Incidents reported on status page for Modal Labs https://status.modal.com/ https://d1lppblt9t2x15.cloudfront.net/logos/4aed1028d24910fc147a2962adc30011.png https://status.modal.com/ en https://status.modal.com/incident/1022108 Thu, 20 Aug 2026 00:00:00 -0000 https://status.modal.com/incident/1022108#a7653b33b6f5136e7c6fae94e866c3a6a82d5e24c5608d8d61546ad7312214be We have recovered. https://status.modal.com/incident/1022108 Wed, 19 Aug 2026 23:45:00 -0000 https://status.modal.com/incident/1022108#2e7b87b9ffbbb9ea4b6e302940956a6419d95928f1a6f2800243267c72830153 Some percentage of .spawn() calls experienced elevated latency. https://status.modal.com/incident/987288 Thu, 30 Jul 2026 15:31:00 -0000 https://status.modal.com/incident/987288#b8da97073b23fa8f7d5d5719ce34a104c2b84119e0b086ba070463bff92020ec We're seeing recovery https://status.modal.com/incident/976659 Fri, 24 Jul 2026 11:15:20 -0000 https://status.modal.com/incident/976659#caa3ccddf255a708e1a623d796f81147d6646ff2e5284d72a076c8cff79ced04 Flash Proxy (us-west) recovered. https://status.modal.com/incident/976659 Fri, 24 Jul 2026 11:11:16 -0000 https://status.modal.com/incident/976659#895080b4a93342335ecfda6338728f146e5ea56ca402eb886ded2828dda0c6a1 Flash Proxy (us-west) went down. https://status.modal.com/incident/974469 Thu, 23 Jul 2026 04:50:00 -0000 https://status.modal.com/incident/974469#0aea86455fe7b63442023a392f7b5867c9f055d34cce37a6d6cd71956709b419 We identified the cause and deployed a fix and seeing recovery. https://status.modal.com/incident/974469 Thu, 23 Jul 2026 04:19:00 -0000 https://status.modal.com/incident/974469#4f50ef6fc5537acd38e1ba0ec2ac9c2d79c5941518641623eec38816fe8c52eb We are investigating elevated rates of 5xx errors on modal.com https://status.modal.com/incident/938811 Mon, 29 Jun 2026 21:02:00 -0000 https://status.modal.com/incident/938811#b8a635b5f0556d51288482896d9098d60f0c6c954b00af43599db783ba21b328 We're tracking errors in our storage subsystem which is causing issues with volumes and app deploys. At 9:03 UTC we applied a mitigation and have observed recovery. https://status.modal.com/incident/925881 Tue, 16 Jun 2026 19:00:00 -0000 https://status.modal.com/incident/925881#9bc8a2d2cb3712795993b5bb9de3823ce360b26641e7b7b0490a9742c5bf8f41 Image builds have recovered and caught up https://status.modal.com/incident/925881 Tue, 16 Jun 2026 17:18:00 -0000 https://status.modal.com/incident/925881#5d078fe248f19340131380ea30d8d47366fa8db1623c269856b346b1e0613758 New Image builds are now processing normally. We have a backlog of old Image builds we are burning down. https://status.modal.com/incident/925781 Tue, 16 Jun 2026 17:18:00 -0000 https://status.modal.com/incident/925781#c311388124744c898f1d1550d8399c4c30ce8fe81d4299379d2d56d9ad23bf54 We've recovered operation https://status.modal.com/incident/925781 Tue, 16 Jun 2026 16:52:00 -0000 https://status.modal.com/incident/925781#5c62c0b8d9775c8078429c90ef2f43a0217fbd9c80fd50494d85e866caac00ff Container scheduling and some misc operations (e.g. app deploys) are down. We are actively working on mitigating. https://status.modal.com/incident/925699 Tue, 16 Jun 2026 15:20:00 -0000 https://status.modal.com/incident/925699#c61fa16f632cfd0b8ab2c96d327a9c622adf199f6731d0fea3716a071e849236 Volume CLI operations are no longer degraded. https://status.modal.com/incident/912021 Wed, 03 Jun 2026 13:52:00 -0000 https://status.modal.com/incident/912021#f359486ed18ba30b53e880cdecdea664f23e82302c4402b9b9af07082ab2bcd5 Seeing recovery. https://status.modal.com/incident/912021 Wed, 03 Jun 2026 13:03:00 -0000 https://status.modal.com/incident/912021#cc861b90f020303c1b1e72d45705e5adbb0f837cb74027f500dd42baeac26315 A failure in our auth subsystem is causing failures affecting several services. https://status.modal.com/incident/910161 Mon, 01 Jun 2026 16:53:52 -0000 https://status.modal.com/incident/910161#14adb6884c4c9a49fc69110497d9e89550e911cfa6ff50eb23d933571e2150c5 Image builds recovered. https://status.modal.com/incident/910161 Mon, 01 Jun 2026 16:53:09 -0000 https://status.modal.com/incident/910161#14cc87c7a892b60adc472cdead07377aaf48c32943f25158e2c612399eb22092 Web endpoints recovered. https://status.modal.com/incident/910161 Mon, 01 Jun 2026 16:52:06 -0000 https://status.modal.com/incident/910161#f3240529aca2a56daae21908f05dad327e090e051b0c38b82df10d8b55130337 Image builds went down. https://status.modal.com/incident/910258 Mon, 01 Jun 2026 16:52:00 -0000 https://status.modal.com/incident/910258#e4987b9a0b007505d7773367823e6c9e17659904ea257493ab85c1d8b9d040f2 Sandboxes have recovered. We continue to investigate the root cause. https://status.modal.com/incident/910161 Mon, 01 Jun 2026 16:45:20 -0000 https://status.modal.com/incident/910161#c4bb66408f27d683ea30dada22450953b96a87f7908ca880d411d6ef23354407 Web endpoints went down. https://status.modal.com/incident/910258 Mon, 01 Jun 2026 16:39:00 -0000 https://status.modal.com/incident/910258#906c9cd7306abbf227bfa81999f7dcba20df36ad3c302988cb27fce75a3a8a76 Sandboxes are not starting due to a suspected database issue. https://status.modal.com/incident/910161 Mon, 01 Jun 2026 15:42:56 -0000 https://status.modal.com/incident/910161#7e0328b3474e18a3b4b388c557ce781ffa21bd22e2d4f02f9ca79e33d1bb0079 Web endpoints recovered. https://status.modal.com/incident/910161 Mon, 01 Jun 2026 15:40:35 -0000 https://status.modal.com/incident/910161#118873e04614d1a9b772c227b8ac23e3fd2ce989365dc22ad993fd4c998973e7 Web endpoints went down. https://status.modal.com/incident/908255 Sun, 31 May 2026 10:00:20 -0000 https://status.modal.com/incident/908255#85802c6c1a0f5fea4f42931fe013a0da43a1a2783ee2bd28768a6c2f68311867 ## Impact Our authorization system will be briefly unavailable during the restart. Any request that requires a permission check will fail with an error for approximately **30–60 seconds**. This affects all API operations, including calling functions, accessing apps and storage, and managing resources such as volumes and environments. An increase in failure rates will occur during the restart window for a period of ~30 seconds, affecting approximately ~15% of requests, as the majority of requests are served from cache or will be retried by the Modal client. ## Recovery Once the restart is complete, all operations resume normally with no action required on your end. https://status.modal.com/incident/899713 Tue, 19 May 2026 14:04:00 -0000 https://status.modal.com/incident/899713#a88081bb30f3b35e3d1df25d0bb20a418032ee7cc947ef0d99ab861b379c8dff All services are back. https://status.modal.com/incident/899713 Tue, 19 May 2026 13:57:00 -0000 https://status.modal.com/incident/899713#b73512565caf5046c09c955c4c9b4baf43e4cecb3198e9c0b82c21a93962baa3 Our team is monitoring the remediation we've made to our system that are going out. Services have recovered. https://status.modal.com/incident/899713 Tue, 19 May 2026 13:40:00 -0000 https://status.modal.com/incident/899713#8ac2e9fa3f9eb145f5543996cf8d098efbca6f70e6711b3e400c3212e69a599f We are actively looking into remediating this issue. In the mean time, Modal dashboard log in is not available, and we are keeping tabs on any other services that are affected. https://status.modal.com/incident/899713 Tue, 19 May 2026 13:37:14 -0000 https://status.modal.com/incident/899713#1a03be47ea0541605723e0d116aefaf1e67290e5223474eee22e2d1e1d837bcd GPU functions and Sandboxes went down. https://status.modal.com/incident/899713 Tue, 19 May 2026 13:34:02 -0000 https://status.modal.com/incident/899713#b90221bd42bdcab42101b338204e79a7b7b6ba65dec3e28fb6461f11177ad170 Flash Proxy (us-west) went down. https://status.modal.com/incident/899713 Tue, 19 May 2026 13:31:23 -0000 https://status.modal.com/incident/899713#1fefa5a24200af18971d5df6508b0dc38e67e622e7a2e30ecc58c18db591880a Volumes went down. https://status.modal.com/incident/899713 Tue, 19 May 2026 13:29:39 -0000 https://status.modal.com/incident/899713#feb279eef3bab6649427c6131727497052110889d84856f3dd4083153a8a8377 CPU functions, Snapshot restores (beta), and Image builds went down. https://status.modal.com/incident/891374 Mon, 11 May 2026 00:00:00 -0000 https://status.modal.com/incident/891374#0daa32cdf43f1348dedac8fe63d3a00b1fbfe33fa7064e178ba2dd56ebc16b0c Following mitigations made to our storage layer, we are going to move some data around during off-peak hours. Existing runs should mostly proceed without disruption, but scheduling will temporarily be impacted and some non-critical operations may lose data or need to be retried (e.g. logs). https://status.modal.com/incident/890542 Fri, 08 May 2026 02:30:00 -0000 https://status.modal.com/incident/890542#f50d152aa99790fbb66dde7d1ca0b510feff80c9cf8782ae35f7517d21cafff4 All data stores are recovered https://status.modal.com/incident/890542 Fri, 08 May 2026 02:30:00 -0000 https://status.modal.com/incident/890542#8b0c957bbf3d7b4b4d13647c2fcab2028b0a06ff3341de21a86d26316e4d97d0 All services except queues have recovered. Queues are currently seeing recovery, and fully recovered as of 11:50pm EDT. https://status.modal.com/incident/890542 Fri, 08 May 2026 01:12:00 -0000 https://status.modal.com/incident/890542#58cf6341c910b25594f0310d632a44fa97ff6659abe19638ea42aa09aa39354b We are continuing to work toward mitigation and will share updates as we have them https://status.modal.com/incident/890542 Fri, 08 May 2026 00:40:00 -0000 https://status.modal.com/incident/890542#aff49f4142598d1c631fcafbe28846954a9c8c8d389d42e0b1e8f9ecc9ae82f7 AWS us-east-1 EC2 is currently experiencing an outage, affecting our internal data stores https://status.modal.com/incident/890542 Fri, 08 May 2026 00:22:00 -0000 https://status.modal.com/incident/890542#a710a4bfd4bc000b8cce0a20a786ec77dd414bb6445396b43032ab54448de20a We are seeing a lot of internal data stores failing right now and are actively working on fixing them. https://status.modal.com/incident/890522 Fri, 08 May 2026 00:03:00 -0000 https://status.modal.com/incident/890522#a29869279304ae895585cc8d749864f8c42e9206b8b698a5c152025478ef27c8 We've recovered https://status.modal.com/incident/890522 Thu, 07 May 2026 23:50:00 -0000 https://status.modal.com/incident/890522#f4231199dc94770303e86bb23fa0d1b50fb8cb40bad5cfcf1c4d5e48ad9a744c We're experiencing container scheduling failures and some RPC errors due to a storage failure. We're working on mitigating now. https://status.modal.com/incident/890409 Thu, 07 May 2026 22:32:00 -0000 https://status.modal.com/incident/890409#9d69ed6fa824e4e480dbcbca8464957ee2a375640b779b23da2e57409aa7ae56 We are still actively working on securing more H200 capacity. We recommend you use RTX6000s or H100s in the meantime. Thank you for your patience! https://status.modal.com/incident/890409 Thu, 07 May 2026 20:04:00 -0000 https://status.modal.com/incident/890409#520e3e80df86bcb66549ff1b7d08d1420c626202332198883412be6c3995a228 Due to an H200 capacity shortage, we are seeing degraded H200 scheduling latency https://status.modal.com/incident/883545 Wed, 29 Apr 2026 20:32:00 -0000 https://status.modal.com/incident/883545#1468a21f3c0d5e21cecce877a2af64b3ad31f2cdb0c390d85c13b28de2a5d9ea The issue has been resolved https://status.modal.com/incident/883545 Tue, 28 Apr 2026 21:30:00 -0000 https://status.modal.com/incident/883545#dbefa75ea287f64ee4566b86753d00bdbb7e6ea205bf0d02ff5dc474e739e98b Due to a code change, CIDR allowlists were applied too aggressively, and egress used for some sandbox functionality (including tunnels, exec API, filesystem API, and connection tokens) was unintentionally blocked. A fix has been merged and is being rolled out. https://status.modal.com/incident/881445 Tue, 28 Apr 2026 02:20:00 -0000 https://status.modal.com/incident/881445#b4c06f148432619c90effd902eba8dd09cfbbca3ecaaa0572081c2ca610c2d2b The issue has been resolved https://status.modal.com/incident/881445 Tue, 28 Apr 2026 00:45:00 -0000 https://status.modal.com/incident/881445#3acf0a8325366e9c439d4d651a3e36f6b8d5a3a533f271fbac0f80093b538b82 Due to a DNS change, container scheduling was degraded https://status.modal.com/incident/877404 Wed, 22 Apr 2026 18:38:00 -0000 https://status.modal.com/incident/877404#2421ebda6df74d5c22c704ec5625e1db79c1d8042ac6c423c008b14b093b91f4 Function execution is recovered https://status.modal.com/incident/877404 Wed, 22 Apr 2026 18:17:00 -0000 https://status.modal.com/incident/877404#4ae085567f7d1842fb8e11b43733759d3f8b13f6e977104c4d2a2707efe18ce6 We're seeing recovery on function execution, still monitoring https://status.modal.com/incident/877404 Wed, 22 Apr 2026 18:03:19 -0000 https://status.modal.com/incident/877404#490e45200fe59dc1791f36843eb2fc267b34d1105976e38ba179b725f63bec39 Web endpoints recovered. https://status.modal.com/incident/877404 Wed, 22 Apr 2026 17:55:00 -0000 https://status.modal.com/incident/877404#327359dc61e84d3e75aeba412f4370aae6c3086158c7122649f40b076006977e Function execution is currently degrated https://status.modal.com/incident/873857 Fri, 17 Apr 2026 14:16:00 -0000 https://status.modal.com/incident/873857#b4137e69c6c90cf54cdff070e723e128a0c55866747f200f2dec4c3382db7e0b us-west input plane has now recovered https://status.modal.com/incident/873857 Fri, 17 Apr 2026 14:00:00 -0000 https://status.modal.com/incident/873857#a56ba7274fc0d68ff2e6342b231abb2f651957b00803342a6121d712fa7e3697 Functions running in us-west input plane are down. https://status.modal.com/incident/866379 Tue, 07 Apr 2026 17:00:00 -0000 https://status.modal.com/incident/866379#06133bc4f56888008c2aa166d04bf5ebecfa6645e315a231880cfc2281375d54 Web endpoints are now recovered https://status.modal.com/incident/866379 Tue, 07 Apr 2026 13:16:00 -0000 https://status.modal.com/incident/866379#170c565a3d57eb61f2bf1b69102db5702b74d3f1b688e57f62f996a563aa02c4 We're noticing increased latency for web endpoints affecting some requests https://status.modal.com/incident/866056 Tue, 07 Apr 2026 05:36:00 -0000 https://status.modal.com/incident/866056#1c68620da72f5db91648c533f85373fff656359f58223899263b8a0d92e95e14 We've rolled back a problematic change which caused the issue, and are seeing recovery. https://status.modal.com/incident/866056 Tue, 07 Apr 2026 04:01:00 -0000 https://status.modal.com/incident/866056#6c4c59f760041d4f1fa1c4bcd3275c4b8e806a12687fb9da860eaf00260aa4a1 A small percentage of Function containers failing to start up https://status.modal.com/incident/863661 Thu, 02 Apr 2026 22:13:00 -0000 https://status.modal.com/incident/863661#ad09c981dc2153c5aabcd7c8151a7e28a6477a4a92c69afcdaddfe23125ef879 We have seen the service recover after the deploy. https://status.modal.com/incident/863661 Thu, 02 Apr 2026 21:42:00 -0000 https://status.modal.com/incident/863661#4a16e2fff5d57385e5e93d2eee10d4ef98803f95cf35eeef616c611c27e06699 Modal.com web dashboard degraded. Metrics are slower to load. https://status.modal.com/incident/863632 Thu, 02 Apr 2026 21:03:00 -0000 https://status.modal.com/incident/863632#5a145c9085829be31196f29de23ccb966b60d545f0595937291ae2ceaf276fe1 Things have recovered. https://status.modal.com/incident/863632 Thu, 02 Apr 2026 19:36:00 -0000 https://status.modal.com/incident/863632#7ca71198032a54c2ddcfbbf423a83c7dca89af19f89e112935ada33d91d03dfa Some web endpoint requests that are proxied through our us-east input plane are failing. https://status.modal.com/incident/851579 Tue, 17 Mar 2026 15:38:00 -0000 https://status.modal.com/incident/851579#c5d36ec0565ec0b9c2d8bab17bc7b6e67c66625a4b63ddbdc882592f7065ebf3 We've resolved the issue. https://status.modal.com/incident/851579 Tue, 17 Mar 2026 15:29:00 -0000 https://status.modal.com/incident/851579#2ba38e772b1084abfbc4de5d4d5be466d2f4fe94363701e5e050bda83050d4be Sandboxes are experiencing transient errors in scheduling. https://status.modal.com/incident/847742 Thu, 12 Mar 2026 13:23:00 -0000 https://status.modal.com/incident/847742#f9c8681106b66d0d8968dc9240d99350a94148e9b092af1447b96875e7744761 We've mostly recovered but closely monitoring to figure out the cause and mitigations. Will post more updates soon. https://status.modal.com/incident/847742 Thu, 12 Mar 2026 12:43:00 -0000 https://status.modal.com/incident/847742#a785db358fdcac7c273ddfeff5062f31eca4f267c17d24356f74eb54a5e57709 We're investigating an issue where function call, container scheduling, and web endpoint latencies are degraded. https://status.modal.com/incident/844945 Mon, 09 Mar 2026 04:09:07 -0000 https://status.modal.com/incident/844945#49955312fdab6968fad483a5776f56547e80e9fca4fdb4ba2ea1e0090ee29f3e Image builds recovered. https://status.modal.com/incident/845313 Mon, 09 Mar 2026 04:06:00 -0000 https://status.modal.com/incident/845313#9b4cc1e338079bfebda17f492e6117a3e70fb325a9f37484bff3ba9e614cce0b We have resolved the issue https://status.modal.com/incident/845313 Mon, 09 Mar 2026 03:58:00 -0000 https://status.modal.com/incident/845313#0d0e42a7d8aff433b6778a004f5348a6aff1258fa1cfa9cf156de0ae3819be11 Sandbox scheduling was unavailable from 3:58 – 4:06 UTC https://status.modal.com/incident/844945 Mon, 09 Mar 2026 03:33:14 -0000 https://status.modal.com/incident/844945#bee067a46735c01d9e469ecde876226677d5eb3e77fc6e65cb16a9022c7a6117 Image builds went down. https://status.modal.com/incident/838264 Mon, 02 Mar 2026 22:43:00 -0000 https://status.modal.com/incident/838264#a9610744a44723c80e43c7b4a38e41bce9634770e8d11f2f883659a353cc34bb We have identified and fixed a bottleneck; task logs are flowing through the system normally https://status.modal.com/incident/838264 Mon, 02 Mar 2026 21:12:00 -0000 https://status.modal.com/incident/838264#7ce38a92e9b653894f6c6f076632df00cf5bdf056964f8dce36bc8440036dc91 Task logs have been delayed since 2:46 PM ET https://status.modal.com/incident/833623 Thu, 26 Feb 2026 02:17:00 -0000 https://status.modal.com/incident/833623#3428cb323b20737c629baace27a6609e27e857c9f0f4083e0632a37aa106c38e We have recovered https://status.modal.com/incident/833623 Thu, 26 Feb 2026 01:59:00 -0000 https://status.modal.com/incident/833623#459086b4843b0b233d3de498e19cabfea07a85516f45438554ff7a8ab83e1035 We're looking into an issue scheduling containers https://status.modal.com/incident/829624 Fri, 20 Feb 2026 18:43:00 -0000 https://status.modal.com/incident/829624#6efa3b219b8198ed004713ab21b5a9bfc590a20d560736da628c4083c5ed6c8f All issues have been resolved. https://status.modal.com/incident/829624 Fri, 20 Feb 2026 18:01:00 -0000 https://status.modal.com/incident/829624#b65316b33fb253cf7be983b5f7b739bb9b21dd86a376b1669b59b56066af5388 Functions are fully restored. We are still investigating possible lingering effects for a small number of Sandboxes that were launched between 13:30-14:44 UTC. https://status.modal.com/incident/829624 Fri, 20 Feb 2026 17:01:00 -0000 https://status.modal.com/incident/829624#3ebaeca4b11e65c3f80d602dad34ece21d7a0f00b26f3a6f44c1e8ff87ea4c4a New containers are working normally. We are continuing to investigate possible lingering effects for recently started containers. At 13:30 UTC a bad change went out causing new containers to potentially get stuck or experience errors. At 14:44 UTC a the bad change was fully reverted and the disruption mitigated. We experienced a secondary, lesser problem with similar symptoms between approximately 16:00 and 16:15 UTC as part of the mitigations put in place during the response. https://status.modal.com/incident/829624 Fri, 20 Feb 2026 14:44:00 -0000 https://status.modal.com/incident/829624#e4c91bcf9ee911b2f7467acf70fcc85e3518b5eff319c67a413dee0020fdf861 Issues with some image builds getting stuck have been resolved. https://status.modal.com/incident/829624 Fri, 20 Feb 2026 13:30:00 -0000 https://status.modal.com/incident/829624#106ce648a94a5a8cb20b54505f46d04b8a3aa26a1d58807705890463c4c979eb We have identified the root cause and are taking action to mitigate. https://status.modal.com/incident/823392 Wed, 11 Feb 2026 14:45:00 -0000 https://status.modal.com/incident/823392#93171485b1d30476b203e55a4ea7ed71af9508f014b828897587f1c2889576bd Web endpoints are healthy again. https://status.modal.com/incident/823392 Wed, 11 Feb 2026 13:40:00 -0000 https://status.modal.com/incident/823392#132dd07e598c9d8b9573d42c0707c92d55017aed48644a19961d54ba69ae437c Web endpoint requests were experiencing elevated latency and errors. https://status.modal.com/incident/822551 Tue, 10 Feb 2026 15:27:00 -0000 https://status.modal.com/incident/822551#ad58c950d1a51e873ef21daa8e324b30be2d43f05abf357455c292febe3a46af All other input planes are now recovered. https://status.modal.com/incident/822551 Tue, 10 Feb 2026 15:22:00 -0000 https://status.modal.com/incident/822551#8aae9efd99c5ff9be3bc432a54a08e593467c08580e69d07731f73edec92c080 us-west input plane is recovered. https://status.modal.com/incident/822551 Tue, 10 Feb 2026 15:03:00 -0000 https://status.modal.com/incident/822551#332aea1e7c78eeaaa48c0fb42f90b9fefcabb52c4a9714c4eb12eef9c2e6f2f3 We are working on recovery. https://status.modal.com/incident/821245 Sun, 08 Feb 2026 20:08:00 -0000 https://status.modal.com/incident/821245#d8c09fbca43bd2eda8abce7a3ed8f2cdf3d53dab694a2d259ec2c71d3e3f8313 Error rate is back to zero and service is fully restored. https://status.modal.com/incident/821245 Sun, 08 Feb 2026 19:25:00 -0000 https://status.modal.com/incident/821245#097c316171e1d994e845894584ff03c5d6769ada6807a69d38536113463f1953 Due to a Redis cluster node becoming saturated Function input fetching and output publishing has an elevated failure rate. We're actively working on remediation to bring down error rates to zero. https://status.modal.com/incident/819817 Fri, 06 Feb 2026 09:55:18 -0000 https://status.modal.com/incident/819817#d060cdc110bda608eb4252dd3654a0c64aa12134cb1a2cab3d2e52bced2e3212 Image builds recovered. https://status.modal.com/incident/819817 Fri, 06 Feb 2026 09:51:07 -0000 https://status.modal.com/incident/819817#166ff253e38642452edf439585de78b9191ab32dab932b93ed1c8d6fe5f8294d Image builds went down. https://status.modal.com/incident/816199 Sun, 01 Feb 2026 09:41:00 -0000 https://status.modal.com/incident/816199#ee7ffa32eb495fc703bf9f4a8e2bed4cbc05581042d6ca63851a384cbf65c1df The dashboard is recovered. https://status.modal.com/incident/816199 Sun, 01 Feb 2026 09:03:00 -0000 https://status.modal.com/incident/816199#51fe8a233646454102c2cc893feb1228b2bfb9a9499c83090bd7d21d6f24a853 Our observability data storage provider is having an outage. Dashboard is severely degraded for all users, function execution should not be affected. https://status.modal.com/incident/810961 Sat, 24 Jan 2026 11:16:39 -0000 https://status.modal.com/incident/810961#7bdf338b44894dc61240e462e6eb5e41420a9638c40deba2d4b7e0cde6d7b3df Image builds recovered. https://status.modal.com/incident/810961 Sat, 24 Jan 2026 11:10:20 -0000 https://status.modal.com/incident/810961#cb1a62769b56ca1f83b7ff100ff4ea6c4fd2c72b47c1ec33427576462501cc1c Image builds went down. https://status.modal.com/incident/809116 Wed, 21 Jan 2026 05:40:00 -0000 https://status.modal.com/incident/809116#dfea39673344699c10ec9b11b937028bcd49aa71af3aa6ebf08c85891bb370d7 We mitigated and are no longer getting bandwidth throttled. https://status.modal.com/incident/809116 Wed, 21 Jan 2026 02:00:00 -0000 https://status.modal.com/incident/809116#4443274aa0054e7247289b64ffd430574f2ee47127a45f0a392c08cec349e592 Our storage backend began bandwidth throttling us, resulting in some errors / degraded Modal Volume performance. https://status.modal.com/incident/806638 Sun, 18 Jan 2026 06:03:00 -0000 https://status.modal.com/incident/806638#8de8e211c28c5261790dbdc3b17ea4fa226fe2962042f3eb89a16da3ef9bd447 We refreshed the cert and the service has recovered. https://status.modal.com/incident/806638 Sun, 18 Jan 2026 05:43:00 -0000 https://status.modal.com/incident/806638#3eb7304c4f781f7d1248240ed7415b5ad1f92ceeb59764c6706b9055fb924068 An expired TLS cert slipped past our early alerting causing the Flash Proxy routing service to go down in us-west only. https://status.modal.com/incident/805726 Thu, 15 Jan 2026 22:27:00 -0000 https://status.modal.com/incident/805726#069ba904eb7ebadd3cb28d349cfdf0fae0ae242af130608cbafd18d13fdca2f2 The issue has been mitigated and normal access to Volumes via CLI, API and the dashboard is restored. https://status.modal.com/incident/805726 Thu, 15 Jan 2026 01:15:00 -0000 https://status.modal.com/incident/805726#488103431d94f795dd63ad6f0a6249ac41a152ddc8dfe38745fb6cab12585a6f We are experiencing intermittent issues with accessing Volumes via CLI, API and the Modal dashboard. Access to Volumes from containers is not affected. https://status.modal.com/incident/804701 Thu, 15 Jan 2026 00:00:00 -0000 https://status.modal.com/incident/804701#64c77ade6b4a4c3392c0363664127d0a44003d5ac1dfb604fb222ed7c97de85b All capacity is back. https://status.modal.com/incident/804701 Wed, 14 Jan 2026 23:45:00 -0000 https://status.modal.com/incident/804701#e34be9d9116ea3e50897f47865893493f872921fb47d329b23976f1765281b07 Our GPU capacity is back. https://status.modal.com/incident/804701 Wed, 14 Jan 2026 23:18:00 -0000 https://status.modal.com/incident/804701#1217fe3111d2e886cb859fb81408f80e000e785ed0949154f7a9e25c85cb9015 We stopped the capacity loss and are beginning bringing back capacity. https://status.modal.com/incident/804701 Wed, 14 Jan 2026 23:04:00 -0000 https://status.modal.com/incident/804701#1c82944a68738d85f90847af6cca0c3a868cb2e19e3e6e903552a956958337b2 We experienced a drop in capacity across our fleet. https://status.modal.com/incident/795061 Sun, 28 Dec 2025 11:06:00 -0000 https://status.modal.com/incident/795061#e267f5368e6e9d5978e3199bd1f02975c217117269c4fdb6a7b18541a964e632 All services operational as of 11:06 UTC. https://status.modal.com/incident/795061 Sun, 28 Dec 2025 11:01:00 -0000 https://status.modal.com/incident/795061#d054104a603490da0398f25a73b432594149e750de094a95a5aa2f3ff9f33d0d We have just finished spinning up a new database instance from backup and pointing traffic to it. We are seeing recovery for users, and are actively keeping a close eye on metrics. https://status.modal.com/incident/795061 Sun, 28 Dec 2025 10:24:00 -0000 https://status.modal.com/incident/795061#1de9f55fea9fff9b82d6db52ce92c5b80713b6fbbee6106d004a8ff80f07e7e2 We have escalated this issue to AWS, and also are working on restoring a copy of the database in parallel. https://status.modal.com/incident/795061 Sun, 28 Dec 2025 10:08:00 -0000 https://status.modal.com/incident/795061#9188e4065962407af1ad2476964a44031bc6a735d3eac6b201942ec2ea40c812 We are currently in the process of figuring out the best mitigation plan that will minimize risk and downtime once it is complete. https://status.modal.com/incident/795061 Sun, 28 Dec 2025 09:15:00 -0000 https://status.modal.com/incident/795061#8f3d21721a6f6a6b470759f30d49326b9ea4db87f80cc17d9d8a521bf402639b We are investigating and believe we have diagnosed the problem: we are having an active incident with our database and are actively working on mitigating. https://status.modal.com/incident/795061 Sun, 28 Dec 2025 09:12:00 -0000 https://status.modal.com/incident/795061#97a55db278826030b0e026fa3d7472f064c5b9cbb2fe8c1c1ee73ebcbce2e8b3 CPU functions, GPU functions, Snapshot restores (beta), and 2 other resources went down. https://status.modal.com/incident/793332 Wed, 24 Dec 2025 02:47:00 -0000 https://status.modal.com/incident/793332#67c536fef2ef1f2c1db8b4a71f813395d789704b9d03968a5cceb07170a0cbed Indicators of scheduling latency have recovered. Apologies for the disruption. https://status.modal.com/incident/793332 Wed, 24 Dec 2025 02:40:00 -0000 https://status.modal.com/incident/793332#36f3bbf036bd83c5367683d542635413f18910a3ec3791a5ec7dfe9705e25b0f The change has been rolled back and we are monitoring recovery. https://status.modal.com/incident/793332 Wed, 24 Dec 2025 02:31:00 -0000 https://status.modal.com/incident/793332#e8d631b7645eda65c76b58eb0627f542baf29450be3b381ba2b7081252adc14d We're currently rolling back a change which caused scheduling to fail for Functions and Sandboxes. https://status.modal.com/incident/789223 Thu, 18 Dec 2025 20:07:02 -0000 https://status.modal.com/incident/789223#6ead28b3c66f825946d643bdb7f15caae20620cfbb826b7a3a119fc12535fdfe Image builds recovered. https://status.modal.com/incident/789223 Thu, 18 Dec 2025 19:57:46 -0000 https://status.modal.com/incident/789223#46f8f0ef213967cefeb53db248212751f3588cebf9977a60d5e235cbdca4d4a1 Image builds went down. https://status.modal.com/incident/787536 Tue, 16 Dec 2025 13:37:00 -0000 https://status.modal.com/incident/787536#204ed66d8026071283c25aec62bf77f97ca21c2e8a9a9018c3ae2f6bf027873c Volume operations appear to be stable for now, we are actively monitoring and working on the underlying issue. https://status.modal.com/incident/787536 Tue, 16 Dec 2025 12:25:00 -0000 https://status.modal.com/incident/787536#ece920ce25648ecb28d32e927be4e8b55f20103a37c9895534295dfa1f44344a We are having an issue with volumes, we are investigating. https://status.modal.com/incident/783644 Wed, 10 Dec 2025 10:05:00 -0000 https://status.modal.com/incident/783644#b12c0d1716e677ead22684d854e949afd7a886d144045a1706f22caaf4e25d02 Queueing has been resolved. Apologies for the disruption. https://status.modal.com/incident/783644 Wed, 10 Dec 2025 10:01:00 -0000 https://status.modal.com/incident/783644#d8af9714a674708c0b5aedcba79418bcba765f58058575dbc7cd8ed1400a0e87 We have been successfully launching new Workers as of 3 minutes ago. https://status.modal.com/incident/783644 Wed, 10 Dec 2025 09:52:00 -0000 https://status.modal.com/incident/783644#12564ea462418bd997c8785bcd6e0a96c60d6ec50e3bc49aa3ff6ed19c701ea9 Due to an outage in a third-party provider, Tailscale, new Workers have been unable to scale since 8:54:37 UTC. We're are working to remove Tailscale as a dependency while it's down. https://status.modal.com/incident/779305 Fri, 05 Dec 2025 01:10:00 -0000 https://status.modal.com/incident/779305#647605be05b4fb42e05e4dcd5ffe581d6669e1fa1a4e41707ef04af598e753fb modal.com website is unavailable https://status.modal.com/incident/779132 Wed, 03 Dec 2025 19:50:00 -0000 https://status.modal.com/incident/779132#285293c73fddf1dc434b4a2880bcdb48557335c1e232223dd50d7c6d358b0efc DNS query latencies have recovered, per our internal synthetic monitoring. We apologies for this disruption. Please contact us for further details. https://status.modal.com/incident/779132 Wed, 03 Dec 2025 19:10:00 -0000 https://status.modal.com/incident/779132#c67ce727fb55c000312ae04760ec32f1cd69953b1b8212b6a1b67a388549edfa At 19:10 UTC today our DNS server system which is used by Sandboxes took on a flood of (invalid) MX traffic. By 19:50, we'd scaled up our DNS servers and the MX traffic spike plateaued, allowing DNS query latencies to recover. https://status.modal.com/incident/777558 Mon, 01 Dec 2025 16:51:00 -0000 https://status.modal.com/incident/777558#2fea63039facad5467f4bba1ae631530c770aa818177407ceead24aa44a58fe9 We've recovered https://status.modal.com/incident/777558 Mon, 01 Dec 2025 16:43:00 -0000 https://status.modal.com/incident/777558#13abc17a28af531350d1fd713b377fc0fa3a1f643b8e1904fc7c7fd9bf3120ce We're being throttled by an upstream service, which is affecting image builds / app deploys. We've identified the root cause and are fixing. https://status.modal.com/incident/777558 Mon, 01 Dec 2025 16:25:43 -0000 https://status.modal.com/incident/777558#5897b65e5c22a51d9b0e786a8e08da489f96a73834a6afc1e5882f8be96c03be Image builds went down. https://status.modal.com/incident/774911 Thu, 27 Nov 2025 00:21:00 -0000 https://status.modal.com/incident/774911#967124559fe5d241a41b9412bd19b8532c816c24dd53352a3faf695fa43a4369 This is a false alarm. Sorry for the noise! https://status.modal.com/incident/774016 Tue, 25 Nov 2025 15:25:00 -0000 https://status.modal.com/incident/774016#f3571ba5018cf3e98fe06b8bea926814ed65d0ab6f3ef3c712e55449a9e32fb8 The rollback has completed and errors have subsided. https://status.modal.com/incident/774016 Tue, 25 Nov 2025 15:08:00 -0000 https://status.modal.com/incident/774016#81a766f45c8c0182db1bcc791d978496c472cfc39e39c8ecc23fc917b0ad8048 An incorrect configuration change applies aggressive throttling on container filesystem bandwidth and is causing downtime. We have reverted the configuration and are managing recovery. https://status.modal.com/incident/770667 Thu, 20 Nov 2025 03:08:00 -0000 https://status.modal.com/incident/770667#7318c5681a87fbe8c0bc057a88b7890d1452fd2e9aac8f4e2fe19f6bee711913 Our web endpoints infrastructure is having spikes of degradation tied to the traffic pattern of a specific tenant. We are in contact and cooperating with the customer and putting in place mitigations. https://status.modal.com/incident/764951 Wed, 19 Nov 2025 09:00:00 -0000 https://status.modal.com/incident/764951#e1829ef14a656ca4171feef53149fcea20ab46e6c659e7c6fe7613dee4e10c96 We are upgrading core systems used for version 2 volumes. Version 1 volumes are not affected. Volumes will remain available during the maintenance but latency and failure rates are expected to be slightly elevated. https://status.modal.com/incident/761763 Mon, 10 Nov 2025 