‹ Back to incident history

Elevated latency in the Responses API

ResolvedMinor incidentOpenAI API
Tuesday, September 1, 2026 06:27 – Wednesday, September 2, 2026 03:05 (20 hr 37 min)
Affected components
APIs / Responses
Updates
ResolvedWednesday, September 2, 2026 03:05

All impacted services have now fully recovered.

MonitoringWednesday, September 2, 2026 02:09

We have applied the mitigation and are monitoring the recovery.

IdentifiedWednesday, September 2, 2026 01:36

We are implementing the mitigation.

IdentifiedTuesday, September 1, 2026 23:15

We have identified elevated latencies impacting Responses API on the US endpoint.

MonitoringTuesday, September 1, 2026 09:46

We have applied the mitigation and are monitoring the recovery.

MonitoringTuesday, September 1, 2026 07:13

We have applied a mitigation and are monitoring recovery.

IdentifiedTuesday, September 1, 2026 06:27

We have identified an issue causing elevated latency for some Responses API requests. We are working on implementing a mitigation.

Incident data from the OpenAI API official status page:Read the official incident

About this data

Where does the incident data for OpenAI API come from?

Data comes from the OpenAI API official status page, syncs every 5 minutes, and covers 90 days. The detail page links to the original report.

How do I read the component status bars?

Each block is one day. Green means no issue was reported, yellow means degraded performance, red means a major outage, and gray means no data. Availability covers the last 90 days.

Why is history missing for some services?

Only services with a public official status page are included.

How is duration calculated?

Duration runs from the official start time to recovery, or to the current time for ongoing incidents. Incidents spanning multiple days appear on each affected day.

See the full service list and live status in the status overview