Phoenix exports some metrics via a Prometheus endpoint, which can be scraped for health and operational metrics, but there is no built-in integration with Grafana, nor does Phoenix natively provide time series metrics like "traces per project" in a Grafana-ready format. For trace counts and similar statistics, Phoenix's UI and API provide trace overviews, but not direct Grafana dashboards or time series exports for external visualization tools. According to a trusted source, there is no official Grafana integration for Phoenix at this time, but Prometheus metrics are available for health checks and basic monitoring if you scrape the endpoint from the Phoenix container deployment (<https://arize-ai.slack.com/archives/C04R3GXC8HK/p1719072670.110699|Slack discussion>, <https://github.com/Arize-ai/phoenix/blob/4b5341712ac9443da3e25355dbe68f8968c9cee0/Dockerfile#L68-L69|Phoenix Dockerfile>, <https://arize-ai.slack.com/archives/C04R3GXC8HK/p1729612912.189099|Support Staff Knowledge>).
For time series trace counts per project, Phoenix does not currently expose this as a Prometheus metric or Grafana-ready data source. However, feature requests and issues have been raised to add time series and quantile metrics for traces and latency in the Phoenix UI and API, but these are not yet available for external dashboards (<https://github.com/Arize-ai/phoenix/issues/1125|GitHub Issue: trace count>, <https://github.com/Arize-ai/phoenix/issues/6763|GitHub Issue: timeseries graph>). Would you like more detail on how to access Prometheus metrics or alternative ways to monitor Phoenix health?
Sources:
- <https://arize-ai.slack.com/archives/C04R3GXC8HK/p1719072670.110699|Slack discussion: Phoenix metrics and Prometheus>
- <https://github.com/Arize-ai/phoenix/issues/1125|GitHub Issue: trace count>
- <https://arize-ai.slack.com/archives/C04R3GXC8HK/p1729612912.189099|Support Staff Knowledge>
- <https://github.com/Arize-ai/phoenix/issues/6763|GitHub Issue: timeseries graph>