22:34:00 -0000 https://status.modal.com/incident/761763#63272d6af208d2af41aef7c24e23c4d9cd2750ed3bb1d39ccab6e79da11e769b We identified the misconfiguration and rolled out the fix. https://status.modal.com/incident/761763 Mon, 10 Nov 2025 20:17:00 -0000 https://status.modal.com/incident/761763#c663e0c7af5338b23684f327b32c0e61753bba56a22ce14c6dd0ba6e49472897 We're seeing elevated latencies across some RPCs due to a misconfiguration we rolled out. We're working on rolling out a fix. Apologies for any disruption you may be experiencing. https://status.modal.com/incident/750831 Fri, 24 Oct 2025 20:43:00 -0000 https://status.modal.com/incident/750831#43162321981b1ee41a509b13e94e21dc0c80b87a24c4507cbf26cd16ebebbbda Database up and service is back to normal. https://status.modal.com/incident/750831 Fri, 24 Oct 2025 20:29:00 -0000 https://status.modal.com/incident/750831#b2bf8133c1c94c8869eae767a19f773d93bb50684de9d4ad4b0aec06a7206df5 We hit a scaling limit on our primary database. Configuration was updated and the database restarted. https://status.modal.com/incident/746748 Mon, 20 Oct 2025 23:30:00 -0000 https://status.modal.com/incident/746748#6ad4512a0274d3eff2b4ca14c645645723b5721b252d27bbdd458e7dc09f6fea AWS has marked the underlying incident us-east-1 as recovered, and we've seen recovery across our affected services. https://status.modal.com/incident/746748 Mon, 20 Oct 2025 22:02:00 -0000 https://status.modal.com/incident/746748#672073beaf2cfb8a34464e25bde025628f798fc3dfac63f2a13e2cb58ecc320c We have mostly recovered alongside the recovery in AWS us-east-1, but continue to have sporadic connection issues against Redis (AWS Elasticache). https://status.modal.com/incident/746748 Mon, 20 Oct 2025 17:20:00 -0000 https://status.modal.com/incident/746748#cf3046d986d9ae017a1e6512641c4a871b6816b0ab594c0b9d2ba6d090c4ea5c A number of AWS services are still degraded in us-east-1 and causing issues. https://status.modal.com/incident/746748 Mon, 20 Oct 2025 16:18:00 -0000 https://status.modal.com/incident/746748#1da6777208eab1051b0f4ddf4f3e8e1caf9c72413889f672d75ce32f371bcf5b AWS us-east-1 is experiencing an outage and many of our services are affected. We're looking at mitigating the impact. https://status.modal.com/incident/746748 Mon, 20 Oct 2025 09:23:00 -0000 https://status.modal.com/incident/746748#050d9f207f6e8980de74c34a56ecda78d4410268251a9946beee0949d27fb9fc Our dashboard is now recovered and service errors are going down. https://status.modal.com/incident/746748 Mon, 20 Oct 2025 07:12:00 -0000 https://status.modal.com/incident/746748#6d5232afe1b9f1fc687e2beeedf1faed371c2855d96af1c3b45cde3c61376006 CPU functions, GPU functions, Snapshot restores (beta), and 3 other resources went down. https://status.modal.com/incident/746748 Mon, 20 Oct 2025 07:12:00 -0000 https://status.modal.com/incident/746748#97760223287fa106adb7affbeb15d7f9f5a043496720eb2015481b8fc55f2d97 AWS us-east-1 is experiencing an outage and many of our services are affected. We're looking at mitigating the impact. https://status.modal.com/incident/743021 Tue, 14 Oct 2025 01:14:00 -0000 https://status.modal.com/incident/743021#5f53347266f079c696e6c6f3bb2bb6a85b3c162ed0c2a5e356b8ff16884e4854 We have resolved the certificate expiration issue on all affected hosts. https://status.modal.com/incident/743021 Tue, 14 Oct 2025 00:56:00 -0000 https://status.modal.com/incident/743021#1df1f3fd890cd486d7a1c5f1fc7247410681b75cfa05636042a6df49a63a8468 Clients attempting to connect to encrypted Modal Tunnels (https://modal.com/docs/guide/tunnels#tunnels) may experience connection failure due to certificate expiry that occurred at midnight October 13th UTC. We are working to restore health to encrypted Tunnels by removing hosts with expired certificates or refreshing certificates. https://status.modal.com/incident/734703 Tue, 30 Sep 2025 03:26:57 -0000 https://status.modal.com/incident/734703#fbcc6ad1a96a7a0cd694394707a310f5c0bbb93fc2c66ac4f4736f29ace3953c Web endpoints recovered. https://status.modal.com/incident/734703 Tue, 30 Sep 2025 03:18:05 -0000 https://status.modal.com/incident/734703#b5da25fe15f2c24cec4275768c8da9ce0e3a69063e1b0993ebaffa009f1d5e77 Web endpoints recovered. https://status.modal.com/incident/734703 Tue, 30 Sep 2025 03:13:29 -0000 https://status.modal.com/incident/734703#dc5807f99c4c98063f723947e70e10925ac573cad5104d5492c6ca1763a2e120 Web endpoints recovered. https://status.modal.com/incident/728913 Mon, 22 Sep 2025 15:55:00 -0000 https://status.modal.com/incident/728913#df49a6fb053c288b08ebdab904aae5658268df141e0bd2627a80b07500b7e7d7 Invite emails, notification emails and others aren't sending. We're currently investigating the issue. https://status.modal.com/incident/724595 Mon, 15 Sep 2025 14:30:21 -0000 https://status.modal.com/incident/724595#696dce005df5d0c84960ffe5040dc65c762103817f25344039c50bda6fc00d83 Image builds recovered. https://status.modal.com/incident/724595 Mon, 15 Sep 2025 13:45:42 -0000 https://status.modal.com/incident/724595#d3ea8968063a17de4d5dbae43b751e9dd8add80f7f002bccc79ef16d9e0726e2 Image builds went down. https://status.modal.com/incident/720372 Mon, 08 Sep 2025 11:06:00 -0000 https://status.modal.com/incident/720372#09f0e07ac18f1bd256ecf34842d9bf922b37fbddc9c990d7f6cef4ef9f8a064e As of 10:41 UTC scheduling latency has recovered on A10G and L40S. Apologies for this incident and the customer impact caused. Please contact support to access the post-mortem document if interested. https://status.modal.com/incident/720372 Mon, 08 Sep 2025 10:27:00 -0000 https://status.modal.com/incident/720372#decc975cfa6535563cdf863f5297a82fb84d55b5f68dac03a2a1c35dc4d440f6 Due to an inability to scale up workers in AWS A10G and L40S Function scheduling latency is degraded. Since 06:47 UTC today A10G scheduling latency has been heavily degraded. Since 06:20 UTC today L40S scheduling latency has been heavily degraded. As of 10:40 UTC scaling in AWS has been restored and queuing times are recovering as the worker pool grows its AWS A10 and L40S capacity. https://status.modal.com/incident/712851 Tue, 26 Aug 2025 15:10:00 -0000 https://status.modal.com/incident/712851#1dee8080c3f3b885a8c3817b8f1aeecf325f5a8d4af1dc6488e697a2b93f707f We identified the issue and we're starting to see recovery for the dashboards and image build times. https://status.modal.com/incident/712851 Tue, 26 Aug 2025 14:31:00 -0000 https://status.modal.com/incident/712851#73e6583623d730fa19458fd0bd8e252c1fe271f999b2b542ff03069905bdeeb5 Metrics dashboards on Modal.com are degraded: requests for metrics, logs, etc., are either slow or failing. Image build performance is also degraded. We are working with a vendor to resolve downstream performance issues. The Modal runtime environment, including function execution, is unaffected. https://status.modal.com/incident/710139 Thu, 21 Aug 2025 19:24:00 -0000 https://status.modal.com/incident/710139#7f99d1769b1342161d20a266be57390af180753ec824368513839151b92b58ef Task startup / volume operations back to normal operation https://status.modal.com/incident/710139 Thu, 21 Aug 2025 18:47:00 -0000 https://status.modal.com/incident/710139#2d5fca631c3cb10bda7e8258b8e798375e1bfc645e44513ec87e9de4677f8349 Task startup / volume operations mostly recovered https://status.modal.com/incident/710139 Thu, 21 Aug 2025 18:33:00 -0000 https://status.modal.com/incident/710139#8c4de84c11c701c2328135ba059bcc2252ae19c8c30fa47973aec906b8dfeae2 Some volume operations and task startup saw errors / degraded performance. https://status.modal.com/incident/709291 Wed, 20 Aug 2025 15:39:00 -0000 https://status.modal.com/incident/709291#e3c7820f1c86d0db247de07c96a0b6f3ca315bab2ad52535eed72736771f4ed5 A false alarm triggered downtime notifications. All services are online and there was no production impact. https://status.modal.com/incident/708569 Tue, 19 Aug 2025 15:24:00 -0000 https://status.modal.com/incident/708569#8369623b579ae18d8f215bdd5645d2f34b6d99327962e4970a7ac17b25ffc317 Image builds and Volume file fetches have now recovered https://status.modal.com/incident/708569 Tue, 19 Aug 2025 15:01:00 -0000 https://status.modal.com/incident/708569#3a80111a37e2e121598134bcbe2aab57ecaa0b0abb28614cdbed228c35eb2b28 Images are failing to build and Volumes are