https://status.vapi.ai/incident/1077399 Tue, 29 Sep 2026 22:18:00 -0000 https://status.vapi.ai/incident/1077399#2bc7fec606bb12860f7fe47c4c9e99f26442ca144a790b6e217b81084f3c62e6 Incident No change - we are still awaiting confirmation from our upstream provider to restore new number provisioning. Creating new Vapi phone numbers remains unavailable; existing numbers and imported numbers are unaffected. We will post another update as soon as we have news. https://status.vapi.ai/incident/1077399 Tue, 29 Sep 2026 21:05:00 -0000 https://status.vapi.ai/incident/1077399#8473596c89829a1bca2cc38af3b3e1e2172f93a8ead6185ffc0167b4980793c5 Incident We are currently working with our upstream provider to restore new number provisioning. Creating new Vapi phone numbers remains unavailable; existing numbers and imported numbers are unaffected. Next update within the hour or as soon as provisioning is restored. https://status.vapi.ai/incident/1077399 Tue, 29 Sep 2026 18:55:00 -0000 https://status.vapi.ai/incident/1077399#b3ce19002e7b4f27f24e9a281269a59d83bdf4057a9a6b5a365abc6ca7b0aacb Incident The team has identified the cause and are actively working on a fix. Creating new Vapi phone numbers remains unavailable; while existing numbers and imported numbers are unaffected. https://status.vapi.ai/incident/1077399 Tue, 29 Sep 2026 17:16:00 -0000 https://status.vapi.ai/incident/1077399#889ca32e2aab52ddd7c0a918f5eac626a0fc5c956563c33a49ff914a644235f7 Incident We're aware of an issue provisioning new Vapi phone numbers - the team is actively looking into it. Calls to existing numbers and importing numbers from other providers are NOT impacted. https://status.vapi.ai/maintenance/1072370 Wed, 23 Sep 2026 18:50:28 -0000 https://status.vapi.ai/incident/1072370#d6c468d05ae053c5504d0f01c12eb854f6a270db41cd53729322bb7127a59f0d Maintenance We're doing scheduled maintenance on part of our database infrastructure. What to expect: Calls, API reads, and the dashboard will keep working normally. Some write operations may briefly fail or slow down during the window. This mainly affects campaigns, chat, and test suites. Action needed: None. If a request fails during the window, retry it. Clients that already retry failed requests should see little or no impact. https://status.vapi.ai/maintenance/1064531 Mon, 21 Sep 2026 06:12:21 -0000 https://status.vapi.ai/incident/1064531#12f968450ccc4f9d886744023037c3ea74306ad4d88cd1cd3e5b6c7d55b7827b Maintenance Due to operational delays, the maintenance occurred at 10:50pm PT. We observed a decrease in the rate of outbound dials that returned to normal levels at 10:58pm PT. No on-going calls would have been impacted. https://status.vapi.ai/maintenance/1064531 Mon, 21 Sep 2026 05:10:16 -0000 https://status.vapi.ai/incident/1064531#87eba64e70f8eef7ad773f7648cbbf68510f014952450443833719773b0d0827 Maintenance Maintenance completed https://status.vapi.ai/incident/1068531 Fri, 18 Sep 2026 23:10:00 -0000 https://status.vapi.ai/incident/1068531#34c6ecc9cbaca37b12e63e59fce70c875faa3b1f17f271bec8585fc17dad6bd9 Incident Our login provider has recovered and the Vapi dashboard is fully operational again. https://status.vapi.ai/incident/1068531 Fri, 18 Sep 2026 23:00:00 -0000 https://status.vapi.ai/incident/1068531#3d3e7e12abde2f563d8dab648160a981f58ce4a99a41bb35596ed189a8465dcb Incident Our dashboard login provider's service is degraded. Our API remains functional. https://status.vapi.ai/maintenance/1064531 Tue, 15 Sep 2026 17:15:23 -0000 https://status.vapi.ai/incident/1064531#7afcd2f03491db07680abdc538d783fb9ff8a68fe18f79c15d86379b87e3206c Maintenance We are performing maintenance on our SIP infrastructure to improve monitoring and stability. This will result in ~1min downtime. Who is affected: Calls using Vapi numbers, SIP (sip.vapi.ai), or a BYO SIP trunk will be unable to connect during the maintenance. Who is not affected: Calls using a native Twilio, Telnyx, or Vonage number connected directly, web callers, or users in the Vapi EU or AUS regions. When: September 20, 2026, 10:00pm to 10:10pm PT What to expect: SIP calls will fail to connect for about 1 minute at 10:00pm PT and return the standard error response. We will then validate for the rest of the window while calls connect normally. Action needed: If one minute of failed calls is a concern, route through an alternate transport such as Twilio for the window. We will update this page when calls are connecting again and when the work is complete. https://status.vapi.ai/incident/1062035 Sun, 13 Sep 2026 18:00:00 -0000 https://status.vapi.ai/incident/1062035#1fc367f0db93052faeb980a4cc0ca6b2d76186fa6786ffbcaeca62fb1fc347fc Incident 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. https://status.vapi.ai/maintenance/1049678 Thu, 03 Sep 2026 23:08:02 -0000 https://status.vapi.ai/incident/1049678#65231c33a69c5a5a4de2a6654698df51369ef2f3fb3e835ec8c454f98c1951c0 Maintenance We're performing routine maintenance on our telephony infrastructure in the EU region. *Users of the US regional deployment will not be affected (dashboard.vapi.ai, api.vapi.ai, sip.vapi.ai)* When: Wednesday, September 9 2-2:15am CET (Tuesday, September 8 5-5:15pm PT) What to expect: There will be downtime at 2am in which calls made using Vapi Numbers, directly via our SIP infrastructure, or via SIP trunk will not connect and fail immediately. After, there will be a period where we monitor and validate the maintenance but calls will start connecting again. Action needed: If there are concerns around minutes of downtime, customers can configure an alternate transport (i.e. Twilio) for calls. We'll update this page as the maintenance progresses when SIP calls should be back online and when the update is completed altogether. https://status.vapi.ai/maintenance/1037976 Fri, 28 Aug 2026 18:19:02 -0000 https://status.vapi.ai/incident/1037976#f45339c239fa4d67cf237f8a3709b71cb1a84f0651d08c3870a542b7a8b54eab Maintenance We're performing scheduled maintenance on our database layer, including a capacity upgrade to a read replica and configuration updates to improve connection handling under load. Brief elevated API latency is possible. Active calls are not affected. https://status.vapi.ai/maintenance/1034541 Wed, 26 Aug 2026 17:20:03 -0000 https://status.vapi.ai/incident/1034541#1031df8d03f218f7865d51d948f7c00e387f520cfc9c31313955423336e663f5 Maintenance We're performing routine maintenance on our telephony infrastructure. When: Monday, August 31 9-10pm PT What to expect: There will be downtime for ~10min at 9pm in which calls made using Vapi Numbers, directly via our SIP infrastructure, or via SIP trunk will not connect and fail immediately. After, there will be a period where we monitor and validate the maintenance but calls will start connecting again. Action needed: If there are concerns around minutes of downtime, customers can configure an alternate transport (i.e. Twilio) for calls. We'll update this page as the maintenance progresses when SIP calls should be back online and when the update is completed altogether. https://status.vapi.ai/incident/1021689 Thu, 20 Aug 2026 17:20:00 -0000 https://status.vapi.ai/incident/1021689#efdd7299e910650f6d6a886a82b6e1f87697c68c158b55bd635c2590a43e6148 Incident Incident Report available at https://drive.google.com/file/d/1ORxSZb8NYgVlmPoqnUEdTmlIua3NSl_k/view https://status.vapi.ai/incident/1021689 Wed, 19 Aug 2026 20:19:00 -0000 https://status.vapi.ai/incident/1021689#9aaad74a2b45acc352703e4fd4e1a42d4d3eede463e71c2a91ea943de612e4d7 Incident The incident is resolved. https://status.vapi.ai/incident/1021689 Wed, 19 Aug 2026 20:02:00 -0000 https://status.vapi.ai/incident/1021689#95b25dbe143f433e5eace17ea4a48cb6fe1530c2ec67199ddc363a50ef3e7de9 Incident We are seeing recovery on all affected services and have moved to monitoring status. https://status.vapi.ai/incident/1021689 Wed, 19 Aug 2026 19:55:00 -0000 https://status.vapi.ai/incident/1021689#4ab6297cdf69f377629caccf86bfb1af63a2c23010976e0afa961ccab6886c2d Incident Some customers are reporting concurrency limits issues. We are resetting all limits to zero for all subscriptions. This change will propagate over the next few minutes. https://status.vapi.ai/incident/1021689 Wed, 19 Aug 2026 19:26:00 -0000 https://status.vapi.ai/incident/1021689#ebdd5b90f7a0ea626ab146fe9c495de3e22fdcd9d13934679aefa4612912bee2 Incident We have rolled out a mitigation measure and are seeing improvements in call success rate. https://status.vapi.ai/incident/1021689 Wed, 19 Aug 2026 19:01:00 -0000 https://status.vapi.ai/incident/1021689#ffb573a9a59f6c3901af06ef3bfafae50ab67d95dbfdf0618f124123f283c8c2 Incident Calls are still failing to connect. Our team has a working hypothesis and we will post as soon as we can confirm the root cause. Next update will be in 30 min or earlier. https://status.vapi.ai/incident/1021689 Wed, 19 Aug 2026 18:36:00 -0000 https://status.vapi.ai/incident/1021689#36d5802904be0f49b025d9a45c54fab6b4327779060a6fb61e4c420be1062a49 Incident We are confirming that calls are not connecting in the US. Our team is still investigating. Next update in 30 min or sooner. https://status.vapi.ai/incident/1021689 Wed, 19 Aug 2026 18:16:00 -0000 https://status.vapi.ai/incident/1021689#c6c9e335c904dfafac098f7eab4658a86661da7fc6f551c3fdb0f4a1b7ceb4bb Incident We're seeing an increased rate of call failures and the team is actively investigating https://status.vapi.ai/incident/1009573 Wed, 12 Aug 2026 11:50:00 -0000 https://status.vapi.ai/incident/1009573#2ca348e420ee01fc4ddfb3fdf81da6417b95edf16cccb5d510ef7c029f1cbf60 Incident 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. https://status.vapi.ai/maintenance/1004936 Fri, 07 Aug 2026 21:39:20 -0000 https://status.vapi.ai/incident/1004936#031d82c71d28ccba1f1ad63d8d3201b1d9ae0f20ea65b89f37888bca6fba5e8e Maintenance We're performing scheduled maintenance on core database infrastructure. When: Tuesday, September 8st, 2026 — 9PM to 10PM PDT What to expect: Calls, API reads, and the dashboard continue to work normally throughout. During the window there are three brief periods, a couple of minutes each, where write operations may fail and need to be retried. This affects changes to assistants, phone numbers, and credentials. Action needed: None. Clients with standard retry behavior will not notice. If a write fails, retry it. We'll update this page as the maintenance progresses and post a final note when it's complete. https://status.vapi.ai/incident/997125 Wed, 05 Aug 2026 20:30:00 -0000 https://status.vapi.ai/incident/997125#470933652e3c940732c279ee16d69cb01e780fdb08e62dd4d02d1d1e8a018d12 Incident Our documentation vendor has resolved their issue and Vapi documentation is now fully available. https://status.vapi.ai/incident/997125 Wed, 05 Aug 2026 19:55:00 -0000 https://status.vapi.ai/incident/997125#3d4aeee5518a06624c64f6aeb02d0c982cae58f451fd42720dfba6f9b190eee8 Incident Our documentation hosting provider is currently experiencing an issue which is impacting the availability of Vapi documentation and MCP server. In the meantime you may directly view our documentation repo here: https://github.com/VapiAI/docs At this time there is no evidence of impact to the Vapi dashboard, API, or other services. https://status.vapi.ai/incident/996148 Tue, 04 Aug 2026 20:20:00 -0000 https://status.vapi.ai/incident/996148#c71159722eab5256985975070d4e0ee5073520d868038410dba99e552ca8e259 Incident 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. https://status.vapi.ai/incident/996148 Tue, 04 Aug 2026 19:52:00 -0000 https://status.vapi.ai/incident/996148#8037d4786f1bd3f4c1ef197a41406eb75ff5de6c422d444712c561c42572c3e8 Incident We are currently seeing recovery, we are actively monitoring the issue and will provide updates within the next 20 minutes. https://status.vapi.ai/incident/996148 Tue, 04 Aug 2026 19:41:00 -0000 https://status.vapi.ai/incident/996148#a9159aa197a1a0a9d0f7cb70a1a7e41e55df0071504ed3bbfa54ae14cbddd1fb Incident We are experiencing API Degradation on the daily channel. The team is actively investigating. https://status.vapi.ai/maintenance/994732 Tue, 04 Aug 2026 01:16:14 -0000 https://status.vapi.ai/incident/994732#430f2c806ee265270ae2947de626660b21c71bcd7ff08cc514eed09088c68635 Maintenance We're upgrading our authentication database as part of ongoing reliability work on the Vapi platform. **What to expect** • Most of this window is prep and verification. The part customers actually notice should only last a few minutes. • During those few minutes, requests that create or change account-level resources may briefly fail. That includes starting new calls and making organization or subscription changes. • Signing in, API key authentication, and read requests are not affected and will keep working throughout. • Calls already in progress won't be interrupted. • Any request that fails is safe to retry. Standard client retries will go through once the window closes. • No data will be lost, and there's nothing you need to do. We'll post updates here as the work progresses. If you run into any issues after the window closes, email us at support@vapi.ai. https://status.vapi.ai/incident/976712 Fri, 24 Jul 2026 11:44:00 -0000 https://status.vapi.ai/incident/976712#bdb5a5e45a4cfeade69c93b8ba758305fbf1b7c2342b1e48b51c6f189a6559b8 Incident Between 10:55 and 11:10 UTC, some API requests and calls failed due to a network performance issue at our upstream network provider affecting US west. EU and Australia regions were not impacted. Service recovered at 11:10 UTC. No action is required. We're continuing to monitor. https://status.vapi.ai/maintenance/973555 Wed, 22 Jul 2026 12:57:58 -0000 https://status.vapi.ai/incident/973555#e152ed5c063535bf2a1a67ba0c96be9934efe697228ae98d98891858b88b9b0e Maintenance We will be performing a patch update on our SIP server. This maintenance requires a brief server restart and will be carried out during a low-traffic period to minimize any impact. We do not anticipate any significant disruption, and service will resume immediately after the restart. https://status.vapi.ai/incident/965921 Thu, 16 Jul 2026 10:17:00 -0000 https://status.vapi.ai/incident/965921#8c88280b148ed0e3cc0995d8e66a61dc27dcae88dc6f04e538d26ac87b2b48cf Incident We have engaged our fallback authentication provider restoring access back to the Vapi Dashboard. We will continue to monitor but at this time, we are observing no further issues. https://status.vapi.ai/incident/965921 Thu, 16 Jul 2026 10:00:00 -0000 https://status.vapi.ai/incident/965921#380185847d9fc68510e359877edff0383b7442ffe724b71c433c86205abd2bb4 Incident We observed an increase in Dashboard Access degradation due to an outage with our downstream authentication provider. We are investigating the root cause and actively monitoring. https://status.vapi.ai/incident/947546 Wed, 08 Jul 2026 20:59:00 -0000 https://status.vapi.ai/incident/947546#594e87eb10534a0f11f3dd0328e973fb3f397426e7b9a572d10742f9c6caa682 Incident We have identified the root cause of this issue and successfully implemented a fix. We will continue to monitor but at this time are observing no further issue. https://status.vapi.ai/incident/947546 Wed, 08 Jul 2026 20:22:00 -0000 https://status.vapi.ai/incident/947546#af8eb295b9e13204bc00d52a78211eb98e0f765dc777010350a4e63874c390ad Incident We observed an increase in API error rates between 12:30 and 1PM PT. Service recovered after 1PM PT. We are investigating the root cause and actively monitoring API health. https://status.vapi.ai/incident/945421 Tue, 07 Jul 2026 07:06:00 -0000 https://status.vapi.ai/incident/945421#8e3744c18c30744e913335268b5020be5530a7ac04c5bd941a0a73d0cbcdadc7 Incident We performed critical maintenance on our analytics service, during which the Analytics charts and Insights (Boards) in the Vapi Dashboard were temporarily unavailable or returned errors. Voice calls, call handling, and all APIs operated normally throughout, with no impact to your account settings or call data. The affected features are now fully restored and we're actively monitoring. We apologize for the disruption. https://status.vapi.ai/incident/945421 Tue, 07 Jul 2026 02:54:00 -0000 https://status.vapi.ai/incident/945421#5c25f2034b554db8ea07f3e6eddc1383f23d98aa2dd9dcd2e51abd880fcb7871 Incident We are deploying a fix into production. We will provide a final update once the fix is merged and the issue has been resolved. https://status.vapi.ai/incident/945421 Tue, 07 Jul 2026 02:01:00 -0000 https://status.vapi.ai/incident/945421#ad6e244b4930277e6e6cc88cf8fddd4cd476f726f4543fe2187d4b71da8bc559 Incident We are continuing to deploy a fix for the degraded performance affecting Boards. We will provide our next update by 7:45 PM PT. https://status.vapi.ai/incident/945421 Tue, 07 Jul 2026 01:14:00 -0000 https://status.vapi.ai/incident/945421#592b9c07a32cfecb01e5d4e6e4bfa8eaa304e821b1f54c2a2021a91d9247852a Incident We have identified the root cause of the issue and are actively deploying a fix to restore normal performance to boards. https://status.vapi.ai/incident/945421 Tue, 07 Jul 2026 00:30:00 -0000 https://status.vapi.ai/incident/945421#21e5bef6a09364f3ea5fc91d48cd8b93a5aaee526069135fb4ed944618a1b69d Incident We are aware of an issue that is impacting the ability for users to create and in some cases view Boards or Insights within the dashboard. This issue is only impacting viewing analytical data and is not impacting live Assistants, Squads, Calls or Chats. https://status.vapi.ai/incident/945104 Mon, 06 Jul 2026 18:15:00 -0000 https://status.vapi.ai/incident/945104#8a52bbc507486a1a4ff6987d58c725a18a5469ba3bd8c4abc9a623c2595fec60 Incident We noticed a degradation in API success rate only on the daily channel from 11 A.M to 11:04 A.M. Success rate has since recovered and we are not seeing any further degradation - the team will continue to monitor the issue. https://status.vapi.ai/incident/941850 Thu, 02 Jul 2026 18:15:00 -0000 https://status.vapi.ai/incident/941850#f1de56e0ebbd5978daef43095d3ba3afeb7dcbb4836a91e97f70499bab696511 Incident We observed an increase in API error rates between 11:00 and 11:04 am PT, affecting only the daily channel. Service levels recovered after 11:04 m PT. We are investigating the root cause and actively monitoring API health. https://status.vapi.ai/incident/941850 Thu, 02 Jul 2026 18:07:00 -0000 https://status.vapi.ai/incident/941850#ae24cfa8d580801bebcfceb317be4d054aadba787802125bc9c431f3383890ee Incident We are aware of and are investigating degradation in API success rate in the daily channel. https://status.vapi.ai/incident/936394 Sat, 27 Jun 2026 00:48:00 -0000 https://status.vapi.ai/incident/936394#810e2bdbe9008352accc6d508c69473411a38bddd98556c8ea2f51ccec90852e Incident We have deployed a fix for this issue and are observing full resolution. All systems are fully operational. Our team will continue to monitor. https://status.vapi.ai/incident/936394 Fri, 26 Jun 2026 23:03:00 -0000 https://status.vapi.ai/incident/936394#159e6f3530ceecd95940560a42e4b55e929b55f95ab161de48f4b757ab2d9da4 Incident We are continuing our work to deploy this fix across our services. Our next update will be once the fix is successfully deployed everywhere. https://status.vapi.ai/incident/936394 Fri, 26 Jun 2026 20:51:00 -0000 https://status.vapi.ai/incident/936394#7f46fc0695ba6093c386abb43043c6eabce1623e506af6c878bd1b90fb570e5b Incident We have identified the root cause of this issue and are working to deploy a fix. https://status.vapi.ai/incident/936394 Fri, 26 Jun 2026 19:55:00 -0000 https://status.vapi.ai/incident/936394#2aa9525ebbd9fde4b700fa3e47e19024b8a34fb5b524256329ef7d1fce06e992 Incident We are investigating reports of high latency when viewing logs within the dashboard. At this time we do not see any impact to call success rate, this issue appears isolated to accessing logs of calls once completed. https://status.vapi.ai/incident/933768 Wed, 24 Jun 2026 20:59:00 -0000 https://status.vapi.ai/incident/933768#f4819423ea0451891f486c669f825e9b00257caf9e6c61c4e7b659a10fde6269 Incident We have deployed a fix for this issue and will continue to monitor. We have not seen any elevated error rate since 1:20PM PT. https://status.vapi.ai/incident/933768 Wed, 24 Jun 2026 20:41:00 -0000 https://status.vapi.ai/incident/933768#01f868c11c32546a1af78e3dce1903ab13c74f44fa3f29982a694b0608c6a542 Incident We have observed recovery of this issue starting around 1:20PM PT. We identified the root cause of the issue and are working to implement a fix. https://status.vapi.ai/incident/933768 Wed, 24 Jun 2026 20:12:00 -0000 https://status.vapi.ai/incident/933768#b1b7898040897805eadcb6b8db4097ba4709a55436c9668766448a4e9a636bcd Incident We are investigating reports of elevated failure rates affecting our API on weekly channel. Our team is actively working to confirm these reports and will provide an update within the next 30 minutes. https://status.vapi.ai/incident/926178 Wed, 17 Jun 2026 01:47:00 -0000 https://status.vapi.ai/incident/926178#85d3aa232ce51d5242b88cc2f6971217e414c35792f618ce8df2f78b2be81c8b Incident We have implemented a fix and observed full recovery. Failures were observed beginning 5:45pm and resolved as of 6:05pm. https://status.vapi.ai/incident/926178 Wed, 17 Jun 2026 01:15:00 -0000 https://status.vapi.ai/incident/926178#103922de53d377d641aa90915e04b7acc9d20f20ddcc81c171bd4fcaaeb0098d Incident We are observing recovery in API success rates across both daily and weekly channels. https://status.vapi.ai/incident/926178 Wed, 17 Jun 2026 01:01:00 -0000 https://status.vapi.ai/incident/926178#db44a32e42e20600beabeaa326dc13acf4db55d659dd4300c10e8ea954eed11c Incident We are observing elevated error rates across API endpoints in the daily and weekly channels. The team is actively investigating. https://status.vapi.ai/incident/925915 Tue, 16 Jun 2026 19:17:00 -0000 https://status.vapi.ai/incident/925915#00c314800e90d36950fada68bf816cefcb844ea4ad3877b0d3c6af09705ef3ee Incident We observed an increase in API error rates between 12:05-12:10pm PT affecting the weekly channel. Service levels recovered after 12:10pm PT. We are investigating the root cause and actively monitoring API health. https://status.vapi.ai/maintenance/918243 Mon, 08 Jun 2026 20:22:48 -0000 https://status.vapi.ai/incident/918243#48d050d78312fb752a9f4dbd02b76f212cdec76b286fcd8f5fa50e18f7fba2e4 Maintenance We will be performing a routine certificate update on our SIP server. This maintenance requires a brief server restart and will be carried out during a low-traffic period to minimize any impact. We do not expect any significant disruption, and service will resume immediately after the restart. https://status.vapi.ai/incident/911982 Wed, 03 Jun 2026 13:31:00 -0000 https://status.vapi.ai/incident/911982#e708a1efcfc1a17ce288a3c0fc2332c716a440a40921cf9b77e261b482b00cde Incident The incident has been resolved, and service restored as of 5:47am PDT. https://status.vapi.ai/incident/911982 Wed, 03 Jun 2026 13:03:00 -0000 https://status.vapi.ai/incident/911982#be03304b21231b2eb3e7cf4f89c34ec9e8db31b99af53a43828a5277bd90487c Incident We implemented a fix and are seeing recovery as of 5:47am PDT. We will continue to monitor and update here. https://status.vapi.ai/incident/911982 Wed, 03 Jun 2026 12:40:00 -0000 https://status.vapi.ai/incident/911982#1b92b2133c933cca947293de77b3f5f88ed7fee6e6fce30f99afd56f7703309c Incident We are seeing a high rate of call creation failures. We are investigating and will share updates here. https://status.vapi.ai/incident/911475 Tue, 02 Jun 2026 23:42:00 -0000 https://status.vapi.ai/incident/911475#3d4230dd7d761815986010b63d384691b2e1efc904b55ca1d101c2cdc6f10f6d Incident Our team has identified the root cause and deployed a fix. The issue has been resolved, and all systems are operating normally. We will continue monitoring to ensure stability. https://status.vapi.ai/incident/911475 Tue, 02 Jun 2026 23:14:00 -0000 https://status.vapi.ai/incident/911475#f99e857be7d9f4452509dffadc3d3af6b4121763683a364dd28038629e15a908 Incident If you are seeing issues, you may use https://dashboard-weekly.vapi.ai/ as an immediate workaround instead of https://dashboard.vapi.ai/ https://status.vapi.ai/incident/911475 Tue, 02 Jun 2026 23:11:00 -0000 https://status.vapi.ai/incident/911475#b54a9c18e5bb1d9f5c1c67eb931c61fae1001d0469f10516962b5bfbb3255815 Incident We are investigating reports of errors loading the dashboard affecting customers on our Weekly channel. Our team is actively working to determine the root cause and will provide the next update within 30 minutes or sooner. https://status.vapi.ai/incident/901977 Fri, 29 May 2026 20:22:00 -0000 https://status.vapi.ai/incident/901977#6ca955afb85d1438ffcd967fb1a4b3901a89063a20df0c7b2481645fb848b568 Incident # Vapi RCA - US Platform Outage, May 21, 2026 **RCA:** US Platform Outage (Database Connection Exhaustion) **Status:** Resolved **Primary Impact:** Voice calls and API requests failed; the dashboard was unavailable **Date:** May 21, 2026 **Customer-facing systems affected:** Calls, API, Chat, Dashboard, Logs **Severity:** Critical ### Executive Summary On May 21, 2026, the Vapi US platform was unavailable for approximately 4 hours and 7 minutes, beginning at 7:02 AM PT, with service restored by 11:09 AM. Calls began failing at 7:02 AM PT, and by 7:12 AM PT the platform had progressed to a full outage of voice calls and the dashboard. During the window, voice calls failed to connect or complete, API requests returned errors, and the dashboard was inaccessible. Customers served from our EU and AUS regions were not affected. The outage began with a configuration change our database provider applied at 6:44 AM PT to the audit logging module used by our databases. The telemetry/audit logging setting caused Postgres processes to block while writing log output (syslog) at the moment they accepted new connections. Two databases that every call and API request depends on stopped accepting traffic, so the platform could neither authorize requests nor record new calls. Service was restored after the provider disabled the affected logging and restarted the database, and we ramped traffic back in a controlled way to avoid a second failure. We marked the incident resolved at 11:49 AM PT after sustained monitoring confirmed stability. The changes below focus on removing the dependencies that let a database fault become a full outage. ### What You May Have Observed - Inbound and outbound voice calls failing to connect, or ending early - API requests returning server errors (HTTP 5xx) - Inability to access the Vapi dashboard - Scheduled and campaign calls not firing during the window - A brief period of partial recovery mid-incident, where some calls succeeded before failures resumed ### Timeline (PT) - **6:44 AM**: Our database provider applies a configuration change to audit logging. - **7:02 AM**: First monitors fire for API degradation; calls begin failing. - **7:18 AM**: On-call engineer acknowledges the page and begins investigating. - **7:38 AM**: The core infrastructure team jumped into a formal incident. - **7:43 AM**: Status page updated to report degradation. - **7:53 AM**: Status page updated to confirm a full outage of calls and dashboard. - **8:10 AM**: Production database identified as the source; database provider support engaged. - **8:16 AM**: Escalated with the provider for higher urgency. - **8:29 AM**: Status page confirms the production database as the cause. - **9:35 to 10:00 AM**: Brief recovery after a database restart, followed by renewed degradation as traffic resumed. - **10:03 AM**: Provider identifies root cause: database processes stuck writing audit logs while accepting connections, caused by a misconfigured project-wide telemetry setting. - **10:05 AM**: Affected logging disabled and the database endpoint restarted; the database returns to normal. - **10:05 to 11:09 AM**: Traffic ramped back gradually, weekly cluster first (restored 10:38 AM), then daily (restored 11:09 AM). - **11:49 AM**: Incident resolved. ### Root Cause **An audit-logging change exhausted the database connection pool** Vapi’s databases include audit logging. At 6:44 AM PT, our database provider changed where that audit output was written. A misconfiguration in the provider's project-wide telemetry settings caused Postgres processes to block while writing log output at the moment they accepted new connections. Connections accumulated in a waiting state until the pool was exhausted, and the affected databases could no longer accept traffic. **A hard dependency on two databases turned the problem into a full outage** Every API request and call passes through two of these databases: one authorizes the request at our API gateway, and the other records the call before it is queued for processing. Both were among the affected databases. With neither reachable, the platform could not authorize requests or create calls, so the failure was total rather than partial. A read replica was in place, but the provider's configuration change applied at the project level and affected both the primary and replica. **Resulting customer impact** For the duration of the window, calls failed to connect or complete and API requests returned errors. The dashboard, which also depends on these databases, did not load. Scheduled and campaign calls due to fire during the window did not run and were not retried automatically. Customers also would have noticed incidents before the Vapi status page was updated, due to the delay between on-call acknowledgment and creation of any status page. ### Resolution - Our database provider disabled the audit log collection on the affected databases and restarted the database endpoint, which restored their ability to accept connections. - To avoid a connection storm overwhelming the recovered databases, we brought internal services back up gradually rather than all at once, restoring the weekly cluster first and then the daily cluster. - We confirmed recovery through API success-rate, error-rate, and database latency monitoring before closing the incident. Our provider has since published and confirmed a fix to the affected audit log collectors. ### Prevention **Within the next week we are working towards:** - Add production monitoring for database query latency and connection-volume anomalies, so this signature is caught at onset rather than inferred from downstream symptoms. - Establish a faster, clearly defined escalation path with our database provider. Provider escalation and resolution took longer than it should have. - Implement a change management process with our database provider so changes that could impact availability are done in a more controlled manner. **Over the next quarter we are working towards:** - Introduce a read cache in front of authorization and configuration data, removing the hard dependency on that database so a future database fault degrades the platform rather than disabling it. - Migrate our critical databases to a platform that supports a regional hot standby, so we can fail over when a primary becomes unavailable. - Implement automatic status updates based on monitors, to ensure customers are made aware of incidents when we are. - Move call-record writes to an asynchronous path, removing the hard dependency on the call database for connecting a call. ### Customer Actions - No action is required to restore service. We are committed to earning your trust. As part of that, progress on the prevention items will be shared with you via your account team. https://status.vapi.ai/incident/907756 Fri, 29 May 2026 03:58:00 -0000 https://status.vapi.ai/incident/907756#22a16b71a89835776385ccfa98c5645b5542f6a95a92c0e91ee74ad056250bee Incident We have identified the cause of the issue and reverted the change. The issue has been resolved, and all systems are operating normally. We will continue monitoring to ensure stability. https://status.vapi.ai/incident/907756 Fri, 29 May 2026 03:51:00 -0000 https://status.vapi.ai/incident/907756#b3ac414d3fde6833f4088e04ac0785b2ea4dabb4edefd0e1c2e45e3ba6edf297 Incident We are investigating reports of degraded performance affecting the Vapi Dashboard. Calls do not appear to be impacted. Our team is actively working to determine the root cause and will provide the next update within 30 minutes. https://status.vapi.ai/incident/907173 Thu, 28 May 2026 11:08:00 -0000 https://status.vapi.ai/incident/907173#aec14e18b6e63c2b511012d90f6c7afd46014c3c8792748c884ca35256265776 Incident The issue was caused by a brief DB hang that has been resolved, and all systems are operating normally. We will continue monitoring to ensure stability. https://status.vapi.ai/incident/907173 Thu, 28 May 2026 10:14:00 -0000 https://status.vapi.ai/incident/907173#cfead94652778cd287c1fd256a557ff2c8cfafd048bf449fbe387e03aa88f174 Incident We're seeing an increased rate in call failures and are actively looking into it. https://status.vapi.ai/incident/905860 Tue, 26 May 2026 19:55:00 -0000 https://status.vapi.ai/incident/905860#9a83bda61a044d7f2a170dca2c87ab6c99032e9164eaafcef05608d1dc24b7f8 Incident The issue was caused by a brief API latency blip that has been resolved, and all systems are operating normally. We will continue monitoring to ensure stability. https://status.vapi.ai/incident/905860 Tue, 26 May 2026 19:17:00 -0000 https://status.vapi.ai/incident/905860#aa521e7b942f04f2e8fd6bfe8f26c472eaebc14f3132f4ee5a351fb2879c2567 Incident We are investigating reports of degraded performance affecting calls. Our team is actively working to determine the root cause and will provide the next update in 45 minutes at the latest. https://status.vapi.ai/incident/901977 Fri, 22 May 2026 03:03:00 -0000 https://status.vapi.ai/incident/901977#7fc7a396a86f0f7be0cd4a61457ec1d1655323be5a7861c4185e04de8ec178ff Incident # Incident Report: Database Outage (Log Collector Misconfiguration) ## What Happened Vapi experienced a large service outage causing voice calls to fail and the dashboard to become unavailable. This was caused by a failure in an audit log collector in the Vapi production database. The triggering event was an `apply_config` that our database provider executed at 6:44 AM PST. A misconfiguration in the project-wide telemetry settings caused Postgres processes to become stuck writing to syslog when accepting new connections, exhausting the connection pool and rendering the database unable to accept traffic, including from within the pod itself. We notified our provider's support line at 8:10 AM PST. The root cause was identified at 10:03 AM PST by our database provider. Mitigation was applied by disabling the OTEL connection and restarting the endpoint, after which the system returned to a normal state. A fix to the audit collectors was subsequently published and confirmed stable. ## Customer Impact - **Service availability:** Large outage. Vapi's voice services were unavailable during the incident window, affecting 100% of customers from 7:12 AM PT until 11:49 AM PT when the incident was marked as resolved. - The Vapi dashboard was also unavailable during that time. ## Timeline (PST) | Time | Event | |------|-------| | 6:44 AM | Our database provider executes an `apply_config` change, triggering the incident. | | 7:12 AM | Vapi begins to observe call degradation. | | 7:22 AM | The team begins its investigation. | | 7:43 AM | Vapi updates the status page to notify customers of observed degradation. | | 7:53 AM | Vapi updates the status page to confirm a full outage of both voice calls and the dashboard. | | 8:10 AM | Vapi suspects production database behavior as the source of the problem and notifies the database provider's support team. Initial investigation begins; a large spike in waiting-status connections is observed. | | 8:16 AM | Internal escalation with the database provider for increased urgency. | | 8:29 AM | Vapi confirms production database behavior as the source of the problem on the status page and continues to collaborate with the database provider on mitigation. | | 9:35–10:00 AM | A brief recovery is observed after restarting the database, but degradation reappears after services are scaled back up. | | 10:03 AM | Database provider identifies the root cause: Postgres processes stuck on syslog writes during connection acceptance, caused by a misconfigured project-wide `telemetry_setting` for log collectors. | | 10:03 AM+ | OTEL connection disabled; endpoint restarted; system returns to normal state. | | 10:38 AM | Vapi increases traffic back on the weekly environment and confirms that service is restored. | | 11:09 AM | Vapi increases traffic back on the daily environment, confirms service is restored, and moves to a monitoring stage. | | 11:49 AM | Vapi marks the incident as resolved. | https://status.vapi.ai/incident/901977 Thu, 21 May 2026 18:32:00 -0000 https://status.vapi.ai/incident/901977#44062674e3d0cbc5451015feee7c7fb3f8ec03ee220efb26d8a1448db4aee75e Incident Service has returned to normal operating levels. Call success metrics have recovered and remained stable for 30 minutes across both daily and weekly channels, and all platform functionality has been restored. We’re continuing to monitor closely and will provide further updates if anything changes. We will update the status page with an incident report within 12 hours. Thank you for your patience. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 18:09:00 -0000 https://status.vapi.ai/incident/901977#f05c9dd8a08e6a422e62e0de7b36eb56af35531bb3e6fa4ef8725564d406924d Incident Services are recovering across both our weekly and daily clusters, and all metrics are trending positive. Our DB provider has identified and confirmed the root cause and we have applied an initial remediation. Our DB provider team remains actively engaged with us as we scale load back up. We are continuing to monitor closely and will provide updates as we have them. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 18:06:00 -0000 https://status.vapi.ai/incident/901977#9e646ca8c56adf9e941e26f7db1a93098c1dfdb452cee157feedd656a5449973 Incident Our weekly cluster is still showing recovery and calls are going through. We are still monitoring the situation. We have shifted our focus to our daily cluster. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 17:41:00 -0000 https://status.vapi.ai/incident/901977#3e2a01d7d5ad93a2974f339eed96fe11a8ced64352df40ab2d5ce25e749b5eee Incident Our weekly cluster has seen recovery over the last 20 minutes. We are still monitoring the situation as there is a possibility for calls to fail again. We are moving to fixing calls in our daily clusters now. We will post updates when we have new information to share or in 30 minutes. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 17:13:00 -0000 https://status.vapi.ai/incident/901977#74f9b2943cab833d7c8d2888c89361402717e6b75f2b2788175094299ae3fd9e Incident Our daily cluster is still experiencing a full outage. Weekly is seeing some recovery. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 17:11:00 -0000 https://status.vapi.ai/incident/901977#357ef6ad5131e7c9eeeecef431ff58c193189b214ba84493a5f01b48920e9e5b Incident We are still in a degraded state on weekly and working on fully resolving the issue. Our daily cluster is still out. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 16:41:00 -0000 https://status.vapi.ai/incident/901977#a9c65e0ad3cbd819ca9deda4d6f065b3107618e6ab4275f47d7aa66355c9886e Incident We are seeing some recovery in Voice Calls and Dashboard calls and are continuing to monitor the situation. We will post updates as we have news or in 30 minutes. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 16:29:00 -0000 https://status.vapi.ai/incident/901977#b27cb903a68fceac436fc50e6a3de5c98bdac799b17d0c6bae2b84f7f801eb8e Incident Our DB provider has escalated to the highest level. Their most senior architect is now directly involved in identifying the fix. We are collaborating closely on resolution. We will post an update as we have news or in 30 minutes. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 15:59:00 -0000 https://status.vapi.ai/incident/901977#4d3a3033b97de54cb08f6f8a47e803639c9fb1003307ccf436fe3582a93d0d1f Incident Our DB provider confirmed the config change which we have identified as the cause for our DB outage, which causes voice calls to drop and our dashboard to not load. We are collaborating with our provider on an eventual fix or workaround. They have escalated this issue to the highest level of urgency on their side. We will post an update as we have news or in 30 minutes. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 15:27:00 -0000 https://status.vapi.ai/incident/901977#98a8d6c344800b42cffd198fb2ef7061bfb51a020e9f2653cb2de3f24a07e77a Incident We are still investigating a complete outage in Voice Calls. Our DB provider applied a configuration change at 6:44am which is causing our DB to be completely unavailable. We are working with them to get our DBs back up. We do not have an ETA or resolution yet, however our provider has escalated the issue internally. We will post an update as we learn more or in 30 minutes. https://status.vapi.ai/incident/901977 Thu, 21 May 2026 13:55:00 -0000 https://status.vapi.ai/incident/901977#f8cb2d0811765f6efcc178134dad27ff9150a1d488382ef286927d953228693a Incident We are investigating an incident causing voice calls dropped. We will publish updates as we get more information or in 30 minutes. https://status.vapi.ai/incident/896802 Fri, 15 May 2026 16:30:00 -0000 https://status.vapi.ai/incident/896802#4b2cf71d77f12b1dad14e3a76612656c3bd4e26d1ea24e74e51a715c1d53e4cc Incident The incident has been resolved and platform functionality has been fully restored. We will continue monitoring and will publish additional details if necessary. https://status.vapi.ai/incident/896802 Fri, 15 May 2026 15:50:00 -0000 https://status.vapi.ai/incident/896802#63c63b1fef11ce64c537c08871590fceb93058d92a511fb0bb1da0e0d10644b9 Incident We are seeing SIP issues affecting some customers and are investigating. https://status.vapi.ai/incident/896603 Fri, 15 May 2026 09:40:00 -0000 https://status.vapi.ai/incident/896603#aaeead6c15b0e6cf3a01c9d1f79a00354a9228a35ab459da32e3b0838d816608 Incident We have noticed a higher-than-usual rate of tool calls in the daily cluster and are currently investigating the issue. https://status.vapi.ai/incident/894167 Tue, 12 May 2026 17:03:00 -0000 https://status.vapi.ai/incident/894167#5d1ad18ddca38885c34c28a75a9500b6153384d09dd28cc187846204ab0cee26 Incident This incident has been resolved. All systems are operating normally https://status.vapi.ai/incident/894167 Tue, 12 May 2026 16:36:00 -0000 https://status.vapi.ai/incident/894167#cbf09e1c09f6921672735ab5044314a900e263ab7a2b3e376bcc4865181436e1 Incident The team has identified the issue, scaled the offending service accordingly, and we're starting to see a recovery. We will continue monitoring the situation as it improves. https://status.vapi.ai/incident/894167 Tue, 12 May 2026 15:53:00 -0000 https://status.vapi.ai/incident/894167#db22463265fe3788be0cdbd11b2cb82dd65ed59d879679fb8e2bc542e985696e Incident The team is still actively looking into the issue and working on a fix. https://status.vapi.ai/incident/894167 Tue, 12 May 2026 15:18:00 -0000 https://status.vapi.ai/incident/894167#ec50b2c21912686da9cca0fbdce616872161d856785f7db1eb353f3046149bca Incident We're seeing an increased rate in call failures and are actively looking into it. https://status.vapi.ai/incident/888152 Tue, 05 May 2026 14:44:00 -0000 https://status.vapi.ai/incident/888152#d8e442a8ed0005442498ab22d4651b680bfb582eb77faef1eb077c0297e23bd5 Incident Chat assistants on the weekly update channel were returning empty responses after tool calls, causing conversations to stall or end unexpectedly. We have rolled back the weekly update channel to a stable version for now to mitigate this. Note: It impacts only chat endpoints. https://status.vapi.ai/incident/876010 Mon, 20 Apr 2026 22:12:00 -0000 https://status.vapi.ai/incident/876010#59f00261b0c32e94df074648a3dab5db108dd6ccb724afa222a50071d6bd057f Incident Our documentation provider is experiencing an outage. We’re in touch with the team and will provide communication when services are back up https://status.vapi.ai/incident/873215 Thu, 16 Apr 2026 17:00:00 -0000 https://status.vapi.ai/incident/873215#18b409e2669990d474f29284b11efe38d57215d75ca822ea73189bcb020481ea Incident We have now resolved this incident. Between ~7:30AM PT and ~9:30AM PT, a new query pattern caused database slowness that increased API latency and led to dropped inbound calls with certain providers. We mitigated by rolling back the deployment and are following up with a deeper review of the query change. https://status.vapi.ai/incident/873215 Thu, 16 Apr 2026 15:35:00 -0000 https://status.vapi.ai/incident/873215#2abf856bd8639124beef2926d54f8a6253d6fef620cccaeefce38244d6940d4e Incident We are observing systems recover and performance is returning to normal. Some users may still see brief residual impact as systems stabilize. https://status.vapi.ai/incident/873215 Thu, 16 Apr 2026 14:45:00 -0000 https://status.vapi.ai/incident/873215#f8b4561bbbd5cacd6e39596af2c93a990b757cd4b12e82eed50cd45e67a0a986 Incident We are investigating reports of degraded performance affecting a subset of calls. Our team is actively working to determine the root cause and will provide updates as we learn more. https://status.vapi.ai/incident/871401 Tue, 14 Apr 2026 15:27:00 -0000 https://status.vapi.ai/incident/871401#0af584e7d1c5175d618d42df5189ca155afd2b44082730b06ca589e879763bde Incident The issue has been resolved. After applying the remediation, we monitored the affected systems and confirmed stable operation. All services are functioning normally. https://status.vapi.ai/incident/871401 Tue, 14 Apr 2026 15:12:00 -0000 https://status.vapi.ai/incident/871401#85fb57417c21dde8daca9b278f9ea5fec0eb476b59e05d4eb4bd5ccb06a09cdd Incident We identified and applied a remediation for the issue. The change has been deployed and we are actively monitoring to confirm full resolution. We will provide an update within 30 minutes or once we've confirmed stability. https://status.vapi.ai/incident/871401 Tue, 14 Apr 2026 14:57:00 -0000 https://status.vapi.ai/incident/871401#c0d2308d61ca58168b0d729dc5d0122e5bdfa8d8464213adc3220f08840f44bc Incident Our engineering team continues to actively work on restoring SIP services. We are still assessing the full scope of the issue and working toward a resolution. https://status.vapi.ai/incident/871401 Tue, 14 Apr 2026 14:25:00 -0000 https://status.vapi.ai/incident/871401#ffd6ce58cc26cb5a15260b97207af798d8ce8dae659c694d0f47d4771bdc911e Incident Upon further investigation, the impact to our SIP infrastructure is significantly greater than initially assessed. All SIP Calls services are currently experiencing full downtime, affecting inbound and outbound calls, transfers, and all in-call functionality. Our engineering team is fully engaged and working urgently to restore services. https://status.vapi.ai/incident/871401 Tue, 14 Apr 2026 13:32:00 -0000 https://status.vapi.ai/incident/871401#320c111ddeb909721d8f0e0a899c6b1b518fecf51618f57480d0cba0c4155386 Incident We are currently experiencing degradation in our SIP infrastructure, resulting in in-call failures including call transfers, increased latency, and other related issues. Our team is actively investigating and working to resolve the problem. We will provide updates as more information becomes available. https://status.vapi.ai/maintenance/869144 Sat, 11 Apr 2026 01:43:30 -0000 https://status.vapi.ai/incident/869144#d653a57238554929b87bb81e4fce4377daadd71128c6bf1f5cd08b378072e0ab Maintenance We'll be applying the latest patches and security fixes to our SIP SBC node. This is a routine procedure and should result in no more than a few seconds of downtime. https://status.vapi.ai/maintenance/869141 Sat, 11 Apr 2026 01:42:39 -0000 https://status.vapi.ai/incident/869141#d261f9be01667c0dc6904c7c245f3ac71ab177e0b4fb3890fd41ca951ebd888e Maintenance We'll be applying the latest patches and security fixes to our SIP SBC node. This is a routine procedure and should result in no more than a few seconds of downtime. https://status.vapi.ai/incident/863336 Thu, 02 Apr 2026 11:30:00 -0000 https://status.vapi.ai/incident/863336#53cea7f2ac152d5b4664a9828855408247be9adb98db7ecf0e76abace2e4d320 Incident We are currently observing elevated error rates affecting calls that use the Soniox transcriber. Impacted calls may terminate unexpectedly with the ended reason call.in-progress.error-vapifault-soniox-transcriber-failed. While we work to resolve this, we recommend switching to an alternative transcriber or configuring a transcriber fallback plan to ensure call continuity. You can set up fallbacks by following the guide here: https://docs.vapi.ai/customization/transcriber-fallback-plan We are actively monitoring the situation and will provide updates as more information becomes available. https://status.vapi.ai/incident/857606 Wed, 25 Mar 2026 20:53:00 -0000 https://status.vapi.ai/incident/857606#02cd21ac0ff66a6fbe37fc1f54779115dd562adbe292a497438d75d607804d2a Incident We observed an elevated rate of API errors from 1:28pm to 1:39pm PDT. The errors have since resolved. We are closely monitoring API performance and investigating the root cause. https://status.vapi.ai/incident/853214 Sat, 21 Mar 2026 05:46:00 -0000 https://status.vapi.ai/incident/853214#1ec488020290792118f0b7a2ae7ed9c9e3f45afd391fecdba457cb0754119c0f Incident **Incident Report, March 19, 2026** **Impact:** A service disruption affected inbound and outbound call reliability on the Daily and Weekly channel. Some calls failed to connect with `transport-never-connected`, `worker-not-available`, `worker-died`, and `deepgram-transcriber-failed` end reasons. **Timeline (all times PDT):** **12:20 PM** We detected elevated call failure rates on the Weekly production cluster. **12:22 PM** We published a status page incident and began investigating. **12:25 PM** We identified the trigger as an unanticipated surge in call volume that exceeded our provisioned cluster capacity and downstream rate limits with a model provider. **12:30 PM** We applied traffic controls and began working with the model provider to increase capacity. Call failures began declining. **1:40 PM** Call success rates returned to normal and held stable. First incident window closed. **~4:00 PM** A separate traffic spike re-triggered infrastructure constraints, leading to elevated failures. We began investigating immediately. **4:00 PM to 4:40 PM** We rebalanced traffic and migrated affected workloads to dedicated infrastructure to restore headroom on shared clusters. **4:50 PM** All mitigations took effect. Call success rates returned to normal. **4:50 PM to 8:10 PM** We continued active monitoring. No further failures observed. **8:10 PM** Second incident window closed. **Immediate Action Items:** Improve workload isolation and per-account capacity guardrails to prevent resource contention from cascading across the platform. **Note:** A full root cause analysis is underway and will be available upon request. We sincerely apologize for the disruption and thank you for your patience. https://status.vapi.ai/incident/853214 Fri, 20 Mar 2026 04:23:00 -0000 https://status.vapi.ai/incident/853214#5df2c9f8e885c73cda7da0ac38204d30539512f762dc54edc94ac23fede085f0 Incident The incident has been resolved and services have been stable since 4:50pm PT. We will continue monitoring and will publish additional details if necessary. https://status.vapi.ai/incident/853214 Fri, 20 Mar 2026 03:09:00 -0000 https://status.vapi.ai/incident/853214#984c2c2ace24e6eb3834f91fe9062c6b16f798379f2d04db5f108a968d1c679f Incident Our earlier mitigation is working and services have been stable since 4:50 PM. We have identified a potential root cause and are working on a permanent fix. We will share further updates once we deploy and validate the fix. https://status.vapi.ai/incident/853214 Fri, 20 Mar 2026 00:22:00 -0000 https://status.vapi.ai/incident/853214#2e4255ec6176ab936ad0884cb095c615f04ec928221d8c4b249268849a2d900d Incident The immediate mitigation we deployed is working and we are seeing call success rates continuing to recover. We are still investigating root cause and closely monitoring service performance. https://status.vapi.ai/incident/853214 Thu, 19 Mar 2026 23:50:00 -0000 https://status.vapi.ai/incident/853214#f0fc82ad196c936cce266a8db767d28628a3f7c8d4b79943f80942e52bc506e1 Incident We're seeing improved call success rates, but we're still monitoring the situation. https://status.vapi.ai/incident/853214 Thu, 19 Mar 2026 23:17:00 -0000 https://status.vapi.ai/incident/853214#c3784d0d08086ea8f46b1fb51f1e997a8a5d9d0f6acd7c19a883b1590df52232 Incident We're seeing elevated call failures on weekly, and the team is actively looking into it. https://status.vapi.ai/incident/853120 Thu, 19 Mar 2026 20:40:00 -0000 https://status.vapi.ai/incident/853120#354d58eb21545626600e9462990f349adf1b427b908b28653ed0ed2eaa87c7d2 Incident Resolved — The issue causing degraded performance has been identified and mitigated as of 13:45 PDT. All services are operating normally. We will continue to monitor and provide an update if needed. https://status.vapi.ai/incident/853120 Thu, 19 Mar 2026 20:22:00 -0000 https://status.vapi.ai/incident/853120#4be5c7d28bd73a2af59638b6c59bfaa6b5db5410dd132575f10e3407a2a4bd0b Incident We've partnered with Deepgram to apply a mitigation and are actively monitoring error rates. For an immediate workaround, affected users can switch to Deepgram Nova 3 or use a non-Deepgram transcriber. https://status.vapi.ai/incident/853120 Thu, 19 Mar 2026 19:51:00 -0000 https://status.vapi.ai/incident/853120#6367ee004b95c060207e4312a59ca11da57896a0717d13c8512049eaec2cf283 Incident We are seeing worker-not-available error rates going down in the weekly channel. We are also actively working with Deepgram to mitigate transcriber-failed errors in daily and weekly cluster. https://status.vapi.ai/incident/853120 Thu, 19 Mar 2026 19:32:00 -0000 https://status.vapi.ai/incident/853120#9d75a7851f747e2701bca61fa79cbadb0a61c6564b03cf09b82e5ae7c099a689 Incident The root cause for worker-not-available failures has been identified and we are actively deploying fixes to restore normal service. Some users may still experience failures or degraded performance while mitigation is in progress and fixes roll out. https://status.vapi.ai/incident/853120 Thu, 19 Mar 2026 19:21:00 -0000 https://status.vapi.ai/incident/853120#e70e2fb4dfabdcb8c139bba4564db00499e0f425dfa6ac755f634e4b564cfc20 Incident We are aware of elevated call failures rates on the weekly cluster with worker-not-available ended reason, and deepgram-transcriber-unavailable in both daily and weekly channels. Our team is actively investigating the issue. https://status.vapi.ai/incident/846049 Thu, 19 Mar 2026 18:51:00 -0000 https://status.vapi.ai/incident/846049#b51781609f443eb200d1af8b7e96afaf5ba26bc2ad64c6e661bcbec2e0bf33a6 Incident The issue has been resolved we're not seeing any further degradation https://status.vapi.ai/maintenance/851649 Tue, 17 Mar 2026 22:46:01 -0000 https://status.vapi.ai/incident/851649#5eb65de955ff90a46b3914711615e3ab1d042fe6d125c5169a68fc013139a7a3 Maintenance We need to apply updates to our SIP server, which will require a restart. During this time, there may be a brief service disruption. The activity is low risk and should be completed within 15 seconds. https://status.vapi.ai/incident/847828 Thu, 12 Mar 2026 16:22:00 -0000 https://status.vapi.ai/incident/847828#bbdb7cf035399a9373ccd33f319621f0a0fd0012ed3b5437f80274a507f50b13 Incident Resolved — The issue causing degraded performance has been identified and mitigated as of 8:22 AM. All services are operating normally. We will continue to monitor and provide an update if needed. https://status.vapi.ai/incident/847828 Thu, 12 Mar 2026 15:23:00 -0000 https://status.vapi.ai/incident/847828#6d3aecc1793582c0fc4442a8940e129c8ed340d0abb259d20e930f09d40b7794 Incident High failure rate in connecting calls and API in the daily channel. Team is working on resolving it. https://status.vapi.ai/incident/846049 Tue, 10 Mar 2026 12:46:00 -0000 https://status.vapi.ai/incident/846049#32f9f2185d9f6e3c552d7057038d5964864cc8b820fc504d5ffebd57b1c63dd1 Incident We're noticing a small percentage of calls using GPT 5.2 fail with an internal error during inference from OpenAI's side. We've reached out to the team and are closely monitoring the situation. In the meantime, we recommend switching to another model as we're seeing the degradation only on 5.2 currently. https://status.vapi.ai/maintenance/845585 Mon, 09 Mar 2026 22:33:49 -0000 https://status.vapi.ai/incident/845585#96529491b2f49a27d31943239c6a118c3735014a590de90c446a6a6fdbeba103 Maintenance Our SIP service TLS certificate is approaching its expiration date and needs to be renewed. To apply the updated certificate, a brief restart of the SIP service will be required. No prolonged disruption to the service is expected. https://status.vapi.ai/incident/840264 Wed, 04 Mar 2026 16:17:00 -0000 https://status.vapi.ai/incident/840264#304cb5d51fc9af638fdece66d154f08819643cb862a108bf47236509ad7e044a Incident The issue has been resolved and all systems are operational. https://status.vapi.ai/incident/839609 Wed, 04 Mar 2026 16:04:00 -0000 https://status.vapi.ai/incident/839609#24325fe434d524f2b351e087db0c12f1593c5aa2c7ce1182435018024c50a024 Incident The issue has been resolved and the voice is currently usable. We still recommend setting up fallbacks for any voices for the future to avoid call drops - https://docs.vapi.ai/voice-fallback-plan https://status.vapi.ai/incident/840264 Wed, 04 Mar 2026 16:03:00 -0000 https://status.vapi.ai/incident/840264#b7b23cbc3a05789d4cb49c2c7d50e0929efaef9c70e6513785313f6b5b64217e Incident We're noticing some call degradation primarily on the Daily channel. We are monitoring the situation and will update as we know more. https://status.vapi.ai/incident/839609 Wed, 04 Mar 2026 02:31:00 -0000 https://status.vapi.ai/incident/839609#e5fb4ac499f5cf6aa787fb226f77ed5b833b28fce31cdac86467b956ffd456c4 Incident We're noticing issues with calls using the Vapi voice "Emma". If you are using this voice, we recommend switching to another voice while this is resolved, and add voice fallbacks to prevent complete failures - https://docs.vapi.ai/voice-fallback-plan No other voices are currently impacted. We will update the status page as we know more. https://status.vapi.ai/incident/832329 Thu, 26 Feb 2026 17:08:00 -0000 https://status.vapi.ai/incident/832329#36f7f43f7d538fe3528a574a3e3b6ce6c5848d69be677bb1ba9475cc87d56373 Incident Our provider has confirmed the issue is specific to accessing projects and seems to not include authentication. They are still resolving the issue from their end, but we are marking the issue as resolved. If customers continue to see issues with authentication, please reach out to support@vapi.ai https://status.vapi.ai/incident/833083 Thu, 26 Feb 2026 01:59:00 -0000 https://status.vapi.ai/incident/833083#d960f75e523f7589e67724f439f653dacba6ca2842c93f61339741927cfb449a Incident We have not seen the issue since ~3:50pm today. We have determined the root cause and are rolling out a fix to improve stability in the `daily` channel. # Incident Report — Daily Channel Call Failures (February 25, 2026) ## Impact Between 7:27 AM – 3:59 PM PST, approximately 19,527 calls failed on the Daily channel due to call worker failures. All Daily channel users were impacted. The Weekly channel was not affected. ## Timeline (all times in PST) **7:27 AM** — Degraded call reliability detected on the Daily channel. Status page updated and investigation begins immediately. **8:33 AM** — Issue escalated. Team recommends affected customers switch to the Weekly channel while investigation continues. Status page updated. **9:04 AM** — Team begins proactive outreach to guide affected customers to the Weekly channel. **10:55 AM** — Additional call failures observed on Daily after a brief period of stability. Investigation continues. **11:00 AM** — Rolled back previous deployment. Did not observe any significant improvement. **1:30 PM** — Continued investigating the issue. **3:59 PM** — No further issues observed. **6:00 PM** — Released a fix to improve stability in the Daily channel. Incident resolved. ## What Went Well - The issue was detected and acknowledged quickly. - A dedicated incident response was organized promptly to focus investigation. - Teams were notified early and guided affected customers to switch to the Weekly channel. ## Action