GPT-4o-mini Fine-Tuned Models High Error Rate

Incident Report for OpenAI

Resolved

This incident has been resolved.

Posted Jul 27, 2024 - 20:35 PDT

Monitoring

Service error rates and latencies for GPT-4o-mini fine-tunes have returned to normal. We will monitoring these services closely to ensure they continue to operate as expected.

Posted Jul 27, 2024 - 16:17 PDT

Update

Error rate is returning to 0% but we are still experiencing high variance in request latency. Continuing to monitor.

Posted Jul 27, 2024 - 15:55 PDT

Update

A mitigation has been deployed, error rates are stabilizing but still elevated.

Posted Jul 27, 2024 - 15:13 PDT

Update

We are continuing to work on a fix. The inference services for 4o-mini fine-tuned models (only 4o-mini) are still experiencing a partial outage.

Posted Jul 27, 2024 - 14:56 PDT

Identified

We are currently experiencing very high error rates for fine-tuned gpt-4o-mini models.

Posted Jul 27, 2024 - 14:24 PDT

This incident affected: API.