get aggregated session analytics
Returns aggregated latency analytics across sessions — percentile distributions (p50/p90/p95/p99/max/avg) for each stage of the transcription → LLM → TTS → first-audio path, interruption and error rates, tool call outcomes, and a sample of the slowest turns. Only sessions where Anam runs the conversational pipeline (turnkey, custom LLM and ElevenLabs agent sessions) produce analytics reports; LiveKit and audio-passthrough sessions count toward sessionCount but never carry analytics. Defaults to the last 24 hours; the maximum range is 31 days. At most the 1000 most recent report-bearing sessions are aggregated per request (the truncated field reports when this cap was hit) — narrow the time range or filters to analyse busier periods exhaustively.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Query Parameters
Start of the time range (ISO 8601). Defaults to 24 hours before to.
End of the time range (ISO 8601). Defaults to now.
Only include sessions for this persona.
Only include sessions minted by this API key.
Only include sessions whose client label matches exactly.
Only include sessions of this type.
turnkey, custom_llm_server, custom_llm_client, livekit, elevenlabs_agent Response
Successfully computed aggregate analytics
Echo of the applied filters.
Total sessions matching the filters in the range, whether or not they produced an analytics report.
Sessions whose analytics report was aggregated (capped at the 1000 most recent).
True when more report-bearing sessions matched than the scan cap; only the most recent 1000 were aggregated.
Percentile distributions per latency stage, computed across all turns.
The slowest turns per headline latency metric, for jumping straight to problem sessions.

