outages.live
Live
OpenAIIncident ·

Unable to start new Workspace Agent runs

Major outageOfficial update
0

OpenAI reports that users cannot start new Workspace Agent runs. OpenAI is investigating the issue.

State

Investigating

Started

Ongoing for

58 min

Worst impact

Major outage

Timeline

1 update
22:5023:0423:1923:3323:48
Major outageUpdate postedTimes in UTC

Investigating

58 min 100%

Updates

Times in UTC

As posted by OpenAI

Investigating

We are investigating an issue preventing users from starting new Workspace Agent runs. We will share another update as more information becomes available.

OpenAI in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

34

Days with an incident

25

Median duration

1 h 54 min

This incident

49% shorter than the median

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

4 days
median 1 h 54 min
90 days agoToday

Other OpenAI incidents

All incidents

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.

Resolved

OpenAI·Incorrect cost data in Costs API exports

Costs API exports published between November 6 and November 9 contain incorrect cost data. OpenAI reports that the incident is resolved. The incident lasted 140 minutes.

Resolved

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

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