Traces

The Traces page provides visibility into AI request activity across the organization. Use it to investigate requests, review operational metrics, analyze usage patterns, and troubleshoot routing or model behavior.

Use REFRESH to reload summary metrics and trace results for the selected filters and time range.

Summary cards at the top of the page display aggregated request statistics, including total requests, success rate, token usage, estimated spend, and average request latency for the selected period.

Filters allow you to narrow trace results by provider, model, and employee. The time-range selector supports predefined intervals such as 1 day, 1 week, 2 weeks, and 1 month, as well as custom date ranges. Selected filters and time ranges apply to both the summary cards and the trace table.

The main table lists recorded AI requests in chronological order. For each request, the table displays the request timestamp, provider, model, execution status, associated virtual key, employee, token usage, estimated cost, latency, routing information, and streaming status. Additional columns provide request-specific operational details when available.

Because the table contains a large number of attributes, horizontal scrolling may be required to access token, cost, latency, and routing information.

Select a row to open the trace details view and inspect the full request and response information.

Trace details

Selecting a trace from the table opens a detail panel displaying the trace UUID in the header (with a copy control if needed), together with the Provider, Model, Status, and Time.

The Request details section displays request metadata, including the provider that handled the request, the full model identifier, the virtual key used for the request, the applied routing rule, the initiating employee or principal, and whether streaming was enabled.

The Metrics section displays request statistics, including total token usage with prompt and completion breakdowns, end-to-end latency, request cost, and the request timestamp.

The Request & Response section displays captured prompt and completion payloads. When request bodies are unavailable or not stored for the deployment, the panel displays No data.

The Params section contains the JSON request payload sent to the provider, including request parameters such as tools, function definitions, and parameter schemas. Use the copy control in the panel corner to copy the full payload for debugging or support purposes.

Use Traces to audit who used which models, debug latency or failures after routing changes in Providers, and reconcile per-request token usage with Usage and Cost. For profiled training runs and experiment outputs, see Experiment Tracking — Tasks and Artifacts.