experiencing issues fetching some files. https://status.modal.com/incident/705524 Tue, 12 Aug 2025 06:30:00 -0000 https://status.modal.com/incident/705524#6edc5142bcfb30f62dbed759b478e330fcbf74de7741fa07c643904b645bb21a Container scheduling degradation was resolved. https://status.modal.com/incident/705524 Tue, 12 Aug 2025 05:38:00 -0000 https://status.modal.com/incident/705524#cfeb455298b5add0c5b76536034ecb77d9c4e47968c38b6837e2c5ada97403e8 Due to an internal service issue we observed degraded container scheduling during 8/12 5:38 UTC to 6:30 UTC. Containers took much longer than typical to come up, affecting new inputs. Existing containers continued serving traffic. This was resolved by 8/12 6:30 UTC. https://status.modal.com/incident/624762 Wed, 23 Jul 2025 23:40:00 -0000 https://status.modal.com/incident/624762#6f815e8f1c77fa6a8209768dd527af06bc6208a2ab499ed962a8b5441527007b We have pushed a fix for the issue and performance is back to normal. https://status.modal.com/incident/624762 Wed, 23 Jul 2025 23:20:00 -0000 https://status.modal.com/incident/624762#dcc78ee403c4a0c0b5b82eaf5d50de5f93ccddf6d9b124f3ad018ddd929866c1 We are investigating a performance issue with the dashboard and logging. https://status.modal.com/incident/623979 Tue, 22 Jul 2025 16:20:00 -0000 https://status.modal.com/incident/623979#74bc9b21ec9b2ea900fc2279a9b8d82e7bbe5325d6656349966588031a70104e We restarted a web server. The issue is resolved. https://status.modal.com/incident/623979 Tue, 22 Jul 2025 16:18:00 -0000 https://status.modal.com/incident/623979#104bc8225b03cf20616f8f5d1947ba125f593085eadd4f708a0bd5b4f26a68f4 We are investigating reports that the dashboard may not be loading. https://status.modal.com/incident/623584 Tue, 22 Jul 2025 02:32:00 -0000 https://status.modal.com/incident/623584#ff0da1ffbba0a3d15f2b8ac5b847445a2f9f65ce0919e5de658b51b5c5e85b06 We have added a backup provider for SSL certificates, and issuance has resumed successfully. https://status.modal.com/incident/623584 Tue, 22 Jul 2025 01:09:00 -0000 https://status.modal.com/incident/623584#b2a77d87871e7ade1c845d020097eb6b0b307219cc264ca360ae62316d50ee70 Due to an [active incident at Let's Encrypt](https://letsencrypt.status.io/), we are unable to issue SSL certificates for web endpoints on new, custom domains (eg., `yourwebsite.com`). * New web endpoints using our default `modal.run` domain are unaffected. * Existing web endpoints for which we have already issued certificates are unaffected. * We renew certificates 30 days in advance, so we do not expect any certificates to expire. We are actively testing a backup provider which we may bring online if the incident continues. https://status.modal.com/incident/619480 Mon, 14 Jul 2025 18:42:00 -0000 https://status.modal.com/incident/619480#cc6c37eb294081b5d354182fd57630df6dc27e48d888a8c68a9fb9b1525e6792 CPU functions, GPU functions, Volumes, and 1 other resource recovered. https://status.modal.com/incident/619480 Mon, 14 Jul 2025 18:26:00 -0000 https://status.modal.com/incident/619480#372eddc42f4dcf9e69fb26c1af34c1fdce31aaf2a892634dd4a6805f0c766692 CPU functions, GPU functions, Sandboxes, and 1 other resource went down. https://status.modal.com/incident/616977 Mon, 14 Jul 2025 18:00:00 -0000 https://status.modal.com/incident/616977#83914c89304f7f61f731e15d341c294f893130ea174c045860125dd2baa0ee1a We're performing a version upgrade to a critical infrastructure component. We do not expect any downtime for Function or existing Sandbox execution. There will be a brief period of web UI downtime and a pause in new container creation and scheduling (including Sandboxes) lasting ~2 minutes. Apologies in advance for any inconvenience, and please let us know if you have any questions. https://status.modal.com/incident/611946 Mon, 30 Jun 2025 19:59:00 -0000 https://status.modal.com/incident/611946#1a9a91367ef8891dd40b29a664baf265df654e11eda0f816e1a17b2225558534 Bug has been reverted out of production. All new exec processes will now function correctly. https://status.modal.com/incident/611946 Mon, 30 Jun 2025 19:40:00 -0000 https://status.modal.com/incident/611946#2406618c0d02472fef8dc37e3963b8b24052744bf0d0ae8f214fec548c76b856 Due to an incorrectly expired internal channel, operations against a Sandbox exec process which are older than 5 minutes fail. We are rolling back the change. https://status.modal.com/incident/609934 Fri, 27 Jun 2025 03:08:12 -0000 https://status.modal.com/incident/609934#3eabbcbde2a6b441c2ab153b82e2986c371f2dcc061930e4f962f6a1c4582ecd Web API recovered. https://status.modal.com/incident/609942 Fri, 27 Jun 2025 03:08:00 -0000 https://status.modal.com/incident/609942#72292064395e879fd271e28477378a591483c54a93ef75774e335e6acd3333cf We have rolled back the affected component and services have recovered. https://status.modal.com/incident/609934 Fri, 27 Jun 2025 03:06:14 -0000 https://status.modal.com/incident/609934#919ef97c210791c292882844321cf56f9d3cba860ce3c114e7ba164fc3e90560 Web endpoints recovered. https://status.modal.com/incident/609934 Fri, 27 Jun 2025 02:57:16 -0000 https://status.modal.com/incident/609934#f1d58d982eff54e6e4cad85f73256f2108af69df17505a0c0ed7d5809e0c8b25 Web endpoints went down. https://status.modal.com/incident/609934 Fri, 27 Jun 2025 02:53:25 -0000 https://status.modal.com/incident/609934#a9922cd77e943561d19f6b5275eeeb5c85ae7810e341650f2866fe8cd1c5e9b4 Web API went down. https://status.modal.com/incident/609942 Fri, 27 Jun 2025 02:51:00 -0000 https://status.modal.com/incident/609942#3890bc20bf2fe03dc6b2133c02a348f1f3ab9709a3755e542cd3fb16165ea405 Multiple services are unavailable. https://status.modal.com/incident/597829 Sat, 07 Jun 2025 03:59:21 -0000 https://status.modal.com/incident/597829#ffb6ca123dd16abf89389d1b4bf0519581c5c6930b68fd7cfa25e82f3dadae23 We're performing a scaling update to a critical infrastructure component. There may be a short window (estimated 2 minutes) of downtime. We don't anticipate that workloads (i.e. functions, webhooks) will be affected. However, there may be UI issues and task scheduling delay. https://status.modal.com/incident/575767 Thu, 22 May 2025 18:00:28 -0000 https://status.modal.com/incident/575767#1e500f850b9e735ebff37a9174deb7a91f6a0f908bca8c1dd679368a40ec0772 We will be conducting internal networking updates that affect our main API server. https://status.modal.com/incident/575650 Thu, 22 May 2025 14:09:32 -0000 https://status.modal.com/incident/575650#6b4033b679ef7b176fef68d8c604de6ddce16bf0de1fbb7bd31d37b9de08645f Web API recovered. https://status.modal.com/incident/575650 Thu, 22 May 2025 14:06:57 -0000 https://status.modal.com/incident/575650#607e7f817d0789c8eeff7940a374da7763e840ed4b3df80dcbf33d7d79732e64 Web API went down. https://status.modal.com/incident/566071 Thu, 15 May 2025 15:09:26 -0000 https://status.modal.com/incident/566071#07ee3e88fafc54e4e9b21da03a93c29029ea06fcfe76d8de641b42b0150727cd Web endpoints recovered. https://status.modal.com/incident/566071 Thu, 15 May 2025 15:04:35 -0000 https://status.modal.com/incident/566071#cb127589cd2d455056ae57b6591a441fe9a042f0c690b277497b65d6faffe7b0 Web endpoints went down. https://status.modal.com/incident/558881 Thu, 08 May 2025 20:15:00 -0000 https://status.modal.com/incident/558881#0ad7384d3b86fc61be776e4e859276934922d5cd9aa4c177f84ed618ebd42501 Fully recovered https://status.modal.com/incident/558881 Thu, 08 May 2025 19:22:00 -0000 https://status.modal.com/incident/558881#621ed1d5b7ab59956f356f6118fdac9e135afda2e1c07b5c29b4bbfd7bd5bce7 Scheduling for sandboxes is degraded https://status.modal.com/incident/540813 Sun, 06 Apr 2025 17:03:00 -0000 https://status.modal.com/incident/540813#693d0a8126bafbbfa1e96a028dc6a399fdd47a2499aaa8f67468f871b18f3b46 Due to network degradation in GCP, Modal is compromised in its ability to maintain Worker capacity and container health. If you have GCP-pinned (cloud="gcp") Functions or Sandboxes, unpinning will result in avoiding this issue. https://status.modal.com/incident/535641 Thu, 27 Mar 2025 20:03:00 -0000 https://status.modal.com/incident/535641#1952ec8f8799ddf0ac6c75a9caa32dc84762330d6397a820420ed0e49a2ea033 Update: The incident is now resolved. Cloudflare incident: https://www.cloudflarestatus.com/incidents/t8mq7d1yjqm4 We are