History

All impacted services have now fully recovered.

1. identified Aug 7, 2026, 7:52 AM GMT+08:00

   We have identified that some users may be experiencing issues with computer use in the latest ChatGPT desktop app update. We are working on implementing a mitigation.

2. resolved Aug 7, 2026, 8:30 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. monitoring Aug 6, 2026, 1:06 AM GMT+08:00

   Error rates affecting ChatGPT conversations that use files and images have improved. We have applied the mitigation and are monitoring the recovery.

2. resolved Aug 6, 2026, 4:19 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Aug 6, 2026, 12:55 AM GMT+08:00

   We are investigating the issue for the listed services.

2. identified Aug 6, 2026, 2:28 AM GMT+08:00

   We are still implementing the mitigation.

3. monitoring Aug 6, 2026, 3:03 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

4. monitoring Aug 6, 2026, 6:46 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

5. resolved Aug 6, 2026, 6:49 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Aug 5, 2026, 10:55 PM GMT+08:00

   We are investigating elevated errors affecting image generation. Some users may experience failed image generation requests. We are working to reduce the errors and will provide another update as we learn more.

2. monitoring Aug 5, 2026, 11:28 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Aug 6, 2026, 7:22 AM GMT+08:00

   All impacted services have now fully recovered.

We have identified the cause of elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Opus 5 and are working on a fix. We will provide an update as soon as possible.

1. identified Aug 5, 2026, 3:05 PM GMT+08:00

   We have identified the cause of elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Opus 5 and are working on a fix. We will provide an update as soon as possible.

This issue has been resolved.

1. investigating Aug 5, 2026, 4:48 AM GMT+08:00

   We are currently investigating this issue.

2. investigating Aug 5, 2026, 5:04 AM GMT+08:00

   We have identified an issue which resulted in some users experiencing issues when attempting to log into Anthropic services, including Claude.ai and Claude Code via oAuth. Additionally, some users saw errors when making requests to models. At this time, we have seen success rates recover and are monitoring closely to ensure there are no further issues.

3. resolved Aug 5, 2026, 5:59 AM GMT+08:00

   This issue has been resolved.

All impacted services have now fully recovered.

1. investigating Aug 4, 2026, 8:43 PM GMT+08:00

   We are investigating elevated errors affecting ChatGPT conversations. Some users may experience failed or interrupted responses, and some conversation turns may not be saved. The issue is affecting users across Plus, Pro, Business and Edu ChatGPT plans.

2. monitoring Aug 4, 2026, 8:57 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Aug 4, 2026, 11:25 PM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Aug 4, 2026, 7:27 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Aug 4, 2026, 7:37 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Aug 4, 2026, 7:52 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Aug 4, 2026, 2:16 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Aug 4, 2026, 2:28 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Aug 4, 2026, 2:55 PM GMT+08:00

   This incident has been resolved.

As of 15:20 UTC (8:20am PT), error rates on Claude Sonnet 5 have returned to baseline. This incident is resolved.

1. investigating Aug 3, 2026, 11:13 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Aug 3, 2026, 11:29 PM GMT+08:00

   As of 15:20 UTC (8:20am PT), error rates on Claude Sonnet 5 have returned to baseline. This incident is resolved.

This incident has been resolved.

1. investigating Aug 3, 2026, 8:52 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Aug 3, 2026, 9:30 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Aug 3, 2026, 10:17 PM GMT+08:00

   This incident has been resolved.

This is now resolved.

1. identified Jul 31, 2026, 5:04 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. identified Jul 31, 2026, 5:05 PM GMT+08:00

   We have identified that some ChatGPT Business and Education users are experiencing elevated errors when starting or continuing conversations. We are working on implementing a mitigation and will provide another update as soon as we have more information.

3. monitoring Jul 31, 2026, 5:06 PM GMT+08:00

   The issue has been mitigated.

4. resolved Jul 31, 2026, 5:28 PM GMT+08:00

   This is now resolved.

This incident has been resolved.

1. investigating Jul 31, 2026, 2:18 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 31, 2026, 3:04 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. identified Jul 30, 2026, 10:35 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jul 30, 2026, 10:53 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. monitoring Jul 30, 2026, 11:26 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

4. resolved Jul 31, 2026, 12:01 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 30, 2026, 9:43 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 30, 2026, 10:24 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 30, 2026, 1:57 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 30, 2026, 2:26 PM GMT+08:00

   All models except Opus 5 have recovered. We're working to recover Opus 5 as well.

3. identified Jul 30, 2026, 3:33 PM GMT+08:00

   As of 7:32 UTC / 0:32 PT, Opus 5 errors are back to baseline but we're seeing again Sonnet 5's errors up.

4. identified Jul 30, 2026, 4:06 PM GMT+08:00

   As of 8:05 UTC / 1:05 PT, Sonnet 5 errors are back to baseline, but we're seeing an increased error rate on Fable 5.

5. identified Jul 30, 2026, 4:33 PM GMT+08:00

   As of 01:33 PT / 08:33 UTC we are back to errors across all models.

6. monitoring Jul 30, 2026, 6:03 PM GMT+08:00

   As of 2:58 PT / 9:58 UTC the errors are back to baseline.

7. monitoring Jul 30, 2026, 6:23 PM GMT+08:00

   We are also investigating issues with Opus 4.7 and Opus 4.5.

8. resolved Jul 30, 2026, 6:48 PM GMT+08:00

   This incident has been resolved.

This issue has been resolved.

1. investigating Jul 30, 2026, 3:49 AM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 30, 2026, 4:33 AM GMT+08:00

   We have identified an issue resulting in elevated errors across multiple models, and are working to resolve this. We will provide an update as soon as possible.

3. identified Jul 30, 2026, 5:38 AM GMT+08:00

   We are continuing to work to fully resolve issues resulting in elevated requests and latency to Claude models. At this time, we are seeing recovery across most models. We will provide an additional update as soon as possible.

4. monitoring Jul 30, 2026, 6:20 AM GMT+08:00

   From 12:45 PT / 19:45 UTC through to 1:26 PT / 21:26 UTC, we saw elevated rates of errors across Claude models. We have seen recovery in success rates across all models and are monitoring closely to ensure no further issues.

5. resolved Jul 30, 2026, 6:36 AM GMT+08:00

   This issue has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 29, 2026, 8:55 AM GMT+08:00

   We are investigating the issue for the listed services.

2. monitoring Jul 29, 2026, 9:39 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 29, 2026, 10:20 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jul 28, 2026, 10:39 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jul 28, 2026, 11:13 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 28, 2026, 11:15 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 27, 2026, 10:04 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. resolved Jul 28, 2026, 4:24 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 27, 2026, 11:30 PM GMT+08:00

   We are investigating the issue for the listed services.

2. resolved Jul 28, 2026, 1:30 AM GMT+08:00

   All impacted services have now fully recovered.

As of 7:34 PST / 14:34 UTC the errors have returned to baseline.

1. investigating Jul 27, 2026, 9:39 PM GMT+08:00

   We are currently investigating this issue.

2. investigating Jul 27, 2026, 9:41 PM GMT+08:00

   We are continuing to investigate this issue.

3. investigating Jul 27, 2026, 9:42 PM GMT+08:00

   We are currently investigating this issue.

4. investigating Jul 27, 2026, 10:04 PM GMT+08:00

   Haiku 4.5 is also returning errors.

5. resolved Jul 27, 2026, 10:36 PM GMT+08:00

   As of 7:34 PST / 14:34 UTC the errors have returned to baseline.

As of 4:47 PST / 11:47 UTC the errors have returned to baseline.

1. investigating Jul 27, 2026, 7:27 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 27, 2026, 8:30 PM GMT+08:00

   As of 4:47 PST / 11:47 UTC the errors have returned to baseline.

As of 2:03 PST / 9:03 UTC the errors have returned to baseline.

1. investigating Jul 27, 2026, 4:16 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 27, 2026, 5:05 PM GMT+08:00

   As of 2:03 PST / 9:03 UTC the errors have returned to baseline.

This incident has been resolved.

1. investigating Jul 26, 2026, 5:17 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 26, 2026, 5:45 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. identified Jul 26, 2026, 6:28 PM GMT+08:00

   We are continuing to work on a fix for this issue.

4. monitoring Jul 26, 2026, 6:34 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

5. resolved Jul 26, 2026, 6:44 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 26, 2026, 6:09 AM GMT+08:00

   We are investigating intermittent errors that may prevent some users from loading or continuing conversations in ChatGPT. The current period of impact began around 1:00 PM PT.

2. identified Jul 26, 2026, 7:16 AM GMT+08:00

   We have identified the source of intermittent errors affecting some ChatGPT conversations and are working to mitigate the issue. Error rates have decreased, but some users may continue to experience failures.

3. monitoring Jul 26, 2026, 7:57 AM GMT+08:00

   Mitigation has been implemented, and we are monitoring the recovery of ChatGPT conversations.

4. resolved Jul 28, 2026, 12:32 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 26, 2026, 5:34 AM GMT+08:00

   We are investigating elevated errors on requests to Claude Fable 5, Claude Sonnet 5, Claude Haiku 4.5, and other Claude models. We will provide an update as soon as possible.

2. resolved Jul 26, 2026, 6:08 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 26, 2026, 2:40 AM GMT+08:00

   We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Haiku 4.5. We will provide an update as soon as possible.

2. identified Jul 26, 2026, 2:44 AM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. resolved Jul 26, 2026, 3:44 AM GMT+08:00

   This incident has been resolved.

For approximately 10 minutes, error rates on Sonnet 4.6 and 5 were elevated. Service returned to normal at approximately 11:07a PDT.

1. resolved Jul 26, 2026, 2:13 AM GMT+08:00

   For approximately 10 minutes, error rates on Sonnet 4.6 and 5 were elevated. Service returned to normal at approximately 11:07a PDT.

All impacted services have now fully recovered.

1. identified Jul 25, 2026, 7:35 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jul 25, 2026, 7:46 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 25, 2026, 7:57 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 25, 2026, 5:17 PM GMT+08:00

   We are investigating the issue for the listed services.

2. monitoring Jul 25, 2026, 6:02 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 25, 2026, 7:08 PM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 24, 2026, 5:09 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jul 24, 2026, 5:35 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jul 24, 2026, 6:22 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 24, 2026, 3:55 PM GMT+08:00

   We are investigating the issue for the listed services.

2. monitoring Jul 24, 2026, 4:11 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 24, 2026, 5:35 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jul 24, 2026, 7:56 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. resolved Jul 24, 2026, 8:09 AM GMT+08:00

   All impacted services have now fully recovered.

We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

1. identified Jul 24, 2026, 3:16 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

All impacted services have now fully recovered.

1. identified Jul 24, 2026, 1:56 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jul 24, 2026, 2:22 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 24, 2026, 4:41 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 23, 2026, 11:36 PM GMT+08:00

   We are investigating the issue for the listed services.

2. identified Jul 23, 2026, 11:56 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

3. identified Jul 24, 2026, 12:08 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

4. identified Jul 24, 2026, 12:48 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation with the downstream infrastructure provider.

5. identified Jul 24, 2026, 1:36 AM GMT+08:00

   We are continuing to work on implementing a mitigation.

6. identified Jul 24, 2026, 1:58 AM GMT+08:00

   We are continuing to work on implementing a mitigation.

7. monitoring Jul 24, 2026, 2:50 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

8. investigating Jul 24, 2026, 3:37 AM GMT+08:00

   We are investigating the issue for the listed services.

9. monitoring Jul 24, 2026, 4:22 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

10. investigating Jul 24, 2026, 5:56 PM GMT+08:00

    We are investigating the issue for the listed services.

11. investigating Jul 24, 2026, 6:06 PM GMT+08:00

    We are investigating the issue for the listed services.

12. monitoring Jul 24, 2026, 7:34 PM GMT+08:00

    We have applied the mitigation and are monitoring the recovery.

13. resolved Jul 25, 2026, 3:33 AM GMT+08:00

    All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 23, 2026, 7:52 AM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 23, 2026, 8:10 AM GMT+08:00

   This incident has been resolved.

This issue has been resolved.

1. identified Jul 23, 2026, 1:56 AM GMT+08:00

   Users who installed the following add-ins may experience issues accessing the add-in functionality: Claude by Anthropic for PowerPoint, Claude by Anthropic for Word, and Claude by Anthropic for Excel. To regain immediate access to Claude for Microsoft 365, install the add-in here: https://marketplace.microsoft.com/en-us/product/office/wa200010725

2. resolved Jul 24, 2026, 11:36 PM GMT+08:00

   This issue has been resolved.

This incident has been resolved.

1. investigating Jul 23, 2026, 1:27 AM GMT+08:00

   We are investigating an outage affecting features such as document creation in claude.ai, Cowork Remote, Claude Code, Claude Code on the Web, Claude Tag, and Claude Design

2. identified Jul 23, 2026, 1:28 AM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. resolved Jul 23, 2026, 1:45 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 22, 2026, 11:24 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 22, 2026, 11:36 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. resolved Jul 23, 2026, 12:12 AM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 22, 2026, 10:48 PM GMT+08:00

   We are investigating the issue for the listed services.

2. identified Jul 22, 2026, 11:49 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

3. resolved Jul 23, 2026, 12:09 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 22, 2026, 9:37 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 22, 2026, 10:16 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. identified Jul 22, 2026, 10:18 PM GMT+08:00

   We are continuing to work on a fix for this issue. Haiku 4.5 has recovered

4. monitoring Jul 22, 2026, 11:06 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

5. resolved Jul 22, 2026, 11:23 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. identified Jul 22, 2026, 4:34 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

2. monitoring Jul 22, 2026, 4:45 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jul 22, 2026, 5:00 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 22, 2026, 3:32 PM GMT+08:00

   We are investigating the issue for the listed services.

2. investigating Jul 22, 2026, 3:54 PM GMT+08:00

   We are investigating the issue for the listed services.

3. identified Jul 22, 2026, 5:26 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

4. monitoring Jul 22, 2026, 5:44 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

5. resolved Jul 22, 2026, 10:39 PM GMT+08:00

   All impacted services have now fully recovered.

OpenAI has recovered.

1. investigating Jul 22, 2026, 4:01 AM GMT+08:00

   Status storage update failed.

2. resolved Jul 22, 2026, 10:51 AM GMT+08:00

   OpenAI has recovered.

Image generation functionality has fully recovered, and error rates have returned to normal levels.

1. investigating Jul 22, 2026, 3:33 AM GMT+08:00

   We are investigating elevated error rates affecting image generation requests via the API. We are working to restore normal service.

2. monitoring Jul 22, 2026, 4:26 AM GMT+08:00

   We have applied mitigations and are seeing error rates return to normal levels. We are monitoring the recovery.

3. resolved Jul 22, 2026, 6:19 AM GMT+08:00

   Image generation functionality has fully recovered, and error rates have returned to normal levels.

All affected API Platform functionality has now fully recovered.

1. investigating Jul 22, 2026, 2:36 AM GMT+08:00

   We are investigating issues affecting logins and account creation for ChatGPT and the API Platform. Users who are already signed in may still be able to use ChatGPT.

2. identified Jul 22, 2026, 2:41 AM GMT+08:00

   We are seeing recovery for API Platform login functionality. Account creation, organization management, and dashboard access remain affected. We are continuing to investigate.

3. monitoring Jul 22, 2026, 2:56 AM GMT+08:00

   The affected API Platform functionality has recovered, including login, account creation, organization management, and dashboard access. We are monitoring the recovery.

4. resolved Jul 22, 2026, 3:00 AM GMT+08:00

   All affected API Platform functionality has now fully recovered.

This incident has been resolved.

1. identified Jul 22, 2026, 1:40 AM GMT+08:00

   We are investigating an outage affecting features such as document creation in claude.ai, Cowork Remote, Claude Code, Claude Code on the Web, Claude Tag, and Claude Design

2. identified Jul 22, 2026, 1:41 AM GMT+08:00

   We are continuing to work on a fix for this issue.

3. identified Jul 22, 2026, 1:46 AM GMT+08:00

   We are continuing to work on a fix for this issue.

4. identified Jul 22, 2026, 1:47 AM GMT+08:00

   We are continuing to work on a fix for this issue.

5. monitoring Jul 22, 2026, 1:51 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

6. resolved Jul 22, 2026, 2:03 AM GMT+08:00

   This incident has been resolved.

From 8:28am PT / 15:28 UTC through 9:26am PT / 16:26 UTC users experienced elevated errors on requests to multiple Claude models. This issue has been resolved.

1. investigating Jul 21, 2026, 11:35 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 21, 2026, 11:51 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jul 22, 2026, 1:07 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jul 22, 2026, 2:18 AM GMT+08:00

   From 8:28am PT / 15:28 UTC through 9:26am PT / 16:26 UTC users experienced elevated errors on requests to multiple Claude models. This issue has been resolved.

This incident has been resolved.

1. investigating Jul 21, 2026, 9:04 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 21, 2026, 9:14 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jul 21, 2026, 9:22 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. identified Jul 21, 2026, 10:44 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

5. monitoring Jul 21, 2026, 11:30 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

6. resolved Jul 22, 2026, 12:38 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 21, 2026, 7:19 PM GMT+08:00

   We are currently investigating this issue.

2. investigating Jul 21, 2026, 7:24 PM GMT+08:00

   We are continuing to investigate this issue.

3. identified Jul 21, 2026, 7:28 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

4. monitoring Jul 21, 2026, 7:47 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

5. resolved Jul 21, 2026, 8:07 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. identified Jul 21, 2026, 6:36 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jul 21, 2026, 7:29 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. investigating Jul 21, 2026, 8:20 PM GMT+08:00

   We are investigating the issue for the listed services.

4. investigating Jul 21, 2026, 8:22 PM GMT+08:00

   We are investigating the issue for the listed services.

5. investigating Jul 21, 2026, 8:25 PM GMT+08:00

   We are investigating the issue for the listed services.

6. investigating Jul 21, 2026, 8:57 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

7. investigating Jul 21, 2026, 9:31 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

8. identified Jul 21, 2026, 9:38 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

9. identified Jul 21, 2026, 10:04 PM GMT+08:00

   We are still implementing the mitigation.

10. monitoring Jul 21, 2026, 10:37 PM GMT+08:00

    We have applied the mitigation and are monitoring the recovery.

11. monitoring Jul 21, 2026, 11:15 PM GMT+08:00

    We have applied the mitigation and are monitoring the recovery.

12. resolved Jul 22, 2026, 10:50 AM GMT+08:00

    All impacted services have now fully recovered.

13. investigating Jul 27, 2026, 10:04 PM GMT+08:00

    We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

14. investigating Jul 28, 2026, 12:52 AM GMT+08:00

    We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

15. resolved Jul 28, 2026, 3:04 AM GMT+08:00

    All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 21, 2026, 6:11 PM GMT+08:00

   We are currently investigating issues with Claude Haiku 4.5 and Opus 4.8.

2. monitoring Jul 21, 2026, 7:10 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jul 21, 2026, 7:18 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. identified Jul 21, 2026, 3:11 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

2. identified Jul 21, 2026, 4:19 PM GMT+08:00

   We are continuing to work on a fix for this issue.

3. resolved Jul 21, 2026, 4:53 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 20, 2026, 10:41 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 20, 2026, 11:09 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jul 21, 2026, 12:07 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jul 21, 2026, 12:16 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 20, 2026, 9:20 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 20, 2026, 11:09 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jul 20, 2026, 11:33 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jul 20, 2026, 11:41 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. monitoring Jul 20, 2026, 3:35 PM GMT+08:00

   Some Claude Code Max plan users were incorrectly prompted to use usage credits to access Fable 5, which is included in their plan. If you were affected, please restart Claude Code.

2. resolved Jul 20, 2026, 11:35 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 20, 2026, 3:03 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 20, 2026, 3:57 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. identified Jul 20, 2026, 6:05 PM GMT+08:00

   We are continuing to work on a fix for this issue.

4. monitoring Jul 20, 2026, 6:57 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

5. resolved Jul 20, 2026, 8:48 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 20, 2026, 8:34 AM GMT+08:00

   Users may experience failures or delays in ChatGPT and Codex workflows that depend on GitHub. This is related to an active GitHub API partial outage and degraded GitHub Actions.

2. investigating Jul 20, 2026, 8:39 AM GMT+08:00

   Users may experience failures or delays in ChatGPT and Codex workflows that depend on GitHub. This mostly should impact Codex web and code review for PRs on Github. This is related to an active GitHub API partial outage and degraded GitHub Actions. [https://www.githubstatus.com/incidents/8vfyvq16hzh9](https://www.githubstatus.com/incidents/8vfyvq16hzh9 "https://www.githubstatus.com/incidents/8vfyvq16hzh9")

3. investigating Jul 20, 2026, 9:49 AM GMT+08:00

   Users may experience failures or delays in ChatGPT and Codex workflows that depend on GitHub. This mostly should impact Codex web and code review for PRs on Github. This is related to an active GitHub API partial outage and degraded GitHub Actions. [https://www.githubstatus.com/incidents/8vfyvq16hzh9](https://www.githubstatus.com/incidents/8vfyvq16hzh9 "https://www.githubstatus.com/incidents/8vfyvq16hzh9")

4. investigating Jul 20, 2026, 10:52 AM GMT+08:00

   Users may experience failures or delays in ChatGPT and Codex workflows that depend on GitHub. This mostly should impact Codex web and code review for PRs on Github. This is related to an active GitHub API partial outage and degraded GitHub Actions. [https://www.githubstatus.com/incidents/8vfyvq16hzh9](https://www.githubstatus.com/incidents/8vfyvq16hzh9 "https://www.githubstatus.com/incidents/8vfyvq16hzh9")

5. monitoring Jul 20, 2026, 11:25 AM GMT+08:00

   We are monitoring the recovery.

6. resolved Jul 20, 2026, 11:34 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 19, 2026, 10:49 PM GMT+08:00

   Some users are experiencing elevated errors when loading or continuing conversations in ChatGPT. We are investigating.

2. identified Jul 19, 2026, 11:01 PM GMT+08:00

   We have identified the cause of elevated errors affecting ChatGPT conversations, Voice, and Work Mode. We are applying mitigations and monitoring recovery.

3. monitoring Jul 19, 2026, 11:04 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

4. monitoring Jul 20, 2026, 12:55 AM GMT+08:00

   Service has been restored and we are continuing to monitor.

5. resolved Jul 20, 2026, 1:05 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jul 18, 2026, 4:05 PM GMT+08:00

   We have identified an issue causing some users to receive access-denied errors when using the Codex desktop app and CLI.

2. monitoring Jul 18, 2026, 4:31 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 18, 2026, 8:58 PM GMT+08:00

   All impacted services have now fully recovered.

This issue has been resolved, and Claude Fable 5 is available once again without usage credits, as expected.

1. investigating Jul 18, 2026, 2:32 AM GMT+08:00

   We are currently investigating this issue.

2. investigating Jul 18, 2026, 2:36 AM GMT+08:00

   We are aware of an issue preventing users from selecting Claude Fable 5 within Claude.ai, Claude Code, and other surfaces, and are working to resolve this issue.

3. monitoring Jul 18, 2026, 2:48 AM GMT+08:00

   We have applied a fix to resolve the erroneous requirement for usage credits on Fable 5, and are monitoring to ensure no further issues. You may need to relaunch Claude.ai or Claude Code to restore access as expected.

4. resolved Jul 18, 2026, 3:43 AM GMT+08:00

   This issue has been resolved, and Claude Fable 5 is available once again without usage credits, as expected.

This incident has been resolved.

1. investigating Jul 18, 2026, 2:12 AM GMT+08:00

   We are currently investigating this issue.

2. investigating Jul 18, 2026, 2:13 AM GMT+08:00

   We are continuing to investigate this issue.

3. monitoring Jul 18, 2026, 2:22 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jul 18, 2026, 2:27 AM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. identified Jul 18, 2026, 1:19 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jul 18, 2026, 3:07 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 18, 2026, 4:42 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jul 17, 2026, 11:32 PM GMT+08:00

   Enterprise users who do not have Codex RBAC enabled may see a "codex_cli_workspace_disabled" error when trying to log into the new ChatGPT app post-install. Please use our ChatGPT Classic while we work to implement a fix.

2. resolved Jul 18, 2026, 1:45 PM GMT+08:00

   A fix has been released. Please update to the latest version of the ChatGPT app to receive the fix.

3. identified Jul 18, 2026, 3:43 PM GMT+08:00

   We have identified that this issue has recurred for some Enterprise users. We are working to resolve this.

4. resolved Jul 18, 2026, 4:24 PM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. identified Jul 17, 2026, 10:57 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

2. monitoring Jul 17, 2026, 11:27 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jul 17, 2026, 11:33 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 17, 2026, 2:47 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jul 17, 2026, 3:03 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. identified Jul 17, 2026, 3:10 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

4. resolved Jul 17, 2026, 8:21 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. identified Jul 17, 2026, 6:54 AM GMT+08:00

   We have identified that users are experiencing elevated errors when using the Github connector. We are working on implementing a mitigation.

2. identified Jul 17, 2026, 7:12 AM GMT+08:00

   We have identified that users are experiencing elevated errors when using the Github connector. Github is experiencing system-wide service-availability issues. We are monitoring their recovery: <https://www.githubstatus.com/>

3. resolved Jul 17, 2026, 8:17 AM GMT+08:00

   All impacted services have now fully recovered.

This issue has been resolved. From 11:30am PT / 18:30 UTC through to 3:15pm PT / 22:15 UTC some users experienced elevated errors on requests to Claude Models. Most errors were experienced within the first hour of the impact window.

1. investigating Jul 17, 2026, 2:36 AM GMT+08:00

   We are investigating elevated errors on requests to multiple models. We will provide an update as soon as possible.

2. identified Jul 17, 2026, 3:14 AM GMT+08:00

   We have identified the cause of elevated errors on requests to multiple models, and are working to resolve this issue. We will provide an update as soon as possible.

3. identified Jul 17, 2026, 4:07 AM GMT+08:00

   We are continuing to work to resolve issues resulting in elevated errors on requests to some Anthropic models. We will provide additional updates as soon as possible.

4. identified Jul 17, 2026, 4:58 AM GMT+08:00

   At this time, we are seeing recovery on requests to most models. We are continuing to see elevated errors on requests to Claude Fable 5 and Mythos 5, and are working to resolve these remaining issues. We will provide an additional update as soon as possible.

5. monitoring Jul 17, 2026, 6:01 AM GMT+08:00

   We have seen success rates recover and are continuing to monitor closely to ensure no further issues. We will provide an additional update shortly.

6. resolved Jul 17, 2026, 6:53 AM GMT+08:00

   This issue has been resolved. From 11:30am PT / 18:30 UTC through to 3:15pm PT / 22:15 UTC some users experienced elevated errors on requests to Claude Models. Most errors were experienced within the first hour of the impact window.

This incident has been resolved.

1. identified Jul 16, 2026, 5:23 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

2. resolved Jul 16, 2026, 6:27 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 16, 2026, 4:58 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 16, 2026, 9:30 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 16, 2026, 4:39 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 16, 2026, 4:53 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. identified Jul 16, 2026, 4:36 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. investigating Jul 16, 2026, 5:59 PM GMT+08:00

   We are investigating the issue for the listed services and seeing gradual recovery.

3. monitoring Jul 16, 2026, 6:57 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

4. resolved Jul 16, 2026, 11:23 PM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 15, 2026, 10:04 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 15, 2026, 10:49 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jul 15, 2026, 11:02 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jul 15, 2026, 11:11 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 15, 2026, 8:36 AM GMT+08:00

   We are investigating the issue for the listed services.

2. resolved Jul 15, 2026, 8:38 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 15, 2026, 7:39 AM GMT+08:00

   We are investigating login issues and intermittent errors affecting ChatGPT.

2. monitoring Jul 15, 2026, 8:25 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 15, 2026, 8:39 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 15, 2026, 5:31 AM GMT+08:00

   We are investigating an outage affecting features such as document creation in claude.ai, Cowork Remote, Claude Code, Claude Code Remote, and Claude Design

2. investigating Jul 15, 2026, 5:56 AM GMT+08:00

   We are continuing to investigate this issue.

3. monitoring Jul 15, 2026, 5:58 AM GMT+08:00

   A fix has been implemented and we are monitoring the results

4. resolved Jul 15, 2026, 6:16 AM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. identified Jul 14, 2026, 11:07 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jul 14, 2026, 11:25 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 15, 2026, 12:02 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 13, 2026, 10:44 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jul 13, 2026, 11:04 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jul 13, 2026, 11:24 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 13, 2026, 7:39 PM GMT+08:00

   We are investigating the issue for the listed services.

2. monitoring Jul 13, 2026, 8:21 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jul 13, 2026, 8:59 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 13, 2026, 5:11 PM GMT+08:00

   We are investigating the issue for the listed services.

2. investigating Jul 13, 2026, 6:13 PM GMT+08:00

   We are continuing to investigate elevated errors affecting file uploads, deletions, and navigation in the ChatGPT Library.

3. monitoring Jul 13, 2026, 7:11 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

4. investigating Jul 13, 2026, 7:48 PM GMT+08:00

   We are investigating the issue for the listed services.

5. monitoring Jul 13, 2026, 9:11 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

6. resolved Jul 13, 2026, 10:35 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 12, 2026, 5:49 PM GMT+08:00

   We are investigating an issue where some users may encounter 403 errors when loading or using ChatGPT conversations on iOS. We will provide updates as we learn more.

2. investigating Jul 12, 2026, 7:02 PM GMT+08:00

   We are continuing to investigate elevated errors affecting some users on iOS. Some users may be unable to load or use conversations.

3. investigating Jul 12, 2026, 7:29 PM GMT+08:00

   We are continuing to investigate elevated errors affecting conversations, sign-ups, and sign-ins for some users on iOS and macOS.

4. identified Jul 12, 2026, 8:02 PM GMT+08:00

   We have identified the issue causing elevated conversation, sign-up, and sign-in errors for some users on iOS and macOS. We are working to implement a mitigation.

5. identified Jul 12, 2026, 8:34 PM GMT+08:00

   We have implemented a mitigation that restored conversation access for affected users on iOS and macOS. We are continuing to work on mitigating sign-up and sign-in errors.

6. identified Jul 12, 2026, 9:09 PM GMT+08:00

   We have restored sign-in access for affected users. We are continuing to work on mitigating account creation and password update errors on iOS and macOS.

7. monitoring Jul 12, 2026, 11:15 PM GMT+08:00

   A mitigation has been applied, and the affected services have recovered. We are monitoring the results.

8. resolved Jul 12, 2026, 11:28 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 11, 2026, 2:35 PM GMT+08:00

   We are investigating the issue for the listed services.

2. resolved Jul 11, 2026, 3:03 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jul 11, 2026, 5:13 AM GMT+08:00

   Some OpenAI website content pages, including Help Center articles, are currently unavailable. Help Center search functionality is also unavailable, and the chatbot experience may be degraded. We are investigating the issue.

2. identified Jul 11, 2026, 6:38 AM GMT+08:00

   Some OpenAI website content pages, including Help Center articles, are currently unavailable. Help Center search functionality is also unavailable, and the chatbot experience may be degraded. We are investigating the issue.

3. resolved Jul 11, 2026, 7:07 AM GMT+08:00

   All impacted services have now fully recovered.

Elevated errors for Claude Opus 4.5 and Claude Sonnet 4.5 between 6:00am PT / 1:00pm UTC and 8:15am PT / 3:15pm UTC.

1. resolved Jul 10, 2026, 9:00 PM GMT+08:00

   Elevated errors for Claude Opus 4.5 and Claude Sonnet 4.5 between 6:00am PT / 1:00pm UTC and 8:15am PT / 3:15pm UTC.

This incident has been resolved.

1. investigating Jul 10, 2026, 10:36 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 10, 2026, 11:02 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 10, 2026, 3:44 AM GMT+08:00

   We are investigating an issue causing users to receive “Selected model is at capacity. Please try a different model.” errors across multiple models. We are working to identify the cause and restore normal service.

2. resolved Jul 10, 2026, 4:42 AM GMT+08:00

   All impacted services have now fully recovered.

This issue has been resolved

1. investigating Jul 9, 2026, 11:28 AM GMT+08:00

   We are investigating elevated errors on requests to Claude Opus 4.8. We will provide an update as soon as possible.

2. resolved Jul 9, 2026, 11:50 AM GMT+08:00

   This issue has been resolved

This issue has been resolved.

1. investigating Jul 9, 2026, 3:07 AM GMT+08:00

   We are currently investigating a performance issue affecting features such as Claude Code on the Web (claude.ai/code), Claude Code Review, Cowork Remote, Claude Tag, and document creation in claude.ai. Our team is working on mitigating this issue.

2. monitoring Jul 9, 2026, 3:41 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jul 9, 2026, 5:04 AM GMT+08:00

   This issue has been resolved.

This issue has been resolved. Users saw elevated errors on requests to some models between 10:45am PT / 17:45 UTC and 12:40pm PT / 19:40 UTC.

1. investigating Jul 9, 2026, 2:00 AM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 9, 2026, 2:28 AM GMT+08:00

   We have identified an issue causing elevated errors on requests to some models, and our team is working to resolve this issue as quickly as possible. We will provide an additional update shortly.

3. monitoring Jul 9, 2026, 3:05 AM GMT+08:00

   At this time, success rates have recovered across impacted models and we are monitoring closely to ensure no further issues occur.

4. identified Jul 9, 2026, 3:29 AM GMT+08:00

   We are continuing to work to fully resolve errors impacting some requests, and will provide an additional update as soon as possible.

5. resolved Jul 9, 2026, 5:04 AM GMT+08:00

   This issue has been resolved. Users saw elevated errors on requests to some models between 10:45am PT / 17:45 UTC and 12:40pm PT / 19:40 UTC.

Users are unable to send authorized requests to MCP servers.

1. resolved Jul 9, 2026, 3:00 AM GMT+08:00

   Users are unable to send authorized requests to MCP servers.

This incident has been resolved.

1. investigating Jul 8, 2026, 2:26 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 8, 2026, 2:40 PM GMT+08:00

   This incident has been resolved.

This issue has been resolved.

1. investigating Jul 8, 2026, 4:02 AM GMT+08:00

   We are investigating elevated errors on requests to some models. We will provide an update as soon as possible.

2. identified Jul 8, 2026, 4:28 AM GMT+08:00

   We have seen success rates return to normal, but we are continuing to work to fully resolve this issue and ensure no further recurrences.

3. identified Jul 8, 2026, 5:47 AM GMT+08:00

   We are continuing to work to resolve an issue resulting in elevated errors on requests to some models, primarily Claude Fable 5. We will provide an additional update as soon as possible.

4. monitoring Jul 8, 2026, 7:19 AM GMT+08:00

   We are continuing to monitor issues affecting requests to some models, and have once again seen success rates return to normal. We are working to ensure there are no further issues, and will provide an additional update shortly.

5. resolved Jul 8, 2026, 7:46 AM GMT+08:00

   This issue has been resolved.

All impacted services have now fully recovered.

1. investigating Jul 7, 2026, 7:29 PM GMT+08:00

   We are investigating elevated errors affecting image generation in ChatGPT. Some users may be unable to generate images.

