Status updates | Neuralwatt Incidents and maintenance reported on status page for Neuralwatt https://neuralwatt.betteruptime.com/ https://d1lppblt9t2x15.cloudfront.net/logos/0e4af78e591cbc63878b08e38e90a498.png Status updates | Neuralwatt https://neuralwatt.betteruptime.com/ en GLM-5.3-Flash degraded: slow or stalled responses https://neuralwatt.betteruptime.com/incident/1130803 Fri, 20 Nov 2026 01:59:10 -0000 https://neuralwatt.betteruptime.com/incident/1130803#10db8901a6d34c98a47bb24da7f04ad709a6dd10f8276e86e276446debbae4e4 Incident The fix is deployed to all GLM-5.3-Flash capacity and responses are back to normal. We will keep monitoring closely. GLM-5.3-Flash degraded: slow or stalled responses https://neuralwatt.betteruptime.com/incident/1130803 Fri, 20 Nov 2026 01:39:19 -0000 https://neuralwatt.betteruptime.com/incident/1130803#05cd633b099adea843672abc3d39914e5e913343a22b6856fe86f441d21bcef1 Incident The fix is live on part of GLM-5.3-Flash capacity and we are completing the rollout now. Responses should be returning to normal; we will update when it is fully complete. GLM-5.3-Flash degraded: slow or stalled responses https://neuralwatt.betteruptime.com/incident/1130803 Fri, 20 Nov 2026 01:13:22 -0000 https://neuralwatt.betteruptime.com/incident/1130803#b3ddfbdfd42fa16b3432a4c1d30824da003758e50e829c526976ae24b0832050 Incident We identified the cause: certain very long tool-heavy conversations take minutes to prepare, which holds up other requests on the same server. A fix is tested and being rolled out now. You may still see occasional slow responses on GLM-5.3-Flash until it completes. GLM-5.3-Flash degraded: slow or stalled responses https://neuralwatt.betteruptime.com/incident/1130803 Fri, 20 Nov 2026 00:58:09 -0000 https://neuralwatt.betteruptime.com/incident/1130803#9d83e5d8d29e0228d42701c911c58c54f7c54426a81abe3f96665b6f15ab3553 Incident Since about 23:55 UTC some GLM-5.3-Flash requests have been slow to start or have stalled. We have identified the cause and are restoring capacity now. Other models are not affected. mimo-v2.6-pro and glm-5.3-flash are down https://neuralwatt.betteruptime.com/incident/1125770 Sun, 15 Nov 2026 20:39:46 -0000 https://neuralwatt.betteruptime.com/incident/1125770#c1be94b13186d566796ee71798244fb7bb51ad3e73ff86a42740831dd88ca968 Incident glm-5.3-flash recovered. mimo-v2.6-pro and glm-5.3-flash are down https://neuralwatt.betteruptime.com/incident/1125770 Sun, 15 Nov 2026 20:35:10 -0000 https://neuralwatt.betteruptime.com/incident/1125770#61fc9e4e82f4040ba48115a7152ff8d66abfc13fa0fefba6819d45cf8d110613 Incident glm-5.3-flash went down. GLM-5.3-Flash unavailable https://neuralwatt.betteruptime.com/incident/1126172 Sun, 15 Nov 2026 20:34:58 -0000 https://neuralwatt.betteruptime.com/incident/1126172#736e8a3d4d0c9431bf7fb3e41e4005fc1c0d8cb3ab152adb85d055738db60f21 Incident glm-5.3-flash has recovered and has been serving normally since 20:24 UTC. Requests between about 20:11 and 20:24 UTC may have failed. We're reviewing the cause and will make sure it doesn't recur. GLM-5.3-Flash unavailable https://neuralwatt.betteruptime.com/incident/1126172 Sun, 15 Nov 2026 20:19:30 -0000 https://neuralwatt.betteruptime.com/incident/1126172#31fda7787959a75707b3539f5e615574140601270b2df7462e4efb9e64553239 Incident We're investigating an outage affecting glm-5.3-flash (and glm-5.3-flash-flex). Requests to this model may fail with errors. Other models are not affected. We'll post an update as soon as we know more. mimo-v2.6-pro and glm-5.3-flash are down https://neuralwatt.betteruptime.com/incident/1125770 Sun, 15 Nov 2026 05:17:21 -0000 https://neuralwatt.betteruptime.com/incident/1125770#b196d085770486a373ecdea8ae5daaa204ff0fb305c8f4cdf4ebc25dc31e2754 Incident mimo-v2.6-pro recovered. mimo-v2.6-pro and glm-5.3-flash are down https://neuralwatt.betteruptime.com/incident/1125770 Sun, 15 Nov 2026 04:46:18 -0000 https://neuralwatt.betteruptime.com/incident/1125770#2fe58deabd80b00e6d963344c2dbf0e62caa783ddff5878b002395bea9d84fee Incident mimo-v2.6-pro went down. Portal login temporarily unavailable https://neuralwatt.betteruptime.com/incident/1123446 Thu, 12 Nov 2026 17:01:25 -0000 https://neuralwatt.betteruptime.com/incident/1123446#3cf075b6eefa5d83c5c96221b946024d94d644713919e4ff1acb89f456f6b0a0 Incident Maintenance is complete and portal sign-in is working again. Usage figures on the portal may take a few minutes to catch up. Thanks for your patience. Portal login temporarily unavailable https://neuralwatt.betteruptime.com/incident/1123446 Thu, 12 Nov 2026 16:25:25 -0000 https://neuralwatt.betteruptime.com/incident/1123446#3f8bcd9c6c6805d343608a76265cd5e84575cf2492b0ea7624618a5493713563 Incident We're performing scheduled maintenance. Signing in to the portal and viewing usage may fail for a short time. The API and models continue to serve requests. We'll update this when it's resolved. glm-5.3-flash is down https://neuralwatt.betteruptime.com/incident/1120546 Tue, 10 Nov 2026 04:09:40 -0000 https://neuralwatt.betteruptime.com/incident/1120546#9583a6c1af3bc586c3861e55f4e0dd69ebc49459084051bb40c02c952ccee703 Incident glm-5.3-flash recovered. glm-5.3-flash is down https://neuralwatt.betteruptime.com/incident/1120546 Tue, 10 Nov 2026 04:00:26 -0000 https://neuralwatt.betteruptime.com/incident/1120546#eeeb98a7fb6bd9fb23d4a242141df288af73fe18becae2c0ab902c6993bc6000 Incident glm-5.3-flash went down. Some services are down https://neuralwatt.betteruptime.com/incident/1120535 Tue, 10 Nov 2026 04:00:16 -0000 https://neuralwatt.betteruptime.com/incident/1120535#e0774cf0c52504759f0dbd77af6be466728071aa1e641bee5690676006064123 Incident Resolved. GLM-5.3-Flash requests stalled or failed from about 03:18 to 03:53 UTC, when both servers for the model stopped responding and were restarted. It has served normally since 03:53 UTC. We are reviewing the cause. Some services are down https://neuralwatt.betteruptime.com/incident/1120535 Tue, 10 Nov 2026 03:42:42 -0000 https://neuralwatt.betteruptime.com/incident/1120535#c9c51440de7696d4f71683e5c2b7767cf239085f4082f1b197114c00ac8ef884 Incident glm-5.3-flash went down. Maintenance: Brief maintenance window https://neuralwatt.betteruptime.com/maintenance/1112644 Tue, 03 Nov 2026 16:44:25 -0000 https://neuralwatt.betteruptime.com/incident/1112644#d03b2c898fcf5e34a5914ecd06cfe49dced8409210d7715664cfe81954fe4ef0 Maintenance Maintenance is complete. All endpoints are operating normally. Maintenance: Brief maintenance window https://neuralwatt.betteruptime.com/maintenance/1112644 Tue, 03 Nov 2026 16:44:25 -0000 https://neuralwatt.betteruptime.com/incident/1112644#bd0f7f9f2cd7db8a9fe678acc4615f6b5126e31a0ee5973aab55452edb3d6eed Maintenance Maintenance completed Maintenance: Brief maintenance window https://neuralwatt.betteruptime.com/maintenance/1112644 