大模型服务状态
每30分钟通过rss或api等检测方式跟踪各模型服务状态，仅供参考。
近期事件
Network Performance Issues in Paris, France (CDG)
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
We are continuing to investigate this issue.
Cloudflare is investigating issues with network performance in Paris, France (CDG). A subset of traffic transiting the Paris data center may observe slightly higher latency. We are working to analyse and mitigate this problem. More updates to follow shortly.
Minor Service Outage
暂无详情
CNI 2.0 issues in London
Cloudflare is currently investigating issues related to CNI 2.0 in London. Customers utilizing CNI 2.0 through London (LHR) data center will experience a failure to send traffic over their CNI. We are working to mitigate impact to CNI customers. More updates to follow shortly.
Minor Service Outage
暂无详情
Increased HTTP 500 Errors in Querétaro, Mexico
A fix has been implemented and we are monitoring the results.
Cloudflare is investigating an increased level of HTTP 500 errors in Querétaro, Mexico. We are working to analyse and mitigate this problem. More updates to follow shortly.
Elevated Errors China Network
A fix has been implemented and we are currently monitoring the results.
The cause of this issue has been identified and a fix is being implemented.
We are investigating an issue with errors in China Network.
CNI 2.0 Experiencing Intermittent 5XX Errors
We have identified and applied a fix for this issue and are currently monitoring the results.
We are currently investigating an issue where customers may experience errors when attempting to view CNI 2.0 interconnections from the API or Dashboard. Data plane traffic is unaffected.
Minor Service Outage
暂无详情
Durable Objects Increased Errors
We are continuing to see service recovery.
We are continuing to see service recovery.
We are continuing to see service recovery.
We have applied a fix and are beginning to see service recovery.
We are continuing to work on a fix for this issue.
We are continuing to work on a fix for this issue.
The cause of this issue has been identified and a fix is being implemented.
Cloudflare is investigating issues causing an increase of errors for Durable Objects and downstream services in multiple regions (Europe and APAC).
We are continuing to investigate this issue.
Cloudflare is investigating issues causing an increase of errors for Durable Objects and downstream services in Europe and APAC. We are working to analyse and mitigate this problem. More updates to follow shortly.
Minor Service Outage
暂无详情
Magic WAN / Magic Transit tunnel health alert delivery
We are investigating an issue that may prevent some Magic WAN and Magic Transit tunnel health alert notifications from being delivered. Affected customers may not have received expected notifications for tunnel state changes during this period. Tunnel traffic and routing are not impacted — this issue is limited to alert notifications only. We have identified the likely cause and are working on a fix.
Minor Service Outage
暂无详情
Cloudflare R2 Issues
Cloudflare is investigating elevated error rates affecting R2 and some services that depend on it, including Stream, Pipelines, and Log Explorer. Customers may have experienced increased errors reading or writing objects and delayed data processing. Impact was partially mitigated at approximately 21:52 UTC, and dependent services have recovered. A low level of R2 errors is still occurring, and we are actively working toward full resolution.
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Elevated errors in ENAM region
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
Customers may experience elevated error rates in ENAM region
Elevated R2 errors in ENAM region
The issue has been identified and a fix is being implemented.
Customers may experience elevated error rates from R2 in ENAM region
Network Performance Issues in AMS
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
Cloudflare is investigating issues with network performance in Amsterdam. We are working to analyse and mitigate this problem. More updates to follow shortly.
Network Performance issues - Increased HTTP 502 Errors in HKG
Cloudflare is investigating an increased level of HTTP 502 errors originating from the Hong Kong datacenter. We are working to analyse and mitigate this problem. More updates to follow shortly.
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Elevated R2 errors in WEUR region
The issue has been identified and a fix is being implemented.
Customers may experience elevated error rates in WEUR region
Gateway List updates using CSV not applied
Cloudflare is aware of and investigating an issue where changes applied via CSV to Gateway Lists are not being applied. More updates to follow shortly.
Minor Service Outage
暂无详情
Elevated errors in item PUT requests to AI Search
Cloudflare is observing issues with Cloudflare AI Search service. We are currently working on a resolution. More updates to follow shortly.
Elevated R2 errors in EU region
A fix has been implemented and we are monitoring the results.
Cloudflare is observing issues with Cloudflare R2 service. We are currently working on a resolution. More updates to follow shortly.
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Cloudflare dash is unavailable
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
Cloudflare is investigating issues with Cloudflare Dashboard and related APIs. These issues do not affect the serving of cached files via the Cloudflare CDN or other security features at the Cloudflare Edge. Customers using the Dashboard / Cloudflare APIs are impacted as requests might fail and/or errors may be displayed.
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Cloudflare Dashboard login issue
A fix has been implemented and we are monitoring the results.
We are continuing to investigate this issue.
Cloudflare is aware of and investigating an issue where some users are unable to login to the Cloudflare Dashboard. We are working to mitigate the problem and will update shortly.
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Pages Dashboard issues
Cloudflare is aware of and investigating an issue where users may not be able to view Pages deployments in the dashboard. We are working to mitigate this problem. More updates to follow shortly.
