Elevated error rates on Codex, ChatGPT and Responses API
A record of the OpenAI incident on June 3, 2026 (Japan time): start time, duration and severity, plus current status, what to do, and alternatives.
Other providers down at the same time
4 other incident(s) at different providers overlapped with this one. It may not have been limited to a single service — several providers were degraded at once.
- AnthropicIssue affecting some Claude Code services
- RunwayIssues with Seedance and Seedream generations
- GitHubDisruption with some GitHub services
- AnthropicElevated errors on Opus 4.7
Derived from our own archive of official status pages across 13 providers. Items lasting more than 24 hours and unresolved items are excluded, as they would misrepresent the moment.
How big was this outage?
This outage lasted 371 minutes. Across 15 major incidents recorded for OpenAI, the median duration is 63 minutes, making this the 4th longest.
Longer than a typical outage.
Only incidents recorded as major-or-worse and already resolved are counted.
Current status
OpenAI is operating normally now. This incident has been resolved.
See current OpenAI status →What you can do during an outage
Source: OpenAI's official status page.
Other OpenAI incidents
- Investigating unexpected usage limit resetsSeptember 10, 2026
- Increased Error Rate For Pro and Plus Plan ConversationsSeptember 10, 2026
- File uploads are delayed or failingSeptember 8, 2026
- Elevated errors for image generationSeptember 8, 2026
- Users in APAC region may face increased error in ChatGPT, Work, image generation, file upload, Voice, and Codex CloudSeptember 4, 2026