Planned Highlights
- Request volume and token usage by model and time range
- Latency percentiles and error rates for each deployment
- Cost and quota insights to track spend and limits
- Exportable reports for audits and internal sharing
Observability
Metrics
Usage and performance analytics for RamaLama Cloud (coming soon).
Metrics will give you visibility into how your cloud workloads perform over time.
We are currently building dashboards and exports to help you understand usage and reliability at a glance.
Metrics are coming soon; here is what to expect.