Skip to main content

OpenAI API outage on October 9, 2026: Delayed Costs data in the Compliance API

OpenAI reported an incident affecting OpenAI API for 2 days 22 hours on 9 October 2026, from 17:23 to 16:02 UTC.

api.openai.com All times UTC

Resolved

Official incident reported by OpenAI

Started
17:23
9 Oct 2026 UTC
Resolved
16:02
12 Oct 2026 UTC
Duration
2d 22h
2 days 22 hours
Impact
Minor
as rated by OpenAI
Updates
5
posted by OpenAI

Timeline

All times UTC.

Official incident from OpenAI

Delayed Costs data in the Compliance API

Resolved Minor impact 9 Oct 2026 17:23 UTC View on OpenAI's status page
  1. Official
    Identified

    We have identified an issue causing delays in publishing organization cost data through the Costs API. API and ChatGPT usage are not affected, and other reporting channels remain available. We are working to restore normal data freshness.

  2. Official
    Identified

    We have identified an issue causing delays in publishing Costs data through the Compliance API. The API Platform organization costs endpoint and ChatGPT usage are not affected, and other reporting channels remain available. We are working to restore normal data freshness.

  3. Official
    Identified

    Some customers may continue to experience delayed Costs data through the Compliance API. ChatGPT usage and API Platform requests are not affected, and other reporting channels remain available. We have identified the cause and are continuing work to restore normal data freshness. We will provide another update as work progresses.

  4. Official
    Monitoring

    We have implemented a mitigation, and delayed Costs data is now processing through the Compliance API. Some customers may continue to see incomplete Costs data while the backlog catches up. We expect this catch-up process to continue through Sunday, October 11. ChatGPT usage and API Platform requests remain unaffected. We are monitoring recovery.

  5. Official
    Resolved

    All impacted services have now fully recovered.

"Official" rows are quoted from OpenAI's public status page, status.openai.com. Very long posts are shortened.

What our checkpoints saw

HostTracker's checkpoints, which test api.openai.com from several locations, recorded no outage of 5 minutes or longer during this incident. A provider can report a problem that affects only some features, regions or accounts, which a check of the main address does not see. The live OpenAI API status shows what our checks see right now.

Does your product depend on OpenAI API?

An outage like this one reaches your users through your product, and most teams hear about it from a customer rather than from a dashboard. HostTracker watches any endpoint you name - your own site, an API you call, a vendor you resell - from 300+ locations, confirms a failure from several of them before it says anything, and then tells you by email, SMS, voice call or your chat tool.

You get the same record you are reading here for your own services: every outage timestamped, with the checks that observed it.

Independent measurement by HostTracker. Not affiliated with OpenAI API. Official updates are quoted from OpenAI's public status page and remain OpenAI's own words.