2. identified Jul 7, 2026, 8:17 PM GMT+08:00

   We have identified the issue and are implementing a mitigation. Some users may continue to experience errors with image generation in ChatGPT while we implement the mitigation.

3. monitoring Jul 7, 2026, 10:40 PM GMT+08:00

   We have implemented a mitigation and are seeing error rates return to normal levels. We are monitoring the recovery, and some users may continue to experience errors with image generation in ChatGPT.

4. resolved Jul 8, 2026, 12:12 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jul 7, 2026, 2:58 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jul 7, 2026, 3:37 PM GMT+08:00

   This incident has been resolved.

Our team is observing a lower error rate after these changes. We will continue investigating in-case we observe any spikes.

1. investigating Jul 7, 2026, 5:49 AM GMT+08:00

   We are currently investigating elevated error rates on calls made Claude Tag. Our team is actively working to identify the root cause. You may experience errors such as GitHub operations denied.

2. investigating Jul 7, 2026, 11:30 PM GMT+08:00

   Our team has made some changes to update the load to GitHub, that we think will reduce this error rate.

3. resolved Jul 7, 2026, 11:52 PM GMT+08:00

   Our team is observing a lower error rate after these changes. We will continue investigating in-case we observe any spikes.

This issue has been resolved.

1. investigating Jul 7, 2026, 3:18 AM GMT+08:00

   We are investigating elevated errors on Claude.ai, and will provide an update as soon as possible.

2. investigating Jul 7, 2026, 3:28 AM GMT+08:00

   We have identified and are working to resolve an issue impacting Claude.ai. An additional impact of the ongoing issue is the inability to log-in via Claude.ai OAuth for Claude Code. We will provide an additional update as soon as possible.

3. monitoring Jul 7, 2026, 3:46 AM GMT+08:00

   We have applied a fix, and at this time are seeing recovery of Claude.ai and related services such as OAuth log-in for Claude Code.

4. resolved Jul 7, 2026, 4:05 AM GMT+08:00

   This issue has been resolved.

This incident has been resolved.

1. investigating Jul 6, 2026, 3:36 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 6, 2026, 4:45 PM GMT+08:00

   Fable 5 has now also started returning errors.

3. resolved Jul 6, 2026, 5:13 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 4, 2026, 7:42 AM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jul 4, 2026, 8:19 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jul 4, 2026, 8:20 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 4, 2026, 5:54 AM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 4, 2026, 5:55 AM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jul 4, 2026, 6:00 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jul 4, 2026, 6:06 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jul 2, 2026, 8:38 AM GMT+08:00

   We are currently investigating this issue.

2. identified Jul 2, 2026, 8:58 AM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. resolved Jul 2, 2026, 9:19 AM GMT+08:00

   This incident has been resolved.

Core functionality in FedRAMP workspaces has been restored, and the broader incident is resolved.

1. investigating Jun 29, 2026, 3:00 PM GMT+08:00

   Core functionality has been restored but we are aware of known and ongoing issues in FedRAMP workspaces with Codex, workspace analytics, conversation search, searching for custom GPTs, ChatGPT user invites, and the Compliance Logs Platform download endpoint. We are working to resolve these issues and will share further updates we have more information available.

2. resolved Jul 11, 2026, 10:11 AM GMT+08:00

   Core functionality in FedRAMP workspaces has been restored, and the broader incident is resolved.

This incident has been resolved.

1. investigating Jun 30, 2026, 10:31 PM GMT+08:00

   We are currently investigating elevated error rates on Opus 4.8. Our team is actively working to identify the root cause.

2. monitoring Jun 30, 2026, 10:45 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 30, 2026, 11:28 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 29, 2026, 9:35 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jun 29, 2026, 9:52 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jun 29, 2026, 10:13 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jun 29, 2026, 10:27 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jun 28, 2026, 6:00 AM GMT+08:00

   We are investigating an issue affecting some users of the ChatGPT Windows desktop app on Windows. Affected users may see chat history or conversations fail to load, missing sidebar icons, or login/sign-up controls that do not respond. ChatGPT on web and mobile remains available as a workaround. We will share updates as we learn more.

2. resolved Jun 28, 2026, 11:29 AM GMT+08:00

   All impacted services have now fully recovered.

Elevated errors on Opus-48. It has been mitigated. We are actively monitoring the system.

1. resolved Jun 28, 2026, 2:00 AM GMT+08:00

   Elevated errors on Opus-48. It has been mitigated. We are actively monitoring the system.

All impacted services have now fully recovered.

1. investigating Jun 27, 2026, 1:04 AM GMT+08:00

   We are investigating reports that Codex usage limits are being consumed faster than expected.

2. monitoring Jun 27, 2026, 7:24 AM GMT+08:00

   We have identified that some reports of Codex usage limits depleting faster than expected are related to our abuse and fraud prevention systems incorrectly rate limiting certain accounts. The impact appears limited, and we have not observed broader degradation to Codex usage. We are continuing to monitor the situation.

3. resolved Jun 30, 2026, 1:06 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jun 26, 2026, 12:02 AM GMT+08:00

   A small number of Users have incorrectly cancelled subscription.

2. resolved Jun 26, 2026, 10:18 AM GMT+08:00

   All impacted services have now fully recovered.

This is now resolved

1. investigating Jun 25, 2026, 1:51 PM GMT+08:00

   We are investigating the issue for the listed services.

2. monitoring Jun 25, 2026, 4:02 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jun 25, 2026, 7:03 PM GMT+08:00

   This is now resolved.

4. resolved Jun 25, 2026, 7:03 PM GMT+08:00

   This is now resolved

This incident has been resolved.

1. investigating Jun 25, 2026, 2:22 AM GMT+08:00

   We are currently investigating this issue.

2. resolved Jun 25, 2026, 2:33 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 24, 2026, 9:16 PM GMT+08:00

   We are currently investigating this issue.

2. resolved Jun 24, 2026, 10:56 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. monitoring Jun 24, 2026, 1:59 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

2. resolved Jun 24, 2026, 2:07 PM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jun 24, 2026, 2:24 AM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 24, 2026, 2:32 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 24, 2026, 2:32 AM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jun 23, 2026, 10:24 PM GMT+08:00

   We are investigating the issue for the listed services.

2. investigating Jun 23, 2026, 11:11 PM GMT+08:00

   We are investigating the issue for the listed services.

3. monitoring Jun 23, 2026, 11:47 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

4. resolved Jun 24, 2026, 12:38 AM GMT+08:00

   All impacted services have now fully recovered.

Anthropic has recovered.

1. investigating Jun 23, 2026, 10:21 PM GMT+08:00

   Partial System Outage

2. resolved Jun 23, 2026, 11:29 PM GMT+08:00

   Anthropic has recovered.

This incident has been resolved.

1. investigating Jun 23, 2026, 10:19 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jun 23, 2026, 10:25 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jun 23, 2026, 10:53 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. monitoring Jun 23, 2026, 11:28 PM GMT+08:00

   We are continuing to monitor for any further issues.

5. monitoring Jun 24, 2026, 12:05 AM GMT+08:00

   We have seen error rates broadly return to normal success levels across all models. We saw elevated error rates on requests to multiple models from 7:08am PT / 14:08 UTC through 8:33am PT / 15:33 UTC.

6. resolved Jun 24, 2026, 12:44 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 23, 2026, 2:28 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 23, 2026, 3:47 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 23, 2026, 4:45 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 23, 2026, 3:14 AM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 23, 2026, 3:20 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 23, 2026, 3:45 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 22, 2026, 4:11 PM GMT+08:00

   We are currently investigating this issue.

2. investigating Jun 22, 2026, 4:12 PM GMT+08:00

   We are continuing to investigate this issue.

3. monitoring Jun 22, 2026, 5:59 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jun 22, 2026, 10:44 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 22, 2026, 8:37 AM GMT+08:00

   We are currently investigating this issue.

2. investigating Jun 22, 2026, 8:37 AM GMT+08:00

   We are continuing to investigate this issue.

3. identified Jun 22, 2026, 9:11 AM GMT+08:00

   The issue has been identified and a fix is being implemented.

4. identified Jun 22, 2026, 9:16 AM GMT+08:00

   Opus 4.8 has recovered.

5. identified Jun 22, 2026, 9:33 AM GMT+08:00

   Haiku 4.5 has recovered

6. identified Jun 22, 2026, 9:56 AM GMT+08:00

   Opus 4.7 has recovered

7. monitoring Jun 22, 2026, 10:01 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

8. resolved Jun 22, 2026, 10:06 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 21, 2026, 1:07 AM GMT+08:00

   We are currently investigating this issue.

2. investigating Jun 21, 2026, 1:23 AM GMT+08:00

   We are continuing to investigate this issue.

3. monitoring Jun 21, 2026, 1:49 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jun 21, 2026, 2:02 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 19, 2026, 4:17 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 19, 2026, 4:37 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 19, 2026, 4:45 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 19, 2026, 2:07 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 19, 2026, 3:03 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 19, 2026, 3:17 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. investigating Jun 19, 2026, 11:39 AM GMT+08:00

   We have identified an issue causing some users to be unable to access ChatGPT on [chatgpt.com](http://chatgpt.com "chatgpt.com"). We are working on implementing a mitigation. In the meantime, please try clearing the cache.

2. monitoring Jun 19, 2026, 1:11 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jun 19, 2026, 1:23 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jun 18, 2026, 4:55 PM GMT+08:00

   We are investigating the issue for the listed services.

2. monitoring Jun 18, 2026, 5:59 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jun 18, 2026, 7:55 PM GMT+08:00

   All impacted services have now fully recovered.

The issue affecting Claude services has been resolved. Impact occurred from 06:55 to 07:40 UTC.

1. identified Jun 18, 2026, 3:41 PM GMT+08:00

   We have identified the cause of the issue affecting Claude.ai and are working on a fix. We will provide an update as soon as possible.

2. resolved Jun 18, 2026, 4:19 PM GMT+08:00

   The issue affecting Claude services has been resolved. Impact occurred from 06:55 to 07:40 UTC.

All impacted services have now fully recovered.

1. investigating Jun 18, 2026, 11:26 AM GMT+08:00

   We are investigating the issue for the listed services.

2. monitoring Jun 18, 2026, 11:43 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jun 18, 2026, 11:55 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jun 18, 2026, 1:20 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jun 18, 2026, 1:44 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jun 18, 2026, 2:23 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jun 17, 2026, 11:34 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 18, 2026, 12:01 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 18, 2026, 12:28 AM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 17, 2026, 4:24 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jun 17, 2026, 4:54 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jun 17, 2026, 5:37 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jun 17, 2026, 6:03 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved. Requests to Claude Opus 4.8 received elevated errors between 9:59pm PT / 04:59 UTC and 10:41pm PT / 05:41 UTC.

1. investigating Jun 17, 2026, 1:08 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 17, 2026, 1:44 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 17, 2026, 2:37 PM GMT+08:00

   This incident has been resolved. Requests to Claude Opus 4.8 received elevated errors between 9:59pm PT / 04:59 UTC and 10:41pm PT / 05:41 UTC.

This incident has been resolved.

1. investigating Jun 17, 2026, 8:47 AM GMT+08:00

   We are currently investigating this issue.

2. identified Jun 17, 2026, 9:52 AM GMT+08:00

   At this time, success rates for Claude Sonnet 4.6 have recovered and we are working to resolve an issue resulting in elevated errors on Opus 4.8. We will provide additional updates as soon as possible.

3. resolved Jun 17, 2026, 10:50 AM GMT+08:00

   This incident has been resolved.

This issue has been resolved. We saw elevated errors on requests to Claude Opus 4.8 between 1:45pm PT / 20:45 UTC and 1:58pm PT / 20:58 UTC.

1. investigating Jun 17, 2026, 4:50 AM GMT+08:00

   We are investigating elevated errors on requests to Claude Opus 4.8. We will provide an update as soon as possible.

2. monitoring Jun 17, 2026, 5:01 AM GMT+08:00

   We have resolved the issue resulting in elevated errors on requests to Claude Opus 4.8, and are currently monitoring closely to prevent any further issues.

3. resolved Jun 17, 2026, 6:02 AM GMT+08:00

   This issue has been resolved. We saw elevated errors on requests to Claude Opus 4.8 between 1:45pm PT / 20:45 UTC and 1:58pm PT / 20:58 UTC.

This incident has been resolved.

1. monitoring Jun 17, 2026, 3:59 AM GMT+08:00

   Opus 4.8 error rates were elevated from 12:41 PDT to approximately 12:53 PDT. The team is monitoring.

2. resolved Jun 17, 2026, 4:16 AM GMT+08:00

   This incident has been resolved.

The incident has now been resolved. We had two phases: * between 10:23 PT / 17:23 UTC to 11:00 PT / 18:00 UTC -- all Sonnet and Opus models were affected, reaching an error rate of around 10% * after 11:00 PT / 18:00 UTC and until 12:20 PT / 19:20 UTC -- Opus 4.8 had an average error rate of 10% The incident is now resolved.

1. investigating Jun 17, 2026, 1:29 AM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 17, 2026, 2:00 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. identified Jun 17, 2026, 2:15 AM GMT+08:00

   We are still seeing errors on Opus 4.8 and Haiku 4.5.

4. identified Jun 17, 2026, 3:00 AM GMT+08:00

   We are continuing to work to resolve an elevated rate of errors on requests to Claude Opus 4.8, and will provide an additional update as soon as possible.

5. identified Jun 17, 2026, 3:08 AM GMT+08:00

   We are continuing to work on a fix for this issue.

6. monitoring Jun 17, 2026, 3:22 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

7. resolved Jun 17, 2026, 3:32 AM GMT+08:00

   The incident has now been resolved. We had two phases: * between 10:23 PT / 17:23 UTC to 11:00 PT / 18:00 UTC -- all Sonnet and Opus models were affected, reaching an error rate of around 10% * after 11:00 PT / 18:00 UTC and until 12:20 PT / 19:20 UTC -- Opus 4.8 had an average error rate of 10% The incident is now resolved.

All impacted services have now fully recovered.

1. identified Jun 16, 2026, 6:32 PM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. monitoring Jun 16, 2026, 9:32 PM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jun 16, 2026, 9:48 PM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. investigating Jun 16, 2026, 8:07 AM GMT+08:00

   We are investigating the issue for the listed services.

