tag:status.okou.ai,2005:/history Okou Status - Incident history 2026-09-05T07:00:00.000+00:00 Okou tag:status.okou.ai,2005:Maintenance/cmtih1c6k04301bmfbkcec7tc 2026-09-05T07:00:00.000+00:00 2026-09-01T09:35:05.386+00:00 Scheduled maintaince for user auth system Type: Maintenance

Affected Components: Web Page

Sep 1, 09:35:05 GMT+0
Identified - We are planning for a scheduled maintenance during that time..

]]> tag:status.okou.ai,2005:Incident/cmtih8eec0ej01bmvfq509dkq 2026-08-31T22:27:56.967+00:00 2026-08-31T22:27:56.967+00:00 Elevated latency in the Responses API Type: Incident

Affected Components: OpenAI → APIs → Responses

Aug 31, 22:27:56 GMT+0
Identified - We have identified an issue causing elevated latency for some Responses API requests. We are working on implementing a mitigation..

Aug 31, 23:13:46 GMT+0
Monitoring - We have applied a mitigation and are monitoring recovery..

Sep 1, 01:46:22 GMT+0
Monitoring - We have applied the mitigation and are monitoring the recovery..

]]> tag:status.okou.ai,2005:Incident/cmtihb4k60g4s13mvbeqv0i7i 2026-08-31T18:47:05.000+00:00 2026-08-31T18:47:05.927+00:00 HTTP/3 issue affecting R2 custom domains Type: Incident

Affected Components: Cloudflare → Cloudflare Sites and Services → R2

Aug 31, 18:47:05 GMT+0
Investigating - Some Firefox users may see delayed or failed asset loads on R2 custom domains due to an incorrect HTTP/3 advertisement. We are working on a fix..

]]> tag:status.okou.ai,2005:Incident/cmtiha9o50e5e1mmvujjzh4nc 2026-08-31T13:55:24.852+00:00 2026-08-31T15:40:21.560+00:00 Elevated API latency Type: Incident

Duration: 4 days, 8 hours and 56 minutes

Affected Components: Clerk → Core services → Authentication & User

Aug 31, 15:40:21 GMT+0
Resolved - API performance has remained stable following mitigation. This incident has been resolved..

Aug 31, 13:42:00 GMT+0
Investigating - We're investigating elevated latency and intermittent timeouts affecting Clerk API requests. Some customers may see slow responses when loading user and organization data. Our team is looking into it and will post another update once we have more information..

Aug 31, 14:18:00 GMT+0
Identified - We identified elevated traffic affecting the Backend API and user-related requests, causing increased latency and intermittent failures. We've applied mitigation and are monitoring its effect. We'll provide another update once we confirm service stability..

Aug 31, 15:22:33 GMT+0
Monitoring - Mitigation has been applied and API performance has stabilized. We've deployed additional safeguards and are monitoring to confirm continued stability..

]]> tag:status.okou.ai,2005:Incident/cmtih7c320fwz13mvnes7qar7 2026-08-24T05:06:39.483+00:00 2026-08-24T05:06:39.640+00:00 Elevated errors for multiple models Type: Incident

Duration: 8 days, 12 hours and 8 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 24, 05:06:39 GMT+0
Investigating - We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, and Claude Opus 4.8. We will provide an update as soon as possible..

Aug 24, 05:27:45 GMT+0
Identified - We have identified the cause of elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, and other Claude models and are working on a fix. We will provide an update as soon as possible..

Aug 24, 06:42:37 GMT+0
Identified - We are continuing to work to resolve issues causing elevated requests on multiple models. We will provide an update as soon as possible..

Aug 24, 07:47:26 GMT+0
Identified - At this time, we have seen errors stabilize on Opus 5 and Fable 5, and are working to fully resolve success rates on all affected models. We will provide an update as soon as possible..

Aug 24, 08:30:47 GMT+0
Resolved - This issue has been resolved. From 9:50pm PT / 04:50 UTC through 00:36am PT / 07:36 UTC, users saw elevated errors on requests to Claude models, including Claude Opus 5 and Fable 5..

]]> tag:status.okou.ai,2005:Incident/cmtihb4k60g4q13mvtour3dqj 2026-08-24T03:53:58.184+00:00 2026-08-24T03:53:58.368+00:00 DO and D1 are degraded in Hong Kong and Singapore Type: Incident

Duration: 11 days, 10 hours and 24 minutes

Affected Components: Cloudflare → Cloudflare Sites and Services → R2

Aug 24, 03:53:58 GMT+0
Investigating - Some DOs and D1 databases may be experiencing issues in Hong Kong and Singapore. We are working to analyse and mitigate this problem. More updates to follow shortly..

Aug 24, 06:42:39 GMT+0
Monitoring - A fix has been implemented and we are monitoring the results..

Aug 24, 08:28:22 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtihb4k90g4t13mv39viyt50 2026-08-22T02:31:34.000+00:00 2026-08-22T02:31:34.000+00:00 Network connectivity issues in Dubai (DXB) Type: Incident

Duration: 1 day, 2 hours and 22 minutes

Affected Components: Cloudflare → Cloudflare Sites and Services → R2

Aug 22, 02:31:34 GMT+0
Investigating - Customers in Dubai may see increased error rates while connecting to Cloudflare services..

Aug 22, 02:57:56 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtihb4k60g4r13mvlsg1pncf 2026-08-21T14:59:50.689+00:00 2026-08-21T14:59:50.832+00:00 Increased Errors for Durable Objects in the Hong Kong region Type: Incident

Duration: 20 hours and 5 minutes

Affected Components: Cloudflare → Cloudflare Sites and Services → R2

Aug 21, 14:59:50 GMT+0
Investigating - Cloudflare is aware of, and investigating an issue with connectivity in the Hong Kong region. Customers trying to use R2, Durable Objects, and some other reliant products such as RealtimeKit in the aforementioned region may be experiencing an elevated level of errors and higher latencies. We are currently investigating this issue..

Aug 21, 15:11:56 GMT+0
Monitoring - A fix has been implemented and we are monitoring the results..

Aug 21, 15:19:56 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c2w0fwv13mvx21vbsgw 2026-08-20T19:16:24.923+00:00 2026-08-20T19:16:25.070+00:00 Elevated errors on requests to multiple models Type: Incident

Duration: 1 day, 2 hours and 13 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 20, 19:16:25 GMT+0
Investigating - We are investigating elevated errors on requests to some Claude models. We will provide additional updates as soon as possible..

Aug 20, 19:42:38 GMT+0
Resolved - This issue has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtihb4la0g4v13mvvn2j04ql 2026-08-20T18:51:08.474+00:00 2026-08-20T18:51:08.566+00:00 Elevated Errors R2 and Durable Objects Type: Incident

Duration: 1 day, 17 hours and 29 minutes

Affected Components: Cloudflare → Cloudflare Sites and Services → R2

Aug 20, 18:51:08 GMT+0
Identified - We have identified and issue that is causing elevated errors for R2 and Durable Objects..

Aug 20, 19:00:34 GMT+0
Monitoring - A fix has been implemented and we are monitoring the results..

Aug 20, 19:32:37 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c2w0fww13mvuaasv7jo 2026-08-20T18:32:13.285+00:00 2026-08-20T18:32:13.448+00:00 Elevated errors on Google connectors Type: Incident

Duration: 1 day, 4 hours and 50 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 20, 18:32:13 GMT+0
Investigating - We are investigating elevated errors affecting Google connectors (Sheets, Docs, Slides, and Chat) and custom Google integrations on Claude.ai. Core functionality is not affected. We will provide an update as soon as possible..

Aug 20, 19:01:03 GMT+0
Resolved - This issue has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtihcyiu0gy40wmv961k4rka 2026-08-20T17:46:33.302+00:00 2026-08-20T17:46:33.396+00:00 New container functions are failing Type: Incident

Duration: 1 day, 23 hours and 27 minutes

Affected Components: Vercel → Functions

Aug 20, 17:46:33 GMT+0
Identified - We've identified an issue where newly deployed container functions may return 5XX errors. Customers can use a previously working container function deployment as a temporary mitigation. We are working on a fix and will provide additional updates as they become available..

Aug 20, 18:23:05 GMT+0
Monitoring - We have deployed a fix. Newly deployed container functions are working as expected..

Aug 20, 18:34:00 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c2x0fwx13mvbnzmpmf7 2026-08-19T09:42:37.402+00:00 2026-08-19T11:02:18.264+00:00 Degraded performance for Claude Opus 5 and Claude Haiku 4.5 Type: Incident

Duration: 3 days, 7 hours and 40 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 19, 11:02:18 GMT+0
Resolved - This incident has been resolved..

Aug 19, 09:42:37 GMT+0
Identified - We have identified the cause of elevated errors on requests to Claude Opus 5 and Claude Haiku 4.5 and are working on a fix. We will provide an update as soon as possible..

Aug 19, 10:33:56 GMT+0
Monitoring - A fix has been implemented and we are monitoring the results..

]]> tag:status.okou.ai,2005:Incident/cmtih7c2t0fwu13mv0r9d9cv9 2026-08-18T16:20:22.231+00:00 2026-08-18T18:26:31.164+00:00 Degraded performance for multiple models Type: Incident

Duration: 6 days, 17 hours and 23 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 18, 18:26:31 GMT+0
Monitoring - A fix has been implemented and we are monitoring the results..

