Console/analytics
Workspace: ws_devtinker

Workspace Usage & Analytics Telemetry

Real-time API request volumes, token consumption, and P50/P95/P99 latency distribution.

Total Requests
0

Across active workspace projects

Total Token Consumption
0

Hybrid vector + graph embeddings

Average Latency
0 ms

Sub-15ms RediSearch semantic cache active

Latency Percentile Breakdown

P50 Latency (Median):
14 ms

RediSearch semantic cache hit

P95 Latency:
38 ms

pgvector HNSW hybrid search

P99 Latency:
85 ms

2-Hop Neo4j graph traversal

Daily Request Telemetry

DateAPI RequestsToken VolumeAvg Latency