Items - Isolate background operations from call handling - Strengthen deployment validation - Improve resilience under load - Expand monitoring and alerting ## Note This report is intended as a summary of the incident timeline, impact, and immediate action items. A deeper root cause analysis is available upon request. This issue impacted the Daily channel only. Customers desiring increased stability (at the cost of delayed access to features) can switch to the Weekly channel by navigating to **Organization Settings** on the Vapi Dashboard and changing the Channel to **"weekly"**. https://status.vapi.ai/incident/833083 Wed, 25 Feb 2026 19:12:00 -0000 https://status.vapi.ai/incident/833083#1a5adba1beeb5e73a07bdce1f5663eff2720adbed947530bcedc4ed7736bbc74 Incident We are seeing intermittent failures related to the earlier incident, slightly higher than normal amounts. The team is investigating and will share additional updates here. Degradation is still limited to `daily` channel. If you are seeing instability we suggest switching to the `weekly` channel (in Organization Settings → Channel). https://status.vapi.ai/incident/832374 Wed, 25 Feb 2026 17:50:00 -0000 https://status.vapi.ai/incident/832374#8e267946a34af6f45ad3da3cb4f68356a389140cf2268817d17ce1e9caa314eb Incident Incident report: **Impact:** A service disruption affected call reliability on the Weekly channel. Some calls ended unexpectedly with `worker-not-available` or `worker-died` end reasons. **Timeline (all times PT):** - **8:07 AM** - We detected a burst of call failures across the platform. - **8:16 AM** - Automated monitoring alert fired. We acknowledged and began investigating. - **8:42 AM** - We scoped the impact across affected accounts. - **8:47 AM** - The issue self-resolved. We identified the root cause as resource contention in our call processing infrastructure during a traffic spike. - **9:18 AM** - We completed an initial root cause analysis and identified an underlying bottleneck in our call queue infrastructure. - **11:13 AM** - A related issue resurfaced due to cascading effects from the earlier contention. We began investigating immediately. - **11:25 AM** - We published a status page to notify customers. - **11:38 AM** - We confirmed the root cause as CPU contention between infrastructure components. - **11:39 AM** - We applied a mitigation. Call queue metrics began recovering. - **11:45 AM** - We updated the status page with the identified cause and fix. - **11:46 AM** - Error rates began declining. We continued active monitoring. - **1:11 PM** - We declared resolution on the status page. - **~1:35 PM** - A brief secondary spike occurred during an infrastructure resource adjustment. We responded immediately. - **3:21 PM** - All systems fully stabilized. **Action Items** Enforce resource limits across processing components and improve infrastructure isolation for critical call processing. **Note** A full root cause analysis is underway and will be available upon request. We sincerely apologize for the disruption and thank you for your patience. https://status.vapi.ai/incident/833083 Wed, 25 Feb 2026 16:56:00 -0000 https://status.vapi.ai/incident/833083#1581c620ecea317f3dad3478cc375f953d024e372ba2cef8333d7a8c42b4a62b Incident The issue is resolved, the team is monitoring and continuing to work on a fix for the recurrent issue. https://status.vapi.ai/incident/833083 Wed, 25 Feb 2026 16:33:00 -0000 https://status.vapi.ai/incident/833083#fc5b0fab6c02d12414def1de60ce44389a0007be9513e7521604d443a3cc577e Incident We have identified the root cause. We did see the issue spike up again during investigation. The team is working on a fix and will update here. In the meantime we suggest customers switch to the Weekly channel for more stability. https://status.vapi.ai/incident/833083 Wed, 25 Feb 2026 15:27:00 -0000 https://status.vapi.ai/incident/833083#f62b1936cb663db3ba58659aaf2c3dc2e5630af799c889069acc801ab575ddcd Incident We are seeing calls being dropped on the Daily channel with ended reason "call.in-progress.error-vapifault-worker-died". The team is looking into it and will update here. https://status.vapi.ai/incident/832374 Tue, 24 Feb 2026 23:21:00 -0000 https://status.vapi.ai/incident/832374#ceb6c6a12d670f0ec7193715c3cb5731871986445cdb889796a4aa6d8b7e0c9b Incident At ~1:35pm roughly 211 more calls dropped on the Weekly cluster. The team is investigating the matter, but we do not see any on-going degradation of service after 2pm PT. We will share an incident report update with the full timeline and action items today. Internally, we are working on a more in-depth root cause analysis to understand deeply why our systems failed and what action we will take to make our platform more stable. https://status.vapi.ai/incident/832374 Tue, 24 Feb 2026 21:11:00 -0000 https://status.vapi.ai/incident/832374#32b7013c6688aafc7434a3e867c28fb90fe36dffe3745e0f8ab35fc032c4f547 Incident The issue is now resolved. https://status.vapi.ai/incident/832374 Tue, 24 Feb 2026 19:45:00 -0000 https://status.vapi.ai/incident/832374#03898747a6fa255fd793c56979fea7bd58014cdce7bc91a2873ae17075801b7a Incident We identified an issue causing a small number of calls to terminate unexpectedly with worker-not-available or worker-died end reasons. A fix has been deployed and error rates are declining. We are continuing to monitor and will provide another update once fully resolved. https://status.vapi.ai/incident/832374 Tue, 24 Feb 2026 19:25:00 -0000 https://status.vapi.ai/incident/832374#64342ce7a0687591132a1a09cd3951b0e61f4c94edde46c2cbfd7d1d52647716 Incident We are seeing calls degraded on Weekly channel. The team is looking into the issue and will share updates here. https://status.vapi.ai/incident/832329 Tue, 24 Feb 2026 18:33:00 -0000 https://status.vapi.ai/incident/832329#f7781f1316a8cfeb7b5ff1c61972a51f46cb2f42f02dde0b8de37353b52a1ae0 Incident Our auth service provider is reporting a degradation specifically in India. Some customers in that region will see issues with login. See our providers status page for live updates: https://status.supabase.com/incidents/xmgq69x4brfk. https://status.vapi.ai/incident/831494 Mon, 23 Feb 2026 18:09:00 -0000 https://status.vapi.ai/incident/831494#97e4497eef8d8ef214551be8396ecedd837e217acd54f5ffbe4a14fb0d85ff8c Incident The issue is resolved as of 10:05am PST. ## Incident Report ### Impact Between 9:10–10:05 AM, 37,806 calls were dropped due to call worker failures. All Daily users were impacted. ### Timeline (all times in PST) 9:02 AM — On-call engineer notices pods crashing in the Daily cluster. 9:11 AM — Black box probe alert fires; acknowledged by on-call engineer, triggering investigation. 9:27 AM — Issue escalates to the point of impacting all calls on Daily. 9:30 AM — Status page created to inform users of impact and request they switch to the Weekly channel. 9:34 AM — Incident team assembles. 9:37 AM — Rollback to previous deployment is initiated. Due to a large backlog of unprocessed jobs, rollback is delayed waiting for an excessive number of pods to become ready. 10:05 AM — Forceful cutover is initiated and service is restored. ### What Went Well Monitoring detected the issue before it became widespread. On-call engineer assembled the incident team quickly. ### Action Items Improve emergency rollback procedure to bypass or relax pod readiness checks during incidents, enabling faster cutover. Continue ongoing observability improvements to reduce MTTD. ### Note A full root cause analysis is underway and available upon request. This report is intended as a summary of the incident timeline, impact, and immediate action items. Note that this issue impacted the Daily cluster only. Customers desiring increased stability (at the cost of delayed access to features) should switch to the Weekly channel by navigating to Organization Settings on the Vapi Dashboard and changing the Channel to "weekly". https://status.vapi.ai/incident/831494 Mon, 23 Feb 2026 17:52:00 -0000 https://status.vapi.ai/incident/831494#fe035841c0c82a76f7b2307589267f66acb9ed1d9b77e3d32179117275bf7072 Incident We are rolling back to an earlier deployment. We are seeing calls getting picked up, but will update here once resolved. https://status.vapi.ai/incident/831494 Mon, 23 Feb 2026 17:30:00 -0000 https://status.vapi.ai/incident/831494#ce1095467be60eeac14672bc65dc9e49591a4529b17dc6e2fa3d127a6bd34040 Incident We are seeing decreased success rate in calls on the `daily` channel. The team is investigating and we will post updates here. In the meantime, we highly recommend switching to `weekly` channel to mitigate service disruption. https://status.vapi.ai/incident/824613 Fri, 13 Feb 2026 05:05:00 -0000 https://status.vapi.ai/incident/824613#d610e560fa7d0de92472bd39ffebd97bb0b6fea02d19a1babf0e1094b0deb4bf Incident Email authentication for the Vapi dashboard has been restored. Users should now be able to sign in normally using their email credentials. https://status.vapi.ai/incident/824613 Thu, 12 Feb 2026 20:57:00 -0000 https://status.vapi.ai/incident/824613#f2afb93f781803ba0437713b5d4f2e72bec00afc2c264301ba182ae581740e05 Incident email authentication for the vapi dashboard was experiencing issues. users were unable to sign in using their email credentials. https://status.vapi.ai/maintenance/824340 Thu, 12 Feb 2026 19:22:35 -0000 https://status.vapi.ai/incident/824340#e504e837a95a52478df28644d57756e643ff39c8a39b4d3302acf3a6ea718780 Maintenance We need to apply patches to our SIP server, which will require a restart. During this time, there may be a brief service disruption. The activity is low risk and should be completed within seconds. https://status.vapi.ai/incident/824251 Thu, 12 Feb 2026 18:58:00 -0000 https://status.vapi.ai/incident/824251#6b005e5beb99fe0f74232cb1cae9123e72f6225667eadca42ef189b139fd94c7 Incident The CDC ClickPipes issue was resolved, and we've confirmed calls made during and after the outage are now appearing in the Vapi dashboard. This issue has now been resolved. https://status.vapi.ai/incident/824251 Thu, 12 Feb 2026 17:34:00 -0000 https://status.vapi.ai/incident/824251#9f24ef212b23cf6396e2945d3f7ecf4245fa95e2d9d7580dce8d6a7ffe5a960b Incident We've identified that the issue is related to the ongoing CDC ClickPipes outage (see: https://status.clickhouse.com/incidents/01KH9BE0WY28P4Z48DQ7FPS4DQ). https://status.vapi.ai/incident/824251 Thu, 12 Feb 2026 17:08:00 -0000 https://status.vapi.ai/incident/824251#a825500f248fdbef453185ec55566b4ef68a84d5ce8c706761623933b206476b Incident We are currently observing that recent call logs are not showing up on the Vapi dashboard since around 7:30am PST. Calls are still being placed. We are actively monitoring the situation and will provide updates as more information becomes available. https://status.vapi.ai/incident/823436 Wed, 11 Feb 2026 20:30:00 -0000 https://status.vapi.ai/incident/823436#7fa639d7dcc346e24911264e028e1706fcbfdab8baf94ab91ad3c5dd0845982a Incident Deepgram had an issue while upgrading their system, which caused 429 errors. They've fixed it and are implementing controls to prevent recurrence. https://status.vapi.ai/incident/823436 Wed, 11 Feb 2026 17:10:00 -0000 https://status.vapi.ai/incident/823436#bb0adf31170a7409804b1c6dd76049ee5c8e2abf77351d00e49d2c70e8bb3e4a Incident We are currently observing elevated error rates affecting calls that use the Deepgram transcriber. Impacted calls may terminate unexpectedly with the ended reason call.in-progress.error-vapifault-deepgram-transcriber-failed. While we work to resolve this, we recommend switching to an alternative transcriber or configuring a transcriber fallback plan to ensure call continuity. You can set up fallbacks by following the guide here: https://docs.vapi.ai/customization/transcriber-fallback-plan We are actively monitoring the situation and will provide updates as more information becomes available. https://status.vapi.ai/incident/818473 Wed, 04 Feb 2026 14:32:00 -0000 https://status.vapi.ai/incident/818473#b540297f3bc5d5acd82f36307eb99e7678f8201473b4cc9eda2e225e9d8e3227 Incident Errors have decreased and the incident has been resolved. We'll post an RCA