2. resolved Jun 16, 2026, 8:55 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jun 16, 2026, 5:23 AM GMT+08:00

   We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

2. investigating Jun 16, 2026, 6:16 AM GMT+08:00

   We are investigating the issue for the listed services.

3. investigating Jun 17, 2026, 9:24 AM GMT+08:00

   We are still investigating the issue for the listed services.

4. investigating Jun 19, 2026, 3:41 AM GMT+08:00

   We are still investigating the issue for the listed services.

5. resolved Jun 27, 2026, 7:07 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jun 16, 2026, 2:05 AM GMT+08:00

   We have identified that users are experiencing an error when attempting to create an account or logging in using Google OAuth for the impacted services. We are working on implementing a mitigation.

2. resolved Jun 16, 2026, 4:12 AM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jun 15, 2026, 2:20 PM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 15, 2026, 4:14 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 15, 2026, 4:56 PM GMT+08:00

   This incident has been resolved.

This incident has been resolved.

1. investigating Jun 13, 2026, 10:03 AM GMT+08:00

   We are currently investigating this issue.

2. resolved Jun 13, 2026, 10:11 AM GMT+08:00

   This incident has been resolved.

Learn more here: https://anthropic.com/news/redeploying-fable-5

1. monitoring Jun 13, 2026, 8:50 AM GMT+08:00

   Learn more here: https://anthropic.com/news/fable-mythos-access

2. resolved Jul 2, 2026, 3:26 AM GMT+08:00

   Learn more here: https://anthropic.com/news/redeploying-fable-5

All impacted services have now fully recovered.

1. identified Jun 12, 2026, 6:22 AM GMT+08:00

   We have identified that some users are experiencing elevated 431 errors for the impacted services. We are working on implementing a mitigation.

2. investigating Jun 12, 2026, 6:59 AM GMT+08:00

   We are continuing to investigate the issue regarding elevated 431 errors and are working on the mitigation.

3. monitoring Jun 12, 2026, 7:25 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

4. resolved Jun 12, 2026, 8:47 AM GMT+08:00

   All impacted services have now fully recovered.

All impacted services have now fully recovered.

1. identified Jun 12, 2026, 4:59 AM GMT+08:00

   We have identified that users are experiencing elevated errors when using GPT 5.5 in Codex. We are working on implementing a mitigation.

2. monitoring Jun 12, 2026, 5:33 AM GMT+08:00

   We have applied the mitigation and are monitoring the recovery.

3. resolved Jun 12, 2026, 6:28 AM GMT+08:00

   All impacted services have now fully recovered.

The issue affecting various models has been resolved. Impact occurred from 09:42am PT / 16:42 UTC to 10:03am PT / 17:03 UTC.

1. investigating Jun 12, 2026, 12:54 AM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 12, 2026, 1:27 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 12, 2026, 1:56 AM GMT+08:00

   The issue affecting various models has been resolved. Impact occurred from 09:42am PT / 16:42 UTC to 10:03am PT / 17:03 UTC.

This incident has been resolved.

1. investigating Jun 11, 2026, 10:37 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jun 11, 2026, 10:37 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jun 11, 2026, 10:58 PM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jun 11, 2026, 11:01 PM GMT+08:00

   This incident has been resolved.

All impacted services have now fully recovered.

1. identified Jun 11, 2026, 9:03 PM GMT+08:00

   We have identified that some ChatGPT Free and Go users are experiencing elevated errors when using conversations. We are working to implement a mitigation.

2. resolved Jun 11, 2026, 10:04 PM GMT+08:00

   All impacted services have now fully recovered.

This incident has been resolved.

1. investigating Jun 10, 2026, 9:06 PM GMT+08:00

   We are currently investigating this issue.

2. identified Jun 10, 2026, 9:19 PM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. identified Jun 10, 2026, 10:59 PM GMT+08:00

   We are continuing to work on a fix for this issue.

4. monitoring Jun 11, 2026, 12:20 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

5. monitoring Jun 11, 2026, 1:13 AM GMT+08:00

   We are continuing to monitor Claude Haiku 4.5 towards full recovery, and at this point have seen success rates recover to close to normal operating levels. We are working to ensure there are no further issues.

6. resolved Jun 11, 2026, 1:21 AM GMT+08:00

   This incident has been resolved.

From 1:20pm PT / 20:20 UTC through 2:05pm PT / 21:05 PT, we saw elevated errors on requests to Claude Opus 4.6. This issue has been resolved.

1. investigating Jun 10, 2026, 4:32 AM GMT+08:00

   We are currently investigating this issue.

2. resolved Jun 10, 2026, 6:10 AM GMT+08:00

   From 1:20pm PT / 20:20 UTC through 2:05pm PT / 21:05 PT, we saw elevated errors on requests to Claude Opus 4.6. This issue has been resolved.

This issue has been resolved. If you are experiencing issues with selecting Claude Fable within the Claude Code Desktop application, please ensure you have updated to the latest version.

1. investigating Jun 10, 2026, 2:24 AM GMT+08:00

   We are currently investigating this issue.

2. identified Jun 10, 2026, 2:35 AM GMT+08:00

   The issue has been identified and a fix is being implemented.

3. monitoring Jun 10, 2026, 4:16 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

4. resolved Jun 10, 2026, 5:03 AM GMT+08:00

   This issue has been resolved. If you are experiencing issues with selecting Claude Fable within the Claude Code Desktop application, please ensure you have updated to the latest version.

This issue has been resolved. Claude Opus 4.8 (Fast Mode) saw elevated errors from 7:50 PM PT / 02:50 UTC to 8:30 PM PT / 03:30 UTC.

1. investigating Jun 9, 2026, 11:13 AM GMT+08:00

   We are currently investigating this issue.

2. resolved Jun 9, 2026, 11:42 AM GMT+08:00

   This issue has been resolved. Claude Opus 4.8 (Fast Mode) saw elevated errors from 7:50 PM PT / 02:50 UTC to 8:30 PM PT / 03:30 UTC.

This issue has been resolved. Claude Opus 4.8 saw elevated errors from 3:06 PT / 22:06 UTC through 3:28 PT / 22:28 UTC.

1. investigating Jun 9, 2026, 6:20 AM GMT+08:00

   We are currently investigating this issue.

2. resolved Jun 9, 2026, 6:36 AM GMT+08:00

   This issue has been resolved. Claude Opus 4.8 saw elevated errors from 3:06 PT / 22:06 UTC through 3:28 PT / 22:28 UTC.

This issue has been resolved. Claude Opus 4.7 saw elevated errors from 2:01 PT / 21:01 UTC through 2:27 PT / 21:27 UTC.

1. investigating Jun 9, 2026, 5:05 AM GMT+08:00

   We are currently investigating this issue.

2. monitoring Jun 9, 2026, 5:35 AM GMT+08:00

   A fix has been implemented and we are monitoring the results.

3. resolved Jun 9, 2026, 5:56 AM GMT+08:00

   This issue has been resolved. Claude Opus 4.7 saw elevated errors from 2:01 PT / 21:01 UTC through 2:27 PT / 21:27 UTC.