OpenAI

ChatGPT and AI APIs · Official status page (opens in a new tab)

Counts cover incidents in this archive only. They are not a complete outage history or a reliability measure.

Failures in OpenAI's systems

Incidents where the documented failure was in OpenAI's own systems. Durations are measured to the end points the sources give.

  • Nov 11, 2026
    OpenAI: Unable to start new Workspace Agent runs
    Unknown · Root cause unknown
    Stated cause

    The provider has not stated a cause in its status updates.

    Duration: 9 h 42 minto: Provider marked resolvedResolved
  • Dec 11, 2024
    ChatGPT, API and Sora outage: a new telemetry service overwhelms Kubernetes
    ChatGPTOpenAI APISora
    Configuration change · Root cause confirmed
    Stated cause

    A new telemetry service deployed at 3:12 PM PST had a configuration that made every node in each cluster run resource-intensive Kubernetes API operations. The API servers were overwhelmed, taking down the control plane in most large clusters; DNS-based service discovery depends on the control plane, so services could no longer find each other.

    Duration: 4 h 22 minto: All services fully recoveredResolved
Showing 2 of 2 documented here