Tue, 03 Nov 2026 16:36:38 -0000 https://neuralwatt.betteruptime.com/incident/1112644#4b2734ec71033ddce5103a7cb50f3b50946cfa64a61c00ae474c54b4f9007509 Maintenance Running a brief maintenance window. /v1/messages, /v1/responses, embeddings and decision model endpoints may see short interruptions during it. We don't expect any impact to /v1/chat/completions. Expected to last a few minutes, no action needed on your side. We'll update here when it's complete. deepseek-v4-flash is down https://neuralwatt.betteruptime.com/incident/1106858 Wed, 28 Oct 2026 15:34:41 -0000 https://neuralwatt.betteruptime.com/incident/1106858#dc53a82c0e6e4e7c8b23d5ad3f37ee174ee031740008f24b178e292d568a7132 Incident deepseek-v4-flash recovered. deepseek-v4-flash: requests failing or timing out https://neuralwatt.betteruptime.com/incident/1106865 Wed, 28 Oct 2026 15:22:15 -0000 https://neuralwatt.betteruptime.com/incident/1106865#591d8c367c741244e413c53eb4b24e53fecccbf00fe57be14bac0b46f768ff1d Incident Resolved. deepseek-v4-flash recovered at about 15:19 UTC after the affected servers were restarted, and requests are completing normally. We are investigating the root cause to prevent a recurrence. deepseek-v4-flash: requests failing or timing out https://neuralwatt.betteruptime.com/incident/1106865 Wed, 28 Oct 2026 15:08:14 -0000 https://neuralwatt.betteruptime.com/incident/1106865#cb339a3dbb08537ec06e852812e69fbbb7f8746bfe402d53ac2e941a8f43b3ad Incident Since about 14:47 UTC, most requests to deepseek-v4-flash (standard and flex) are failing or timing out. The speed tier (deepseek-v4-flash-speed) is not affected. We have identified the cause and are restarting the affected servers now; we expect service to recover within about 20 minutes. We will post an update when it is restored. deepseek-v4-flash is down https://neuralwatt.betteruptime.com/incident/1106858 Wed, 28 Oct 2026 15:01:37 -0000 https://neuralwatt.betteruptime.com/incident/1106858#a049c0b0e251b8391d44e7c40ffb5301cbcc4742a0db5c7def66d47460202b92 Incident deepseek-v4-flash went down. glm-5.3-flash is down https://neuralwatt.betteruptime.com/incident/1103696 Mon, 26 Oct 2026 13:13:54 -0000 https://neuralwatt.betteruptime.com/incident/1103696#5dabf6fde8ca0f473a05f96951efd01a8973799799d04ca000360a8b7ea84771 Incident glm-5.3-flash recovered. glm-5.3-flash is down https://neuralwatt.betteruptime.com/incident/1103696 Mon, 26 Oct 2026 13:03:51 -0000 https://neuralwatt.betteruptime.com/incident/1103696#4bd11604c1ab0350e0bed0a321f9306752c13e66ff50aacdbc48712311dbfe04 Incident glm-5.3-flash went down. Some services are down https://neuralwatt.betteruptime.com/incident/1102793 Mon, 26 Oct 2026 12:20:00 -0000 https://neuralwatt.betteruptime.com/incident/1102793#eb253f3ec4e1fc580461b84553c9529e82035cb82a17a3d5156554c303c3c673 Incident GLM 5.3-flash now back to full serving. Degraded performance on some models due to an upstream network issue https://neuralwatt.betteruptime.com/incident/1100568 Fri, 23 Oct 2026 19:06:37 -0000 https://neuralwatt.betteruptime.com/incident/1100568#dd4ab609c28fded803fb2b8416a497b988e7603ce3d333a9282b992acc471b7c Incident Resolved: Both upstream providers have resolved their network incidents (Cloudflare's connectivity provider and our Finland infrastructure provider). Error rates and latency have been back to normal across all models since ~17:30 UTC. We apologize for the disruption. Degraded