Aug 18, 16:20:22 GMT+0
Investigating - We are investigating reports of degraded performance affecting multiple models. We will provide an update as soon as possible..

Aug 18, 16:20:49 GMT+0
Investigating - We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, and other Claude models. We will provide an update as soon as possible..

Aug 18, 17:12:22 GMT+0
Investigating - We are investigating elevated errors on requests to Claude Opus 5. We will provide an update as soon as possible..

Aug 18, 19:01:45 GMT+0
Resolved - The issue affecting Claude Opus 5 has been resolved. Impact occurred from 16:11 to 18:23 UTC..

]]> tag:status.okou.ai,2005:Incident/cmtih7c2s0fwt13mvw14fba2b 2026-08-17T13:56:41.046+00:00 2026-08-17T13:56:41.229+00:00 Degraded performance for Claude Opus 5, Claude Sonnet 5 Type: Incident

Duration: 3 days, 20 hours and 44 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 17, 13:56:41 GMT+0
Investigating - We are investigating elevated errors on requests to Claude Opus 5. We will provide an update as soon as possible..

Aug 17, 14:25:27 GMT+0
Investigating - Claude Opus 5 is operational. Claude Sonnet 5 is degraded. We are investigating..

Aug 17, 14:39:58 GMT+0
Monitoring - A fix has been implemented and we are monitoring the results..

Aug 17, 15:29:25 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c300fwy13mvu0wdt0jt 2026-08-16T21:58:56.939+00:00 2026-08-16T22:22:35.586+00:00 Service disruption on Claude services Type: Incident

Duration: 1 day, 11 hours and 42 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 16, 22:22:35 GMT+0
Monitoring - A fix has been deployed for the issue affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork and we are monitoring for recovery..

Aug 16, 22:34:39 GMT+0
Resolved - The issue affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork has been resolved..

Aug 16, 21:58:57 GMT+0
Investigating - We are investigating an issue with users authenticating to claude.ai, Claude Code, and Claude Cowork. We will provide an update as soon as possible..

Aug 16, 22:02:03 GMT+0
Investigating - We are investigating reports of degraded performance affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork. We will provide an update as soon as possible..

]]> tag:status.okou.ai,2005:Incident/cmtih7c360fx213mvynfn98zb 2026-08-14T20:30:36.280+00:00 2026-08-14T20:30:36.389+00:00 Service disruption on Claude services Type: Incident

Duration: 3 days, 15 hours and 36 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 14, 20:30:36 GMT+0
Investigating - We are investigating reports of degraded performance affecting the Claude API, Claude Code, and Claude Cowork. We will provide an update as soon as possible..

Aug 14, 20:44:05 GMT+0
Identified - We have identified the cause of the issue affecting the Claude API, Claude Code, and Claude Cowork and are working on a fix. We will provide an update as soon as possible..

Aug 14, 20:44:58 GMT+0
Monitoring - A fix has been deployed for the issue affecting the Claude API, Claude Code, and Claude Cowork and we are monitoring for recovery..

Aug 14, 21:58:12 GMT+0
Resolved - The issue affecting the Claude API, Claude Code, and Claude Cowork has been resolved. Impact occurred from 20:14 to 20:38 UTC..

]]> tag:status.okou.ai,2005:Incident/cmtihb4k90g4u13mvl72k68dh 2026-08-14T15:34:21.619+00:00 2026-08-14T15:34:21.720+00:00 Increased network congestion in the Eastern US Type: Incident

Duration: 2 days and 6 hours

Affected Components: Cloudflare → Cloudflare Sites and Services → R2

Aug 14, 15:34:21 GMT+0
Identified - We are investigating network issues between Cloudflare colocations located in the eastern United States. This may cause increased errors and latency reaching Cloudflare storage products like R2 and Durable Objects..

Aug 14, 16:28:22 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmssf275703rb1bqtl8k0f7fu 2026-08-14T03:57:44.574+00:00 2026-08-14T03:57:44.574+00:00 Claude models are temporarily unavailable Type: Incident

Duration: 45 minutes

Affected Components: API Service

Aug 14, 03:57:44 GMT+0
Identified - Claude models are temporarily unavailable..

Aug 14, 04:43:01 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c340fx113mvxglo6k6k 2026-08-13T14:33:45.150+00:00 2026-08-13T14:33:45.313+00:00 Elevated errors for Claude Mythos 5, Claude Fable 5, and Claude Sonnet 5 Type: Incident

Duration: 3 days, 22 hours and 50 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 13, 14:33:45 GMT+0
Investigating - We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Sonnet 5. We will provide an update as soon as possible..

Aug 13, 15:44:45 GMT+0
Investigating - We are investigating elevated errors on requests to Claude Mythos 5 and Claude Fable 5. We will provide an update as soon as possible..

Aug 13, 16:08:35 GMT+0
Resolved - The issue affecting Claude Mythos 5 and Claude Fable 5 has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c330fx013mvvw4jmpzx 2026-08-12T13:50:28.450+00:00 2026-08-12T13:50:28.580+00:00 Degraded performance for multiple models Type: Incident

Duration: 10 days, 16 hours and 43 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 12, 13:50:28 GMT+0
Investigating - We are investigating elevated errors on requests to multiple models. We will provide an update as soon as possible..

Aug 12, 16:10:01 GMT+0
Identified - We have identified an issue which resulted in errors across multiple models. At this time, errors are primarily impacting Claude Fable 5 and we are working to fully resolve these issues..

Aug 12, 17:28:45 GMT+0
Identified - We are continuing to work to resolve an issue resulting in slightly elevated errors on requests to Claude Fable 5. We will provide an update as soon as possible..

Aug 12, 18:07:11 GMT+0
Resolved - This issue has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmspgpfi304pn0rlsaaa7h8s1 2026-08-12T01:52:00.000+00:00 2026-08-12T02:02:00.000+00:00 We've noticed some unexpected errors appearing in production. Type: Incident

Duration: 10 minutes

Affected Components: API Service

Aug 12, 02:02:00 GMT+0
Resolved - This incident has been resolved..

Aug 12, 01:52:00 GMT+0
Investigating - We are currently investigating this incident..

Aug 12, 02:21:53 GMT+0
Postmortem - This issue was caused by a database lock during one of our deployment tasks, which left the API unresponsive for the 9-minute duration of the lock. To prevent this from happening again, we're going to add checks during the code submission phase to prevent similar issues early..

]]> tag:status.okou.ai,2005:Incident/cmsn8tols1bt00zpqqkejgxwl 2026-08-10T13:04:18.756+00:00 2026-08-10T13:04:18.756+00:00 Some users are reporting errors on page. Type: Incident

Duration: 6 minutes

Affected Components: API Service

Aug 10, 13:04:18 GMT+0
Investigating - We are currently investigating this incident..

Aug 10, 13:08:00 GMT+0
Investigating - We're currently investigating issues from our recent deployment logs and trying to roll back the latest release..

Aug 10, 13:10:41 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c4o0fx413mvfzq6ob65 2026-08-05T13:51:30.277+00:00 2026-08-05T13:51:30.433+00:00 Degraded performance for Claude Opus 5 Type: Incident

Duration: 1 day, 18 hours and 44 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 5, 13:51:30 GMT+0
Identified - We have identified the cause of elevated errors on requests to Claude Opus 5 and are working on a fix. We will provide an update as soon as possible..

Aug 5, 14:34:15 GMT+0
Resolved - This incident has been resolved..

]]> tag:status.okou.ai,2005:Incident/cmtih7c4u0fx713mvapfoezq7 2026-08-05T07:05:54.000+00:00 2026-08-05T09:13:49.089+00:00 Degraded performance of multiple models Type: Incident

Duration: 17 days, 20 hours and 42 minutes

Affected Components: Claude → Claude API (api.anthropic.com)

Aug 5, 09:13:49 GMT+0
Identified - We are continuing to work on a fix for this issue..

Aug 5, 13:08:34 GMT+0
Monitoring - A fix has been deployed for the issue affecting Claude services and we are monitoring for recovery..

Aug 5, 14:14:36 GMT+0
Resolved - This incident has been resolved..

Aug 5, 07:05:54 GMT+0
Identified - We have identified the cause of elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Opus 5, Claude Sonnet 5 and are working on a fix. We will provide an update as soon as possible..

]]> tag:status.okou.ai,2005:Incident/cmtiha9n70e5c1mmvhyd5hjb1 2026-08-04T23:03:58.879+00:00 2026-08-04T23:29:11.464+00:00 Increased API latency and errors Type: Incident

Duration: 1 day, 12 hours and 51 minutes

Affected Components: Clerk → Core services → Authentication & User

Aug 4, 23:29:11 GMT+0
Monitoring - Our upstream provider has applied a fix and we've seen latency and errors subside. We continue to monitor the situation..

Aug 4, 23:03:58 GMT+0
Investigating - We are currently investigating an increase in latency and errors in our FAPI and BAPI services..

Aug 4, 23:14:01 GMT+0
Identified - We've identified the issue with our upstream provider and are working on resolution..

Aug 4, 23:40:50 GMT+0
Resolved - We've resolved the issue with our upstream provider..

]]>