OpenAI outage: Elevated errors with gpt-image-2.5-flare

1. resolvedSep 16, 2026, 00:30 UTC

   All impacted services have now fully recovered.

2. monitoringSep 15, 2026, 23:58 UTC

   We have applied the mitigation and are monitoring the recovery.

3. investigatingSep 15, 2026, 23:50 UTC

   We are experiencing elevated error rates for image generation and editing requests using gpt-image-2.5-flare in the API. Our team is working to mitigate the issue. We will provide another update as more information becomes available.

What APIStatus.watch saw

• Sep 15, 2026, 23:55 UTCoperational → partial outage
• Sep 16, 2026, 00:35 UTCpartial outage → operational

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• MongoDB Atlas: Impaired Cluster operations in AWS me-central-1 and AWS me-south-1Major · Sep 3, 2026, 16:44 UTC
• Elasticsearch: Elastic Agent enrollment/check-in failures on 9.5.3 (and 9.4.6) with Fleet remote Elasticsearch outputMajor · Sep 9, 2026, 20:44 UTC
• Confluent Cloud: Multiple Confluent Cloud services are in a degraded state - All regionsMajor · Sep 15, 2026, 23:59 UTC
• Twilio: Voice Call Failures from a Subset of Twilio Phone Numbers to Hong KongMinor · Sep 12, 2026, 00:16 UTC
• Telnyx: Outbound Messaging LatencyMinor · Sep 15, 2026, 15:27 UTC
• ClickHouse Cloud: ClickPipes failing on Kinesis in AWS us-east-1Minor · Sep 15, 2026, 18:57 UTC
• Telnyx: SMS Delivery — Encoding Issues on Outbound Messages to T-MobileMinor · Sep 15, 2026, 21:57 UTC

How often does OpenAI have incidents?

OpenAI reported 18 incidents in the last 90 days, 4 of them major or critical. A typical incident lasted 52 min. See OpenAI's uptime and incident history