performance on some models due to an upstream network issue https://neuralwatt.betteruptime.com/incident/1100568 Fri, 23 Oct 2026 16:02:31 -0000 https://neuralwatt.betteruptime.com/incident/1100568#f43969ee36e34ffd0cc2e20f85cf007e7e7867ea0042680f79f61c438ea0792b Incident Update: We've identified two separate upstream issues. (1) Cloudflare is investigating degraded network performance between its Ashburn and Atlanta data centers (https://www.cloudflarestatus.com/incidents/sufgcbe8rrwt), which caused intermittent connection errors (HTTP 520/525) across all models between ~15:20 and ~15:45 UTC; error rates have since dropped back to near normal. (2) A network incident at one of our infrastructure providers in Finland is causing higher latency on mimo-v2.6-pro, glm-5.3-flash, deepseek-v4-flash and gemma-4-31b; it is improving. We'll update when both are resolved. Degraded performance on some models due to an upstream network issue https://neuralwatt.betteruptime.com/incident/1100568 Fri, 23 Oct 2026 15:49:43 -0000 https://neuralwatt.betteruptime.com/incident/1100568#866b04912e278e33947c30f3520f9df80a1d3c6e384621c73e76ef9f76ba5ca7 Incident Update: The same upstream network issue also caused a small number of connection errors (HTTP 520/525) across all models between ~15:20 and ~15:45 UTC. Errors have dropped sharply since; we're continuing to monitor. Degraded performance on some models due to an upstream network issue https://neuralwatt.betteruptime.com/incident/1100568 Fri, 23 Oct 2026 15:43:33 -0000 https://neuralwatt.betteruptime.com/incident/1100568#9d815f4064e692292e55bf22b199fb5e9e68b8995aa65c6bce66fd9955a83c01 Incident We're seeing elevated latency and intermittent connection issues for some models, caused by a network incident at one of our infrastructure providers in Finland (started ~15:20 UTC). Requests are being served, but some may see slower time-to-first-token or occasional dropped connections. Other models are unaffected. We're monitoring closely and will update when the provider resolves the issue. qwen-3.8-27b is down https://neuralwatt.betteruptime.com/incident/1100439 Fri, 23 Oct 2026 13:53:01 -0000 https://neuralwatt.betteruptime.com/incident/1100439#7576b4abe57fef10e0c6f248e040479f8f77eac5c9a2f6384f17246f24b3b591 Incident qwen-3.8-27b recovered. qwen-3.8-27b is down https://neuralwatt.betteruptime.com/incident/1100439 Fri, 23 Oct 2026 13:27:01 -0000 https://neuralwatt.betteruptime.com/incident/1100439#bd2079d48b74a80bc2ca64c5cc5b1230f5d6ba80f0f4a88f84030a0ec96140b2 Incident qwen-3.8-27b went down. GLM-5.3-Flash unavailable https://neuralwatt.betteruptime.com/incident/1091238 Thu, 15 Oct 2026 15:54:00 -0000 https://neuralwatt.betteruptime.com/incident/1091238#522830560d815e15b0fa63c82cfdf301a9d5ab5d11df1c2939be0eeb19406741 Incident Resolved. GLM-5.3-Flash has served normally since 15:54 UTC. We are reviewing how we run maintenance on this model so this does not recur. GLM-5.3-Flash unavailable https://neuralwatt.betteruptime.com/incident/1091238 Thu, 15 Oct 2026 15:46:00 -0000 https://neuralwatt.betteruptime.com/incident/1091238#3e57188d92c587d5ecea66350bf7929d74706c393ccc1c9ed0086d030ee9659f Incident GLM-5.3-Flash requests failed with "no healthy replicas" from about 15:46 to 15:54 UTC. During planned maintenance on the model, a serving process stalled and had to restart. The maintenance is postponed to a lower-traffic window.