A trace can contain multiple model calls and therefore link to multiple request logs. Supported direct GenAI spans create request logs, while spans managed by
PromptLayer.run() can link to the run’s existing request log.
Where to Go Next
Request Logs
Review individual model calls, errors, inputs, outputs, usage, and cost.
Traces
Inspect the parent-child execution path across model calls, tools, agents, and application code.
Search
Find request logs or traces with content queries, structured filters, and date ranges.
Analytics
Aggregate the current request-log or trace query into charts.
Configure Observability
Once you know which artifact you need, follow the setup path for the code that produces it:Configure Request Logging
Choose how requests are captured, then add IDs, tags, metadata, scores, and prompt associations.
Configure Tracing
Choose PromptLayer SDK spans, provider auto-instrumentation, a telemetry integration, or OpenTelemetry.