Delayed Costs Data in the Compliance API
OpenAI reports that Organization cost data is delayed in the Compliance API. The Costs API is affected. OpenAI identified the issue and works to restore normal data freshness. API and ChatGPT usage are not affected.
State
Identified
Started
Ongoing for
40 min
Worst impact
Degraded
Timeline
1 updateIdentified
40 min 100%
Updates
Times in UTCAs posted by OpenAI
We have identified an issue causing delays in publishing Organization cost data through the Costs API. API and ChatGPT usage are not affected. We are working to restore normal data freshness.
OpenAI in the last 90 days
Full historyIncidents in 90 days
38
Days with an incident
27
Median duration
1 h 56 min
This incident
65% shorter than the median
Other OpenAI incidents
All incidentsOpenAI·Sites: Publishing failing
OpenAI reports that publishing on Sites failed for some users. OpenAI identified the problem and applied a fix. The incident is resolved and lasted about 2 hours.
OpenAI·Elevated errors affecting the Microsoft 365 connector
OpenAI reports elevated errors on the Microsoft 365 connector. New connections may fail and tools may not work as expected. OpenAI sees signs of recovery and continues to monitor the affected services.
OpenAI·GPT-image-2.5 and 2.6 Sunburst & Flare High error rate
OpenAI reports a high error rate for GPT-image-2.5 Sunburst, 2.5 Flare, 2.6 Sunburst, and 2.6 Flare. OpenAI applied a mitigation and monitored the services. The incident is resolved and lasted 33 minutes.
OpenAI·Unable to start new Workspace Agent runs
OpenAI reports that users could not start new Workspace Agent runs. OpenAI marked the incident as resolved. The outage lasted 9 hours and 42 minutes.
OpenAI·Elevated errors affecting logins, sign-ups, and ChatGPT features
Logins, sign-ups, work mode, dots, sites, and spaces had elevated errors at OpenAI. OpenAI also reported elevated error rates for creating conversations through the OpenAI API. OpenAI reports that the incident is resolved and that all affected services operate normally again. The outage lasted 9 minutes.
Follow OpenAI
Your coding agent knows when OpenAI is down, and tells you when a failure is theirs, not yours. You can also get OpenAI incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "openai" and tell me if OpenAI has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.live/feed.xml?providers=openai/feed subscribe https://outages.live/feed.xml?providers=openaiFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane