‹ Back to status overview

AI service incident history

Official incidents for AI platforms and APIs over the last 90 days. 928 records include timing, duration, affected components, and vendor updates.

November 2026

Incidents: 30
Tuesday, November 3
Service Degradation for Kimi K3 USResolved · Duration: 1 hr 41 min · Affected: Serverless / Kimi K3 USFireworks AI›Incident with API, Git, and Copilot requestsResolved · Duration: 30 min · Affected: API Requests, Issues, CopilotGitHub›Service Degradation for Kimi K3 USResolved · Duration: 10 min · Affected: Serverless / Kimi K3 USFireworks AI›Service Degradation for Kimi K3 USResolved · Duration: 14 min · Affected: Serverless / Kimi K3 USFireworks AI›Service Degradation for Kimi K3 USResolved · Duration: 8 min · Affected: Serverless / Kimi K3 USFireworks AI›Service Degradation for Kimi K3Resolved · Duration: 13 min · Affected: Serverless / Kimi K3Fireworks AI›DeepSeek 网页/API 部分中断(DeepSeek Web/API Partially Unavailable)Resolved · Duration: 1 hr 49 min · Affected: DeepSeek V4.1 Flash API服务(API Service), 对话服务(Chatservice), DeepSeek V4 Pro API服务(API Service)DeepSeek API›DeepSeek 网页/API 部分中断(DeepSeek Web/API Partially Unavailable)Resolved · Duration: 1 hr 49 min · Affected: DeepSeek V4.1 Flash API服务(API Service), 对话服务(Chatservice), DeepSeek V4 Pro API服务(API Service)DeepSeek›Service Degradation for GLM 5.3Resolved · Duration: 20 hr 5 min · Affected: Serverless / GLM 5.3 Fireworks AI›大语言模型 LLM 错误率升高Resolved · Duration: 3 min · Affected: 大语言模型LLMMiniMax›File upload errors in ChatGPTResolved · Duration: 4 hr 52 min · Affected: ChatGPT / File uploadsOpenAI / ChatGPT›Service Degradation for GLM 5.3 FastResolved · Duration: 3 min · Affected: Serverless / GLM 5.3 FastFireworks AI›大语言模型 LLM 错误率升高Resolved · Duration: 2 min · Affected: 大语言模型LLMMiniMax›Elevated errors on GPT-5.4 NanoResolved · Duration: 38 min · Affected: Copilot AI Model ProvidersGitHub›Kling video generations failing or delayedResolved · Duration: 8 hr 6 min · Affected: App, Backend, Public APIRunway›

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