‹ Back to status overview

AI service incident history

Official incidents for AI platforms and APIs over the last 90 days. 925 records include timing, duration, affected components, and vendor updates.

November 2026

Incidents: 1

October 2026

Incidents: 29
Thursday, October 8
Music 2.5 endpoints performance degradedResolved · Duration: 58 min · Affected: ElevenAPI / OtherElevenLabs›DeepSeek 网页/API 性能下降(DeepSeek Web/API Degraded Performance)Resolved · Duration: 3 min · Affected: 对话服务(Chatservice), DeepSeek V4.1 Flash API服务(API Service)DeepSeek API›DeepSeek 网页/API 性能下降(DeepSeek Web/API Degraded Performance)Resolved · Duration: 3 min · Affected: 对话服务(Chatservice), DeepSeek V4.1 Flash API服务(API Service)DeepSeek›大语言模型 LLM 错误率升高Resolved · Duration: Less than 1 min · Affected: 大语言模型LLMMiniMax›Some APAC users are seeing errors in ChatGPT Work, conversations, and GPTs.Resolved · Duration: 1 hr 33 min · Affected: ChatGPT / ChatGPT Work, ChatGPT / Conversations, ChatGPT / GPTsOpenAI / ChatGPT›大语言模型 LLM 错误率升高Resolved · Duration: Less than 1 min · Affected: 大语言模型LLMMiniMax›Service Degradation for GLM 5.3Resolved · Duration: 10 min · Affected: Serverless / GLM 5.3 Fireworks AI›Service Degradation for Qwen 3.8 MaxResolved · Duration: 11 min · Affected: Serverless / Qwen 3.8 MaxFireworks AI›Degraded performance in Codex and Work mode: Dot turn failures, delayed responses, and reduced proactivityResolved · Duration: 1 hr 1 min · Affected: ChatGPT / dotsOpenAI / ChatGPT›Incident with Git Operations, Issues, Actions and Pull RequestsResolved · Duration: 47 min · Affected: Git Operations, Issues, Pull Requests and 1 moreGitHub›Dot in Codex may fail to create new threadsResolved · Duration: 1 hr 34 min · Affected: ChatGPT / dotsOpenAI / ChatGPT›Incident with Git Operations, Pull Requests and ActionsResolved · Duration: Less than 1 min · Affected: Git Operations, Webhooks, Issues and 2 moreGitHub›
Wednesday, October 7
Investigating service degradation — Grok BotResolved · Duration: 1 hr 25 min · Affected: Grok BotCursor›[Grok Bot] Investigating service degradation — Grok BotResolved · Duration: 1 hr 25 minxAI / Grok›Unable to create new ChatGPT Work threads in latest version of desktop appResolved · Duration: 6 hr 21 min · Affected: ChatGPT / Codex in ChatGPT DesktopOpenAI / ChatGPT›Workspace Agents Degraded and Responses ImpactedResolved · Duration: 1 hr 47 min · Affected: ChatGPT / AgentOpenAI / ChatGPT›[grok.com] grok.comResolved · Duration: Less than 1 minCursor›[Grok: grok.com] grok.comResolved · Duration: 5 minxAI / Grok›Investigating service degradation — Cloud AgentsResolved · Duration: 16 min · Affected: Grok Build and Cursor: Cloud Agents, Grok BotCursor›[Grok Bot] Investigating service degradation — Cloud AgentsResolved · Duration: 16 minxAI / Grok›Several services are degradedResolved · Duration: 3 hr 43 min · Affected: Webhooks, Pull RequestsGitHub›Investigating service degradation — Cloud Agents and Grok BotResolved · Duration: 2 hr 39 min · Affected: Grok Build and Cursor: Cloud Agents, Grok BotCursor›[Grok Bot] Investigating service degradation — Cloud Agents and Grok BotResolved · Duration: 2 hr 39 minxAI / Grok›[Grok API: Voice] Enterprise Voice DegradedResolved · Duration: 28 minxAI API›[Grok API: Voice] Enterprise Voice DegradedResolved · Duration: 28 minxAI / Grok›[Voice] Enterprise Voice DegradedResolved · Duration: Less than 1 minCursor›Investigating service degradation — Security Reviewer AgentsResolved · Duration: 1 hr 7 min · Affected: Grok Build and Cursor: Review AgentsCursor›[Grok Build and Cursor: Review Agents] Investigating service degradation — Security Reviewer AgentsResolved · Duration: 1 hr 7 minxAI / Grok›Computer Use Is Experiencing IssuesResolved · Duration: 2 hr 45 min · Affected: APIs / AgentsOpenAI API›

About this data

Where does the incident data for AI services come from?

Data comes from official vendor status pages, syncs every 5 minutes, and covers 90 days. The detail page links to the original report.

How do I read the component status bars?

Each block is one day. Green means no issue was reported, yellow means degraded performance, red means a major outage, and gray means no data. Availability covers the last 90 days.

Why is history missing for some services?

Only services with a public official status page are included.

How is duration calculated?

Duration runs from the official start time to recovery, or to the current time for ongoing incidents. Incidents spanning multiple days appear on each affected day.

See the full service list and live status in the status overview