Resolved -
As of 18:45 UTC, our Engineering team has resolved the issues with OpenAI rate limits that were affecting certain DigitalOcean services. The problem, which began at approximately 09:30 UTC, caused errors (429s) for Agents using OpenAI models for serverless inference.
Systems Affected:
Serverless inference
Evaluations
Technical Details: The issue was caused by exceeding OpenAI rate limits, which resulted in 429 errors for OpenAI models.
Duration: The incident lasted for approximately 9 hours, from 09:30 UTC to 18:45 UTC. We apologize for any inconvenience this may have caused and appreciate your patience as we worked to resolve the issue. If you continue to experience problems, please open a ticket with our Support team.
Aug 13, 09:30 UTC