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Minor Service Outage
暂无详情
Partially Degraded Service
暂无详情
Elevated errors on Sonnet 5 and Haiku 4.5
The issue has been identified and a fix is being implemented.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Minor Service Outage
暂无详情
Elevated errors for multiple models
We have seen success rates recover and are continuing to monitor closely to ensure no further issues. We will provide an additional update shortly.
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.
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.
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.
We are investigating elevated errors on requests to multiple models. We will provide an update as soon as possible.
Minor Service Outage
暂无详情
Enterprise SSO sign-in failures
The issue has been identified and a fix is being implemented.
Partially Degraded Service
暂无详情
Partially Degraded Service
暂无详情
Partial outage of claude.ai: container creation
A fix has been implemented and we are monitoring the results
We are continuing to investigate this issue.
We are investigating an outage affecting features such as document creation in claude.ai, Cowork Remote, Claude Code, Claude Code Remote, and Claude Design
Partially Degraded Service
暂无详情
Partially Degraded Service
暂无详情
Partial System Degradation
暂无详情
Elevated errors for Github connector
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/>
We have identified that users are experiencing elevated errors when using the Github connector. We are working on implementing a mitigation.
Partial System Degradation
暂无详情
Elevated Error Rates For SSO Login
We have applied the mitigation and are monitoring the recovery.
We are investigating the issue for the listed services and seeing gradual recovery.
We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.
Partial System Outage
暂无详情
Elevated errors affecting ChatGPT
We have applied the mitigation and are monitoring the recovery.
We are investigating login issues and intermittent errors affecting ChatGPT.
Partial System Degradation
暂无详情
Some ChatGPT Go users may experience conversation failures when using GPT-5.5.
We have applied the mitigation and are monitoring the recovery.
We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.
Elevated errors when creating sites in ChatGPT
We have applied the mitigation and are monitoring the recovery.
We are investigating the issue for the listed services.
Partial System Degradation
暂无详情
Users may experience elevated errors uploading, deleting, and navigating files in the ChatGPT Library
We have applied the mitigation and are monitoring the recovery.
We are investigating the issue for the listed services.
We have applied the mitigation and are monitoring the recovery.
We are continuing to investigate elevated errors affecting file uploads, deletions, and navigation in the ChatGPT Library.
We are investigating the issue for the listed services.
Partial System Degradation
暂无详情
Elevated conversation and login errors on ChatGPT for iOS and macOS
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.
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.
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.
We are continuing to investigate elevated errors affecting conversations, sign-ups, and sign-ins for some users on iOS and macOS.
We are continuing to investigate elevated errors affecting some users on iOS. Some users may be unable to load or use conversations.
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.
Elevated conversation error rates on ChatGPT for iOS
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.
Elevated Errors for Sora API
We are investigating the issue for the listed services.
Partial System Degradation
暂无详情
OpenAI website and Help Center content may be unavailable
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.
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.
OpenAI Help Center Currently Unavailable
OpenAI's Help Center article and search functionality is currently unavailable, and the Help Center chatbot experience may also be degraded. We are investigating the issue.
Partial System Degradation
暂无详情
Degraded REST API Availability
We are continuing to investigate an issue causing approximately 35% of REST API requests to fail. Based on our current understanding, requests are not consistently reaching the application layer, resulting in failed requests returning HTML responses instead of the expected API response format. We are actively investigating the issue and will provide another update as soon as more information is available.
API Requests is experiencing degraded performance. We are continuing to investigate.
We are aware of degraded REST API availability and are investigating
We are investigating reports of impacted performance for some GitHub services.
Partially Degraded Service
暂无详情
Claude Fable 5 experiencing degraded performance
We are experiencing degraded availability for the Claude Fable 5 model in Copilot products and IDE surfaces. This is due to an issue with an upstream model provider. While we work with them to resolve the issue, we recommend choosing another model or selecting 'Auto' to continue using Copilot.
We are investigating reports of degraded performance for Copilot AI Model Providers
Partially Degraded Service
暂无详情
HuggingFace download issues
Still seeing signs of improvement, most models are able to spin up with a few still waiting their turn from HuggingFace. Models should spin up after enough tries if they are failing for HuggingFace related reasons.
We have seen most HuggingFace calls start succeeding, except for a small subset that are being downloaded through [cas-bridge.xethub.hf.co](http://cas-bridge.xethub.hf.co "cas-bridge.xethub.hf.co"). Most models are now succeeding to spin up
HuggingFace is reporting recovery, which we are also seeing on our end. However, we still see minor degradation, which we believe is due to thundering herd once the main issue was resolved. We are still keeping an eye out, but believe we are recovering
We are aware of 504s being returned by models that reach out to HuggingFace during setup. We believe this is likely related to the disruption visible at [https://status.huggingface.co/](https://status.huggingface.co/ "https://status.huggingface.co/"). We are monitoring and will update when we can identify the HuggingFace CDN is back up/
Partial System Degradation
暂无详情
Partial System Degradation
暂无详情
Partial System Degradation
暂无详情
Partial System Degradation
暂无详情
H100 GPU shortage resulting in high queue times
We pushed a fix and are monitoring
Long queue times, especially on BFL models
Partial System Degradation
暂无详情
Partial System Degradation
暂无详情
High contention on H100 hardware
We are seeing high contention on H100 hardware which is resulting in delays on predictions and scale-out.