Track LLM usage in one screen
When teams manage different model providers, request, token, and cost metrics should be visible in one panel.
V1 target
- Model usage summary
- Request and token metrics
- API key management
- Usage-based billing preparation
- External model provider support
What it helps with
1
Separate model calls
Track usage records per project for providers such as OpenAI, Claude, and Gemini.
2
See limits
Metrics such as tokens and request counts make billing decisions easier to understand.
3
Reduce operations work
See AI usage next to deployment work instead of searching through separate dashboards.
Try the first project from the panel
During early access, you can create an account and review the deploy and AI Gateway flow.