outages.live
Live
OpenAIIncident · 2026-10-14 17:00 UTC

Delayed Costs data in the Compliance API

ResolvedOfficial update

All impacted services have now fully recovered.

The latest update from OpenAI.

State

Resolved

Started

18 d ago

2026-10-14 17:00 UTC

Lasted

41 h 44 min

until 2026-10-16 10:44 UTC

Worst impact

Degraded

Timeline

5 updates
Oct 14Oct 15Oct 15Oct 16Oct 16
DegradedUpdate postedDates in UTC

Identified

29 h 36 min 71%

Monitoring

12 h 8 min 29%

Updates

Times in UTC

As posted by OpenAI

Resolved2026-10-16 10:44 UTC

All impacted services have now fully recovered.

Monitoring2026-10-15 22:36 UTC

We have deployed a fix and are monitoring recovery. Costs data in the Compliance API remains delayed while we process the backlog. We will provide further updates as processing catches up.

Identified2026-10-14 20:00 UTC

We have identified an issue causing delays in publishing organization cost data through the Costs API. A fix is in progress and currently undergoing testing. API and ChatGPT usage are not affected, and other reporting channels remain available. We are continuing work to restore normal data freshness.

Identified2026-10-14 17:02 UTC

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.

Identified2026-10-14 17:00 UTC

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.

OpenAI in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

24

Days with an incident

16

Median duration

1 h 51 min

This incident

22× the median

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

3 days
median 1 h 51 min
90 days agoToday

Other OpenAI incidents

All incidents

OpenAI·Elevated errors with search in Dots, ChatGPT Work, and certain ChatGPT thinking experiences

All affected services are operating normally again. We’re sorry for the disruption, and we appreciate your patience.

Resolvedresolved 1 d ago

OpenAI·Elevated errors for GPT Image 2 API image edits

All affected services are operating normally again. We’re sorry for the disruption, and we appreciate your patience.

Resolvedresolved 2 d ago

OpenAI·6.1 Sol Degraded Model Performance

All affected services are operating normally again. We’re sorry for the disruption, and we appreciate your patience.

Resolvedresolved 5 d ago

OpenAI·Elevated error rates for most hosted Code Reviews and Security Reviews on private GitHub repositories

The issue is now resolved.

Resolvedresolved 5 d ago

OpenAI·Elevated error rates for Ads POST requests

All impacted services have now fully recovered.

Resolvedresolved 6 d ago

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

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane