We just experienced a core component failure that affected some models and APIs:
- Claude Code dedicated API
- CodeX dedicated API
- Gemini (including Vertex AI and Google AI)
- Fireworks
We noticed this issue immediately and began emergency troubleshooting. The problem was caused by a resource exhaustion issue due to one of our internal database indexes. The service has now been restored. We will conduct a thorough post-mortem review and implement measures to prevent similar issues from occurring in the future.