remediating this by shifting Modal Workers away from us-east-1. https://status.modal.com/incident/535052 Wed, 26 Mar 2025 19:45:00 -0000 https://status.modal.com/incident/535052#7445b80ea4dfa7230ccdb453bcfabfbbbc2b903175556624a987c0bebaeb400f We have scaled up capacity successfully and redirected traffic to work around the Oracle Cloud regional networking outage in Ashburn, VA. Newly created sandboxes are fully operational. Some sandboxes created during the incident may not have been able to spin up. https://status.modal.com/incident/535052 Wed, 26 Mar 2025 19:26:00 -0000 https://status.modal.com/incident/535052#ea9ce3ffd33de16985dbb6202f107f1f8d25e3d82af5c6443a9a52eff3d805a3 Oracle Cloud is mitigating the issue. In the meantime, we're trying to help the autoscaler scale up instances as fast as possible in other clouds. https://status.modal.com/incident/535052 Wed, 26 Mar 2025 19:19:00 -0000 https://status.modal.com/incident/535052#0503719bfd267185eb2bb7269d1fb6cde48bc0edf23495737a6b5b85121fa9b1 We have identified the cause of the networking issue in Oracle Cloud. Oracle Cloud has confirmed an ongoing NOC outage in Oracle Cloud in us-ashburn-1. We are moving capacity to other cloud providers right now. https://status.modal.com/incident/535052 Wed, 26 Mar 2025 19:04:00 -0000 https://status.modal.com/incident/535052#f41c7ac044098f284131f6d1819c41491e72addad6fb734b6464379878948f12 We have identified networking issues with generalized user impact https://status.modal.com/incident/535052 Wed, 26 Mar 2025 18:41:00 -0000 https://status.modal.com/incident/535052#91ccfd1b7643b90acf126e41d9f44b9b3cabd28f6aaaff80721e3211481ce488 We are investigating networking issues in some of our hardware, which is causing errors connecting TCP sockets on sandboxes. https://status.modal.com/incident/532418 Fri, 21 Mar 2025 22:45:14 -0000 https://status.modal.com/incident/532418#c60073c7203d2d366f08832bc7da04e7573b2f063fd1ea420b6e4fe1623a28ba Volumes and Image builds recovered. https://status.modal.com/incident/532418 Fri, 21 Mar 2025 21:52:57 -0000 https://status.modal.com/incident/532418#fdf8a907930593089cd49e1f59edc06f78b36622b8a0a5dcab478748381d8efd Volumes went down. https://status.modal.com/incident/532418 Fri, 21 Mar 2025 21:50:27 -0000 https://status.modal.com/incident/532418#53d3a52a229438c6dd7d8db3647b14bdfe670885a6638319b8acf0fc72fc3443 Image builds went down. https://status.modal.com/incident/530407 Tue, 18 Mar 2025 21:50:53 -0000 https://status.modal.com/incident/530407#2ebfcc89a48ef8284d64a07fd109cdcd032639fc915ff56c39704781c7a4fb78 Image builds recovered. https://status.modal.com/incident/530407 Tue, 18 Mar 2025 21:47:14 -0000 https://status.modal.com/incident/530407#21cafeba84a786d0381cef105edc3ade90a9427a2cac59b4644e12ad2ac5b94d Image builds went down. https://status.modal.com/incident/518359 Mon, 24 Feb 2025 22:44:00 -0000 https://status.modal.com/incident/518359#91beaa076d30a3a8b42368e23523b1378192f5e35835ab0f7cd79122a1e81794 Everything is back up. https://status.modal.com/incident/518359 Mon, 24 Feb 2025 22:31:00 -0000 https://status.modal.com/incident/518359#77ae8f4a4847fa40f12b81a6761d48f4c8a86bd418cc5db915e69dd0f7322227 Image builds and some dashboard pages are currently not loading due issues with the metrics database. We are investigating. https://status.modal.com/incident/514631 Tue, 18 Feb 2025 03:37:48 -0000 https://status.modal.com/incident/514631#7767e45b8aaabbfae457ca1c6a506493ebfe2b81cd37f6ceaad56a48ef1f0cd1 CPU functions, GPU functions, and Image builds recovered. https://status.modal.com/incident/514631 Tue, 18 Feb 2025 03:36:31 -0000 https://status.modal.com/incident/514631#e7cd8ab92e003cd992974de449ef44c96830eadab049c628614e34d4fed9741b GPU functions and Image builds went down. https://status.modal.com/incident/514631 Tue, 18 Feb 2025 03:35:27 -0000 https://status.modal.com/incident/514631#d7f3e5d8d7d7add48067777b250969f334527b56b280e1050417fe5353a5add8 CPU functions went down. https://status.modal.com/incident/511178 Tue, 11 Feb 2025 18:16:00 -0000 https://status.modal.com/incident/511178#24b2f296ecf2c0e9ec852d304a231f3880911e6b28b12a8e49254b28793d75d7 Web endpoints, Frontend, Web API, and 1 other resource recovered. https://status.modal.com/incident/511180 Tue, 11 Feb 2025 18:13:00 -0000 https://status.modal.com/incident/511180#fe0874fa7b50462cd5974cc5ad0bb0d4cd7f0d2a13bc5ddf9fb9b6dbea1f9c07 Modal systems are back up. We're monitoring closely. https://status.modal.com/incident/511178 Tue, 11 Feb 2025 18:09:53 -0000 https://status.modal.com/incident/511178#f56aa733f70e0afd2a6679aaa84a315ae7ba3f65f660481eb3b79702cc49b73d Frontend and Web API went down. https://status.modal.com/incident/511178 Tue, 11 Feb 2025 18:09:22 -0000 https://status.modal.com/incident/511178#7fa53413a8c3af0f6cf17306b6d45e84cda610ab09da7d94eb01b4a55147cdde Web endpoints went down. https://status.modal.com/incident/511178 Tue, 11 Feb 2025 18:09:00 -0000 https://status.modal.com/incident/511178#0b6651ad5a52348562865df49224160a9baf95babb8fa31287ba084435759453 OIDC Endpoint went down. https://status.modal.com/incident/511180 Tue, 11 Feb 2025 18:09:00 -0000 https://status.modal.com/incident/511180#507e98f84d510595ca2789a136b785dd30f361c344f391e7d86cb59a49c95216 All Modal services are affected. We're working on rolling back the change. https://status.modal.com/incident/508457 Thu, 06 Feb 2025 18:00:39 -0000 https://status.modal.com/incident/508457#6db191a5e4d8bd835e7c585c2714933e5e2c406718bd0022c2d4b52ebe51b6be During this time, Modal is expected to work. There may be potential degraded performance (hopefully short-lived). https://status.modal.com/incident/501380 Fri, 24 Jan 2025 18:50:00 -0000 https://status.modal.com/incident/501380#76310c5fea622a43d6eb5aa32e8ff736319eeedf768671d30caad1602aa621af We have resolved the issue. The modal.com dashboard has been back online since about 1:40 PM ET, 10 minutes ago. Deployments are stable again. We are continuing to monitor. https://status.modal.com/incident/501380 Fri, 24 Jan 2025 18:16:00 -0000 https://status.modal.com/incident/501380#9774060e8e6b161b965028880be33fd211def8d877934aba47f1dd19c614a375 The modal.com web dashboard is unavailable and returning 502s. We are investigating and believe we have diagnosed the problem. https://status.modal.com/incident/495966 Wed, 15 Jan 2025 01:27:22 -0000 https://status.modal.com/incident/495966#20f5b92241e5eecbbf5f3b7c6e621971e119f7e280c096e3afe21faff5337c4f Web endpoints recovered. https://status.modal.com/incident/495966 Wed, 15 Jan 2025 01:08:27 -0000 https://status.modal.com/incident/495966#799b138de5157043f19d207ad9cf3355136561090d375bce4da3af9e8a7ddb2e Web endpoints went down. https://status.modal.com/incident/493416 Thu, 09 Jan 2025 19:35:00 -0000 https://status.modal.com/incident/493416#85513c2b80fc600f0b634c8147c06e4841c52a8b5523f38ea6a132fcbc137d97 Systems have fully recovered. https://status.modal.com/incident/493416 Thu, 09 Jan 2025 19:00:00 -0000 https://status.modal.com/incident/493416#99b0d8dac3190a63edf78d99dc8888e13509beb5fcb3e72f0ef0827388a72baa We are experiencing performance degradation across all Functions and web endpoint calls. https://status.modal.com/incident/473022 Thu, 05 Dec 2024 18:04:36 -0000 https://status.modal.com/incident/473022#009d7106ba28f2a790dfae8497a0649b636a643375ae2b484fcdfdc5f37a64fb Snapshot restores (beta) recovered. https://status.modal.com/incident/473022 Thu, 05 Dec 2024 18:02:30 -0000 https://status.modal.com/incident/473022#2f256780dc8ee8db894f631a523cfdae0c40bac7d187933b23ecce59784d6be6 Snapshot restores (beta) went down. https://status.modal.com/incident/462246 Wed, 04 Dec 2024 16:00:00 -0000 https://status.modal.com/incident/462246#0fd064f54fd807dc30b225c6b61d9c37387dd0055b48bc1934c535f8c7425f75 We will be performing a scheduled upgrade. https://status.modal.com/incident/453461 Thu, 31 Oct 2024 15:00:18 -0000 https://status.modal.com/incident/453461#2e4bb5317e460618c4c5b0cec71e277d96d193ebd29f825c8bc8040f66ecc818 We are updating the DNS records of our website at modal.com to point to a new CDN deployment. We expect this to be a seamless transition with no observable downtime, but we are declaring a maintenance window as a precaution. (Your website will just get faster!) https://status.modal.com/incident/453967 Thu, 31 Oct 2024 14:52:01 -0000 https://status.modal.com/incident/453967#e3f5564cc58b678ff56700b8c31d9c62fff336949cc07f3059ffd55fae5e38d1 Volumes recovered. https://status.modal.com/incident/453967 Thu, 31 Oct 2024 14:30:37 -0000 https://status.modal.com/incident/453967#e5e8ab8db7d0ba242839c167bf0b07b095d9f92bd2aaff362bb1771ea5f1a9ca Volumes went down. https://status.modal.com/incident/437215 Mon, 30 Sep 2024 21:17:34 -0000 https://status.modal.com/incident/437215#381b1fe087599e235db55914957947640956ce5b55e205aa7a03de64fff826df Image builds recovered. https://status.modal.com/incident/437215 Mon, 30 Sep 2024 21:14:48 -0000 https://status.modal.com/incident/437215#3b6ecb2015a267c40b9e3713b130aeb7b2cb0477ecb0f2299ac8a07ba7919677 Image builds went down. https://status.modal.com/incident/435873 Tue, 24 Sep 2024 17:51:00 -0000 https://status.modal.com/incident/435873#ed7dcb28e0259bcfeca74e18db56dd36486c5474811e906794d9cf97bd6a503f Between Monday 23rd 15:54 UTC and 15:36 UTC a change was made to make GCP workers poll more quickly for containers and this caused them to pick up more CPU-only containers. Between 13:48 UTC and 16:18 UTC on September 24th CPU containers were allowed to be scheduled on GCP NVIDIA T4 workers which are the `n1` class of GCE VMs. Both of these changes combined to cause over-scheduling of CPU work onto GCP T4 workers and significantly degrade the performance of the hosted containers (whether CPU-only or T4 GPU-enabled). https://status.modal.com/incident/428812 Fri, 13 Sep 2024 17:59:00 -0000 https://status.modal.com/incident/428812#900c60fffe241a3d019100cc00a95775712007ce7dd4608bdf8350c7f335fb68 At 12:57 UTC a container filesystem change rolled out across workers which caused spurious 'file not found' (ENOENT) errors against the container's rootfs filesystem. We identified the bad commit and rolled back to prevent new workers from picking up the bug. We then worked to roll over all running production workers which were affected by the bad change and scale up new workers. All affected workers have been quarantined and thus new containers will start on new, healthy workers. We apologize for the disruption. https://status.modal.com/incident/403407 Thu, 25 Jul 2024 06:50:00 -0000 https://status.modal.com/incident/403407#f80f17e70dd761e03b779899c356178392246e169b67b81b618c58ea9b9c78c7 Trigger processing issues have caused issues in ephemeral Apps and modal.Image builds. We're investigating. https://status.modal.com/incident/399044 Tue, 16 Jul 2024 18:43:00 -0000 https://status.modal.com/incident/399044#9c5278190d01f0fa78ce0813c0c185ab566dc171188bb7ad1a126c3c5066594f The system has recovered, and function executions should be proceeding as normal. The team is on standby for any further issues. https://status.modal.com/incident/399044 Tue, 16 Jul 2024 18:42:00 -0000 https://status.modal.com/incident/399044#0539c22c8abe20caaf6acc34aa91106cfcd506684f496dc334eb74b07081b060 We have identified the problem and are recovering at the moment. https://status.modal.com/incident/399044 Tue, 16 Jul 2024 17:53:00 -0000 https://status.modal.com/incident/399044#3a901b892d4e6aad1f0b172096c7ef535210679d570b5746ce4b7aa225d0ab71 We are seeing degraded performance on Modal function executions and are investigating. https://status.modal.com/incident/397339 Fri, 12 Jul 2024 23:35:09 -0000 https://status.modal.com/incident/397339#b3634f16065029d0cd8a2db5ad9454be4b1c17eb4bf0401ebc54c6c37f8bdd4b Web endpoints recovered. https://status.modal.com/incident/397339 Fri, 12 Jul 2024 23:29:58 -0000 https://status.modal.com/incident/397339#9620b91bdaedde3c63229ec065147658982849401caebe6ce02f1c0d43d063ea CPU functions on GCP and Volumes recovered. https://status.modal.com/incident/397339 Fri, 12 Jul 2024 23:29:42 -0000 https://status.modal.com/incident/397339#07706af992b9dfc3b020323accc702991ab370062a774b4bf81c8e7ff90fb810 Volumes went down. https://status.modal.com/incident/397339 Fri, 12 Jul 2024 23:28:41 -0000 https://status.modal.com/incident/397339#1d58c510c17c3423d1cd4aaf519967762713e952f3cbcbb08ae5ebcebfc1e7ca Web endpoints went down. https://status.modal.com/incident/397339 Fri, 12 Jul 2024 16:56:13 -0000 https://status.modal.com/incident/397339#49cb8b61cc9f150e04f6884924031c8de1bd59756e8e66db81e804b97fddf0a1 Web endpoints recovered. https://status.modal.com/incident/397339 Fri, 12 Jul 2024 16:50:11 -0000 https://status.modal.com/incident/397339#c6f9add039a8c2def062c27555dd17f73e411ab3f94b0161421d8bfc381a4721 Web endpoints went down. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:47:03 -0000 https://status.modal.com/incident/384368#8a57b7409f0f90df75fc460aad856f879789ee2977436ddd494ce8a951965f5a Web API recovered. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:46:47 -0000 https://status.modal.com/incident/384368#ae932190df420d12678e43edd66e396bebdcaabe3ab48a111ab054186a729910 Web endpoints recovered. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:41:15 -0000 https://status.modal.com/incident/384368#35101176735e17cd71c9bcbdae693651c490a345abdf31cae11fd7aab9f72621 Volumes recovered. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:40:18 -0000 https://status.modal.com/incident/384368#7f16eccb7c3ab2d244c2ecfed2cfdf34301e0f03c8d39c721363ade985511626 CPU functions on AWS recovered. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:39:13 -0000 https://status.modal.com/incident/384368#07136e9099192a1341fd77b90ce6771730b85fa3311fed4ea7a82e78c6e3d197 CPU functions on AWS, CPU functions on OCI, and Volumes went down. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:34:29 -0000 https://status.modal.com/incident/384368#bbbf51ea8a0841d5f60f0ac47de315fee13034ac128476727b63d0dbc9b66aaf Web API went down. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:30:08 -0000 https://status.modal.com/incident/384368#75b6086b1cb51ffa0cb4a814f363651b437c9cb8957ec8079deb58e2204feb6f Web API recovered. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:21:57 -0000 https://status.modal.com/incident/384368#0aef0635cb9e173df0f80033ef143785f95a92f3d6406a4454ec70717a509766 CPU functions on AWS and Volumes recovered. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:21:37 -0000 https://status.modal.com/incident/384368#41e332dc4fa3f3fb1a928dfc9b2db6c2159d7aa1edd945e12dd7a54039b535a2 CPU functions on AWS went down. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:20:48 -0000 https://status.modal.com/incident/384368#3a50c791a09e9cc0c6dc1358424aee386237a07d8552ee0ef887eda663689338 Volumes went down. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:17:57 -0000 https://status.modal.com/incident/384368#a76eaed96f78a7cd6d6d37b9538e08f857997f9d7a10fbb788cb54cf646c0d65 Web endpoints went down. https://status.modal.com/incident/384368 Fri, 14 Jun 2024 14:16:04 -0000 https://status.modal.com/incident/384368#0b6f0d5f217ef9efb02da7a53dab97ff8e7c053a2ab4b55f7a5bb39086e095ae Web API went down. https://status.modal.com/incident/379898 Wed, 05 Jun 2024 22:44:34 -0000 https://status.modal.com/incident/379898#0bdcdd6f4ef09b9554e9571dadf640a7ec711e9c8b2d540023209a0699e06787 Web endpoints recovered. https://status.modal.com/incident/379898 Wed, 05 Jun 2024 22:44:14 -0000 https://status.modal.com/incident/379898#874808f46c89f2bccfc697680884eb57f260bf2286dede4e5a559c6bac13c369 Web endpoints went down. https://status.modal.com/incident/379898 Wed, 05 Jun 2024 22:41:04 -0000 https://status.modal.com/incident/379898#e430380395c72dc143fc4dfeefb1acf5ddb92b0c37d085475dbcbf0b9c49da4e Web endpoints recovered. https://status.modal.com/incident/379898 Wed, 05 Jun 2024 22:36:40 -0000 https://status.modal.com/incident/379898#96d3b3fe383fb1263563bd450a47caf5f7873ac5b620f7caf18bdc8d02a27f43 Web endpoints went down. https://status.modal.com/incident/377009 Thu, 30 May 2024 18:00:00 -0000 https://status.modal.com/incident/377009#2ff6722f0aa027456a643d8ebf80638eeefdcc412cae3335811edb2f35af212b We're performing an infrastructure change on our website (modal.com). The dashboard may be inaccessible to some users for up to a minute. https://status.modal.com/incident/371971 Mon, 20 May 2024 07:42:07 -0000 https://status.modal.com/incident/371971#a888776a29d52c183297c091f9e0cae90ce8c4b6f9394573914b070752e70e71 Web endpoints recovered.