outages.live
Live
OpenAIIncident ·

Incorrect cost data in Costs API exports

NoticeOfficial update
0

Costs API exports show incorrect cost data. The affected records cover November 6 to November 9. OpenAI reports that it identified the issue, that it is correcting the records, and that it is monitoring the fix.

State

Monitoring

Started

Ongoing for

25 min

Worst impact

Notice

Timeline

1 update
04:4204:4804:5405:0005:07
NoticeUpdate postedTimes in UTC

Monitoring

25 min 100%

Updates

Times in UTC

As posted by OpenAI

Monitoring

We have identified an issue causing incorrect cost data in Costs API exports published between November 6 and 9. We are working to correct the affected records and will provide an update once recovery is confirmed.

OpenAI in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

32

Days with an incident

24

Median duration

1 h 52 min

This incident

78% shorter than the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

3 days
median 1 h 52 min
90 days agoToday

Other OpenAI incidents

All incidents

OpenAI·Elevated Errors On API

OpenAI reported elevated errors on the API. OpenAI later stated that all affected services operate normally again. The incident is resolved and lasted about 43 minutes.

Resolved

OpenAI·Elevated ChatGPT Conversation Errors

ChatGPT conversation errors increased for some users. OpenAI reported the incident as resolved. The outage lasted 52 minutes.

Resolved

OpenAI·Elevated errors with image generation

Image generation does not work and users get errors. OpenAI reports that the incident is resolved. The outage lasted about 109 minutes.

Resolved

OpenAI·Elevated error rates with some U.S. business Mastercards

Payment declines occur on some U.S. business Mastercards, including some Brex cards, and on cards with numbers that start with 544015, 546400, 543502, 543799, 512998, or 513989. This can stop automatic recharges and one-time API credit purchases. OpenAI reports that it applied a mitigation and monitors the affected services.

Notice

OpenAI·ChatGPT Work and Dots Errors

ChatGPT Work and Dots had degraded service with elevated errors. OpenAI reports that the incident is resolved. The outage lasted about 13 hours.

Resolved

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.

Prompt
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.

RSS
https://outages.live/feed.xml?providers=openai
Slack
/feed subscribe https://outages.live/feed.xml?providers=openai

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane