OpenAI

Elevated error rate on gpt-3.5-turbo-0613, gpt-3.5-turbo-instruct, and reserved capacity models
Resolved

This incident has been resolved.

Mon, Jan 15, 2024, 02:54 AM
•
1 year ago
•
Affected components

No components marked as affected

Updates

Resolved

This incident has been resolved.

Mon, Jan 15, 2024, 02:54 AM
1h earlier...

Monitoring

A fix has been implemented and we are monitoring the results.

Mon, Jan 15, 2024, 01:42 AM
1h earlier...

Identified

We are seeing reduced error rates on gpt-3.5-turbo-0613 and gpt-3.5-turbo-instruct. We are continuing to address the issue on reserved capacity models.

Mon, Jan 15, 2024, 12:42 AM

Identified

The issue has been identified and a fix is being implemented.

Mon, Jan 15, 2024, 12:41 AM
26m earlier...

Investigating

We are currently investigating this issue.

Mon, Jan 15, 2024, 12:15 AM
Powered by

Availability metrics are reported at an aggregate level across all tiers, models, and error types. Individual customer availability may vary depending on their subscription tier: PAYG, Scale-Tier, or Reserved Capacity, as well as the specific model and API features in use.