AI Telemetry

Aggregate model usage, token consumption, latency, cost, and quality trends across all LLM requests.

Period:
Total Requests
in period
Total Tokens
input + output
Total Cost
USD estimated
Avg Latency
seconds per call
Cache Hit Rate
semantic cache
Daily Token Consumption
Daily Cost (USD)
Latency by Provider (p50 / p95)
Cache Hit Rate (%)
Provider Distribution
Answer Quality Trend
Query Class Distribution
Provider Summary
Provider Requests Total Tokens Cost (USD) p50 Latency p95 Latency
Loading…