soon. https://status.vapi.ai/incident/818473 Wed, 04 Feb 2026 14:24:00 -0000 https://status.vapi.ai/incident/818473#3c3c4863a153751720f5351c4a5f28e371de18867f694ccc9cb589d036f3387e Incident We've identified the issue and have deployed a potential fix - we will continue to monitor the situation. https://status.vapi.ai/incident/818473 Wed, 04 Feb 2026 14:14:00 -0000 https://status.vapi.ai/incident/818473#8b1f594e61d0bea32dd6a0604036bc2f65c472dd45b707e248c36ebdc255a6d2 Incident The incident has been mitigated. Between 5:00 AM PT and 6:12 AM PT, API and call execution experienced reduced success rates. Services has been fully restored and is operating normally. https://status.vapi.ai/incident/809181 Tue, 03 Feb 2026 21:16:00 -0000 https://status.vapi.ai/incident/809181#12f78c93de9b6020aff066baa19f8ddee40fe3d849600f8545597b73246ea05b Incident Google is still resolving capacity issues on their end, but we have put a mitigation in place to resolve this for gemini-2.5-flash. Please switch to this model when using Google, if you require another model reach out to support@vapi.ai. We are continuing to monitor and work with the Google team to resolve. https://status.vapi.ai/incident/809181 Tue, 27 Jan 2026 17:47:00 -0000 https://status.vapi.ai/incident/809181#a49460a22f262ced6d88d0ba3af864e1f72792199668c7cab2637d912cfadec3 Incident We are still seeing rate limiting issues for Google LLMs and are looking into another fix we can implement to mitigate it. This is likely caused by regional exhaustion of Google Vertex AI resources rather than us hitting an org-level quota. https://status.vapi.ai/incident/809181 Tue, 27 Jan 2026 06:50:00 -0000 https://status.vapi.ai/incident/809181#f56b91a3bbf655bc3dcdafa59098dbe23eff71cad9b7bcae66dde1ff8b231f06 Incident Google has confirmed the underlying issue is resolved. We’re continuing to deploy a mitigation to ensure this doesn’t impact customers if it recurs. https://status.vapi.ai/incident/809181 Mon, 26 Jan 2026 04:03:00 -0000 https://status.vapi.ai/incident/809181#e4dba0203117f84a3cf043fa34b68ca373b2cc19d6ad58c5057f03725702c653 Incident Google has not resolved the issue on their side, we have requested an updated timeline. Our team is working on implementing fallbacks for the services impacted by the Google degradation (the query tool). https://status.vapi.ai/incident/809181 Thu, 22 Jan 2026 18:47:00 -0000 https://status.vapi.ai/incident/809181#c6f70425a0d63b0535a64d8ba015ccedea5015a9d398758a4ddcb0dcb35deafd Incident Google is again reporting issues with the Vertex AI API that is impacting both our default and fallback Gemini clients. Consider using a different model. We are working with the provider to resolve this and will update here. https://status.vapi.ai/incident/809181 Thu, 22 Jan 2026 07:30:00 -0000 https://status.vapi.ai/incident/809181#0ab115a6ddec9474d52234f1f55057facd32a1b0034cd966ea5405af7c1c9387 Incident We have confirmed with the provider that the issue is from their end. We have implemented fallbacks that should help mitigate this issue going forward. We apologize for any disruption to service as a result of this issue. https://status.vapi.ai/incident/809181 Wed, 21 Jan 2026 20:11:00 -0000 https://status.vapi.ai/incident/809181#4d91b03aa8a17973b8554f71730eeb8e70d4efcbfde3e739434cc8d072180fae Incident **Google/Gemini Service Degradation - Immediate Workarounds** We're experiencing intermittent rate limiting from Google affecting several Vapi features. We're working with Google to resolve this. In the meantime, there are immediate workarounds for affected features. - Model (LLM): Gemini models may intermittently fail. - Workaround one - switch to a different model (e.g., GPT 4.1) - Workaround two - [obtain an API key](https://aistudio.google.com/app/api-keys) from Google and use that. - Vapi Dashboard → Settings → Integrations → Custom Credentials - Transcriber (STT): Gemini-based transcription may intermittently fail - Two workarounds - switch your primary or fallback transcriber to a different model (e.g., Deepgram Nova 3) or obtain an API key from Google and use that. - [Voicemail detection](https://docs.vapi.ai/tools/voicemail-tool): may intermittently fail if "provider" is set to "google" - Two workarounds. Switch to "openai" or "twilio" provider (if using Twilio telephony) or turn off **`voicemailDetection`** and switch to Voicemail tool - [Query tool](https://docs.vapi.ai/knowledge-base/using-query-tool): may intermittently fail since it relies on Google infrastructure - Two workarounds (both high effort) - switch to a custom knowledgebase or use a function tool to replicate behavior - [Structured Outputs](https://docs.vapi.ai/assistants/structured-outputs-quickstart): Gemini models may intermittently fail. - Workaround - switch to a different model provider: OpenAI or Anthropic - [Speech-to-Speech](https://docs.vapi.ai/openai-realtime): Gemini models may intermittently fail. - Workaround - switch to a different model provider: OpenAI https://status.vapi.ai/incident/809181 Wed, 21 Jan 2026 19:40:00 -0000 https://status.vapi.ai/incident/809181#3cc62811313738e4c232d188067840f60dbe95718a79ad883d513cd9a108bb7a Incident We are hitting rate limits again with our Google Gemini models. We are working with the vendor to resolve this issue. Please consider using another model at this time or implementing fallbacks. https://status.vapi.ai/incident/808504 Wed, 21 Jan 2026 04:19:00 -0000 https://status.vapi.ai/incident/808504#75f67e2148c2e61275d84c417c68db265844ed49fe6a79d0ae4c990a7e8f09be Incident We have pushed a fix and this issue should be resolved. The team will continue to monitor. https://status.vapi.ai/incident/808504 Wed, 21 Jan 2026 00:10:00 -0000 https://status.vapi.ai/incident/808504#7a5636e503b13bbef73b0ddc0e4aed883be3e11da83e219799be66fecd890fa1 Incident We have identified the issue and are pushing a fix now. https://status.vapi.ai/incident/808504 Tue, 20 Jan 2026 23:32:00 -0000 https://status.vapi.ai/incident/808504#3b1f595d7a771fc6f462153cbd69dd7ce082e92bbcb7d3f97b1c8b64123872b1 Incident We are seeing an issue with our own Google Vertex AI API key resulting in increased 429 errors using Gemini models. Please consider using a different model provider if you are experiencing this issue. Customers bringing their own key should not be impacted. The team is looking into this issue and will update here. https://status.vapi.ai/maintenance/808464 Tue, 20 Jan 2026 21:55:31 -0000 https://status.vapi.ai/incident/808464#b89e04c02c96bfca6c6dd9366d795d1e4d46df99a4d2cba0146a9ed78d279d75 Maintenance We're doing an upgrade to our SIP database which might cause a few minutes of downtime and instability. https://status.vapi.ai/incident/807551 Mon, 19 Jan 2026 18:38:00 -0000 https://status.vapi.ai/incident/807551#7874b714454fa58ca8805ea3c6d28f2ca4b1f416d93518371f31284e7298a8f0 Incident We experienced a temporary increase in call connection errors caused by worker unavailability. The issue has since been resolved. Impact was limited to the daily channel; the weekly channel was not affected. https://status.vapi.ai/maintenance/804803 Thu, 15 Jan 2026 04:00:21 -0000 https://status.vapi.ai/incident/804803#f37a3fb6c91786505808a727a6af6d0d3d53319cd72022d27bddbdda20f46de9 Maintenance We need to perform resizing of our existing SIP database. The operation should finish within a few seconds. https://status.vapi.ai/incident/800838 Thu, 08 Jan 2026 18:11:00 -0000 https://status.vapi.ai/incident/800838#ee9a1114381505acef8f72c9491239deebdb1b108ce7b3dcef15e39d5f8ef3ea Incident We are seeing decreased success rate in calls on the `daily` channel. The team is investigating and we will post updates here. https://status.vapi.ai/incident/793239 Wed, 24 Dec 2025 07:21:00 -0000 https://status.vapi.ai/incident/793239#5e9c6f6c2cf967e727a2bb2228d621fe5379a774a8d73074c53d84574f0e2261 Incident We have reverted the change and tested to confirm the issue is resolved. https://status.vapi.ai/maintenance/793418 Wed, 24 Dec 2025 06:29:15 -0000 https://status.vapi.ai/incident/793418#68169ebf084085e1a3d79fd96cf850a6eec1b13fd255ce1bf65b8403e410ee6f Maintenance A continuation of yesterday's maintenance will be completed tonight. We anticipate minimal disruption to services. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/incident/788461 Tue, 23 Dec 2025 23:18:00 -0000 https://status.vapi.ai/incident/788461#0a4b9dc0b211fdefd3f877d85a547586a1fdd71ab55b4b5b0fd2da9602b92146 Incident # [IR] Dec 17th — Call Worker Degradation — Object Storage Upload Errors ## Summary On December 17, 2025, at 10:25 AM PST, we observed degradation in our Call Worker service. The issue was caused by Call Workers becoming blocked while uploading call recordings to a downstream object storage provider facing an outage of their own. The incident was fully resolved by 11:02 AM PST, once the downstream provider recovered and Call Workers returned to normal operation. ## Timeline (PST) - **10:25 AM** — Initial call degradation alert triggered - **10:40 AM** — Investigation began - **10:45 AM** — Downstream provider partially recovered - **10:52 AM** — Downstream provider fully recovered - **11:02 AM** — Call Workers fully recovered ## Root Cause A downstream object storage provider experienced a partial outage, during which call recording upload requests began failing or stalling. Requests either timed out or returned 502 errors. These stalled upload operations increased processing time within Call Workers, leading to worker exhaustion. Due to this resource saturation, the system was unable to scale quickly enough to accept new incoming calls, resulting in dropped or unaccepted calls during the affected period. ## Impact For approximately 30 minutes, a subset of calls could not be accepted or were dropped due to unavailable or terminated Call Workers. There was no data loss. **Calls not picked up (worker not available):** - Daily organizations: 15,555 - Weekly organizations: 478 ## What Went Well - Autoscaling eventually resolved the issue of workers being unavailable without the need for manual intervention. ## What Went Poorly - No fallback mechanism was in place for object storage uploads. - Monitoring did not quickly identify the downstream dependency as the root cause. ## Remediation - [ ] Make the object storage upload process asynchronous - [ ] Add more aggressive timeouts and retries for upload operations - [x] Investigate procedures for manually scaling capacity during incidents - [x] Add monitoring for object storage upload errors --- If working on realtime distributed systems excites you, consider applying: https://jobs.ashbyhq.com/vapi/295f5269-1bb5-4740-81fa-9716adc32ad5 https://status.vapi.ai/incident/793239 Tue, 23 Dec 2025 22:48:00 -0000 https://status.vapi.ai/incident/793239#0e83ad86a09ed5a329fbd6272b1d535944f171cd3bcc9da2e4091dbf0a914cc3 Incident A code bug is causing the final call transcripts to show duplicate assistant messages when using `modelOutputInMessagesEnabled`. Calls are working fine, but post-call processing may be impacted. This issue is impacting both `weekly` and `daily` channels. The team is working to revert the offending change. We will update here. https://status.vapi.ai/incident/788461 Wed, 17 Dec 2025 19:20:00 -0000 https://status.vapi.ai/incident/788461#02640499745c8598a79dd4b66123a322fbc0743e7f45671f20152b667d620ad3 Incident The system has recovered. The team is monitoring, and we will update here with a full RCA. https://status.vapi.ai/incident/788461 Wed, 17 Dec 2025 19:06:00 -0000 https://status.vapi.ai/incident/788461#2100d0cb083c6e6f46bba4db4115172a2d27870c5549e9fe4bdad6c617bba7ac Incident We have detected an issue with our call workers not scaling to meet demand. The team is investigating and will update here. https://status.vapi.ai/maintenance/787241 Tue, 16 Dec 2025 03:31:25 -0000 https://status.vapi.ai/incident/787241#58c1607f140fdfe1d16ef4f170e24bc30bfcfa19ef4da4817a854062e7bbd32c Maintenance We'll be adjusting our database configuration during a brief maintenance window of up to 1 hour. During this period, API requests may experience intermittent delays or errors, but we do not anticipate any significant disruption. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/maintenance/785619 Sat, 13 Dec 2025 04:00:59 -0000 https://status.vapi.ai/incident/785619#950be9e9582774a146b457bc887c6e5ef7f974718c6d820ba35a89dbb09b6ba7 Maintenance We need to perform an upgrade on our SIP servers, which needs a restart of some critical services. We expect a few seconds of downtime, and the service should recover itself shortly. https://status.vapi.ai/incident/783967 Wed, 10 Dec 2025 20:18:00 -0000 https://status.vapi.ai/incident/783967#c347d694f633728ac11ff9f2fa110153e6de611cc3f8e5e9d5a75b352597f93d Incident Deepgram has resolved the issue, and we're seeing calls go through fine. We will be closely monitoring the issue. We highly recommend setting up transcriber fallbacks to avoid call failures in situations like this. https://docs.vapi.ai/api-reference/assistants/create#request.body.transcriber.DeepgramTranscriber.fallbackPlan https://status.vapi.ai/incident/783967 Wed, 10 Dec 2025 19:49:00 -0000 https://status.vapi.ai/incident/783967#6cb2da61667740cc1c5331727956aa17e51e09a85dbcfee412d75ed155db291b Incident We're noticing some calls failing with issues with the deepgram transcriber, we're actively monitoring it. In the meantime, we recommend switching to a different transcriber and setting up Transcriber Fallbacks to prevent calls from failing. https://status.vapi.ai/incident/781023 Sat, 06 Dec 2025 00:26:00 -0000 https://status.vapi.ai/incident/781023#90b3f4c1552bb50d05ffa7d4f155a27c6e0b404fdb43542ebc93147bd798f3c2 Incident The issue has been resolved and we will continue monitoring the situation. We recommend setting up transcriber fallbacks to avoid any failed calls in such situations - https://docs.vapi.ai/api-reference/assistants/create#request.body.transcriber.ElevenLabsTranscriber.fallbackPlan https://status.vapi.ai/incident/781023 Fri, 05 Dec 2025 23:33:00 -0000 https://status.vapi.ai/incident/781023#79708a3ace5df717a1ab01a6c9ccf18fc1fe5503df3eae2dfc96abd520ab1b27 Incident Transcriber performance for ElevenLabs STT is currently degraded with some requests being dropped. While we monitor the situation, we recommend switching to another transcriber or setting up fallbacks - https://docs.vapi.ai/api-reference/assistants/create#request.body.transcriber.ElevenLabsTranscriber.fallbackPlan Status Report from ElevenLabs - https://status.elevenlabs.io/incidents/01KBRDKA2CKANKJK182W1WXFXH https://status.vapi.ai/incident/780568 Fri, 05 Dec 2025 09:27:00 -0000 https://status.vapi.ai/incident/780568#e0c4f05bcfbed0b2fd849049011160bc6292ee039a78edc42f3f00962bdc95b7 Incident The Vapi dashboard is now available after cloudflare have applied the fix. We will continue to monitor to ensure no further disruptions. https://status.vapi.ai/maintenance/777732 Mon, 01 Dec 2025 22:29:38 -0000 https://status.vapi.ai/incident/777732#0d2342d1a9116b9e808b6f7bdd07714a94e6f24d74c3307321ea5628bae65c2d Maintenance We’re performing a planned resize of our authentication database, which will require a brief restart of the instance. During this window, users may experience elevated errors when signing in or signing up. Call functionality will not be affected. The process is typically completed within one minute. https://status.vapi.ai/maintenance/774887 Wed, 26 Nov 2025 23:18:54 -0000 https://status.vapi.ai/incident/774887#669daaff986c33779c3fc739c30d1526b0d42e81eb54773b69dc29dc918310a0 Maintenance We will be performing critical maintenance on our SIP infrastructure. Calls may be impacted during this period. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/maintenance/761704 Mon, 10 Nov 2025 19:40:57 -0000 https://status.vapi.ai/incident/761704#7527734f28dd220faea37abcf7b450367acf5c6e2adf49b91fcda6c7d60048c8 Maintenance We are seeing moderately higher latency on our SIP database (separate from our core application databases) resulting in slightly higher SIP response times (1-1.5 seconds). We will be performing critical maintenance on our database to remediate this issue. https://status.vapi.ai/maintenance/760148 Fri, 07 Nov 2025 22:27:05 -0000 https://status.vapi.ai/incident/760148#aa086f281b403d1940f5562d211a5fccdbdfdf69f8431bddc5372a3dcbde2c0c Maintenance We will be performing critical maintenance on our SIP infrastructure. Calls may be impacted during this period. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/maintenance/758083 Tue, 04 Nov 2025 23:15:41 -0000 https://status.vapi.ai/incident/758083#2dd04ed2ee25c5495a0603df45f6762459b2f5164e707a5365c9bb129f437124 Maintenance We'll be adjusting our database configuration during a brief maintenance window of up to 1 hour. During this period, API requests may experience intermittent delays or errors, but we do not anticipate any significant disruption. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/maintenance/758079 Tue, 04 Nov 2025 23:13:23 -0000 https://status.vapi.ai/incident/758079#75c52968d56747f09ec59a3db5ad51cb68e17014a08b6f89cf95a009c16952d1 Maintenance We'll be adjusting our database configuration during a brief maintenance window of up to 1 hour. During this period, API requests may experience intermittent delays or errors, but we do not anticipate any significant disruption. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/maintenance/754139 Wed, 29 Oct 2025 23:02:51 -0000 https://status.vapi.ai/incident/754139#c3100f531b02603b292233515abb5be40aceb3af5c2b2c7068beebc1f13ff18a Maintenance We are making a minor change to our SIP service (hosted at sip.vapi.ai) that may result in some downtime. https://status.vapi.ai/maintenance/663861 Thu, 31 Jul 2025 02:35:30 -0000 https://status.vapi.ai/incident/663861#5697f4c2940e8c72c0d965677d0216f2a72acf40c0ce60c4b2e1020192ee80d3 Maintenance We need to perform an upgrade on our SIP service. Therefore, the SIP service needs a restart. It should be a quick restart but there might be some disruption with ongoing calls and incoming calls, during the restart. https://status.vapi.ai/maintenance/624009 Tue, 22 Jul 2025 18:00:00 -0000 https://status.vapi.ai/incident/624009#eb41bf4e5e77d9bfbd65dcbe678361cdc5ff37b6dc20e49b28cccc01ea23b8d0 Maintenance We are rolling out an important update to our database. Call logs and analytics may be impacted during this period. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/maintenance/622184 Sat, 19 Jul 2025 00:35:22 -0000 https://status.vapi.ai/incident/622184#74d93083c5f77cec4eef968d9f9c3bc409c5bd1e9ecd04394e91a8967001c3f5 Maintenance We are rolling out security patches and important updates to our database. This would need a restart of all our database servers. Restarts are quick but there could be a few seconds of intermittent unavailability. https://status.vapi.ai/maintenance/613441 Thu, 03 Jul 2025 04:57:58 -0000 https://status.vapi.ai/incident/613441#8b5cc5c1982e9e57cf3e8202763f311475977f3bc05a172141bb08056b7a3a6a Maintenance We will be making changes to our SIP infrastructure which may result in some service degradation, especially for SIP REFER's and outbound calls. https://status.vapi.ai/maintenance/611086 Sun, 29 Jun 2025 03:30:20 -0000 https://status.vapi.ai/incident/611086#03333700f42d153bfcba7952eeaad980e3c1632d500477d32abb0f4eeffecccc Maintenance We'll be adjusting our database configuration during a brief maintenance window of up to 30 minutes. During this period, API requests may experience intermittent delays or errors, but we do not anticipate any significant disruption. We appreciate your patience and apologize for any inconvenience this may cause. https://status.vapi.ai/maintenance/608654 Wed, 25 Jun 2025 02:34:23 -0000 https://status.vapi.ai/incident/608654#9aa7c3a2e879c94e3093c5aa25471321b9364499d1e9dea34bcb5d43e5cfdcc6 Maintenance We are scheduling a 4 hour maintenance window 2025-06-28 1-5pm PT to upgrade the version of our dedicated SIP infrastructure. There may be some disruption to calls during this time. https://status.vapi.ai/maintenance/608457 Tue, 24 Jun 2025 15:00:02 -0000 https://status.vapi.ai/incident/608457#0155401031b04db193306c40a08d981b98fd6b12ebabb4c653323b10627ccd3e Maintenance We’re currently performing maintenance on our analytics database. As a result, call exports from the weekly cluster may return blank CSV files until maintenance is complete. If you run into this issue and need to export data, please temporarily switch your organization’s export setting to daily, then revert back to weekly after exporting. Maintenance will finish by 6 PM PST today. Thank you for your patience. https://status.vapi.ai/maintenance/596392 Tue, 03 Jun 2025 17:00:28 -0000 https://status.vapi.ai/incident/596392#0c66983c18defde7bd44b75d04e02ceabec1ec38246a87f2eb8596085f530960 Maintenance Weekly cluster is undergoing additional maintenance https://status.vapi.ai/maintenance/595722 Mon, 02 Jun 2025 18:00:25 -0000 https://status.vapi.ai/incident/595722#6520f342d0eba9ca95157cc8585b66e698d1f702a42d61ec428eebe6a148925e Maintenance Weekly cluster is under additional monitoring and maintenance after update. We should have things resolved by tonight https://status.vapi.ai/maintenance/556160 Sun, 04 May 2025 03:20:35 -0000 https://status.vapi.ai/incident/556160#176bdbb88e6591794fa4861760d76610dcdb2b2b3adb38b61804bb7294ef3408 Maintenance Regular upgrades to cluster https://status.vapi.ai/maintenance/551227 Fri, 25 Apr 2025 03:16:59 -0000 https://status.vapi.ai/incident/551227#c526351a07064d68239f280afc8ee5accf115b082c606cd096653802db39fb5c Maintenance We will be performing a brief restart of our authentication database to accommodate increased scale. This maintenance is expected to complete within one minute. We appreciate your patience and apologize for any inconvenience. Should only impact the signin & signup on dashboard. Calls and other APIs will not be impacted by it. https://status.vapi.ai/maintenance/545796 Tue, 15 Apr 2025 18:21:20 -0000 https://status.vapi.ai/incident/545796#cbdf444c8b6a535dc24ab371e6773fbd6a3fa000638912c819eb257d4594eed5 Maintenance Applying performance optimizations https://status.vapi.ai/maintenance/534587 Wed, 26 Mar 2025 01:44:35 -0000 https://status.vapi.ai/incident/534587#c50935ef7ac59cbe45242e553e39517657dfe860a347fe46bced63ac3a10d633 Maintenance We are rolling out some major infra changes to our SIP infrastructure that should make it more stable. There should not be any downtime but could be some cases of call drops that rely on SIP during the infrastructure rollout. https://status.vapi.ai/maintenance/526599 Tue, 11 Mar 2025 19:58:24 -0000 https://status.vapi.ai/incident/526599#c946fab547dc33ed64fc8868cb81d6bf91fe1f61a670ccfb70e5d29e4d4a3e81 Maintenance Neon is doing scheduled maintenance in our region `us-west-2`: https://neonstatus.com/aws-us-west-oregon/incidents/01JP2WGPKFV2GDV4QSKV8F8NGP. This will require a restart of our endpoint that will result in seconds of downtime. We have marked off the block of time in which this restart will likely happen. https://status.vapi.ai/maintenance/524956 Sat, 08 Mar 2025 19:00:38 -0000 https://status.vapi.ai/incident/524956#e2133bb71f134d0fc1dc4d970e2308a5d4740a52904e50666499c8d0bc628ddc Maintenance We're rolling out Kubernetes cluster upgrades for security and reliability. https://status.vapi.ai/maintenance/504040 Wed, 29 Jan 2025 21:49:46 -0000 https://status.vapi.ai/incident/504040#59b705687ec6a76e027862f48cdf0c749d83073bd5d9574279813ba4e7b5670c Maintenance We will be retrying our deployment of SIP cluster to make sure we are ready for upcoming scale. There might be some minor disruptions wrt connecting SIP calls, but we will be closely monitoring the situation and complete the migration swiftly. https://status.vapi.ai/maintenance/451110 Sat, 26 Oct 2024 21:45:29 -0000 https://status.vapi.ai/incident/451110#389ad992f9fae1583f3b19f5ab3ee645be8274364c15d70ffd0a218159d8974c Maintenance We need to resize the DB to handle increased load. 5m of downtime is expected. https://status.vapi.ai/maintenance/442681 Fri, 11 Oct 2024 01:04:56 -0000 https://status.vapi.ai/incident/442681#dd5bebb37dd51e8e4d03ac3c3c73c1464df20556737b37107cc145c04bb87c62 Maintenance We're partitioning our biggest table call. We expect this to be zero downtime but want to be communicative.