Queries Processed
847.2K
+12.3%vs last 24h
Avg Latency (P95)
142ms
-8.1%vs last 24h
Cost / 1K Queries
$2.41
-15.2%vs last 24h
RAG Accuracy
94.7%
+2.1%vs last 24h
Deployed Models
6 active · 2 staginggpt-4-turbo-rag-v3active
RAG + Generation1,247 qps
134ms · 94.7%
embed-v3-customactive
Embedding8,412 qps
12ms · —
classifier-intent-v2active
Classification3,891 qps
28ms · 97.2%
summarizer-legal-v1staging
Summarization— qps
892ms · 91.3%
reranker-cohere-v2active
Reranking4,102 qps
45ms · 96.1%
Activity Feed
RAG pipeline retrained
2m ago
Embedding index rebuilt (2.4M docs)
14m ago
Anomaly detected: latency spike +340ms
31m ago
A/B test promoted: reranker-v2
1h ago
Data pipeline: 847K records ingested
2h ago
Model drift alert: classifier-intent
3h ago
GPU cluster scaled to 8 nodes
5h ago
Query Throughput (24h)
Queries Tokens
294K queries · 00:00
414K queries · 01:00
258K queries · 02:00
469K queries · 03:00
616K queries · 04:00
662K queries · 05:00
534K queries · 06:00
745K queries · 07:00
856K queries · 08:00
800K queries · 09:00
699K queries · 10:00
874K queries · 11:00
810K queries · 12:00
837K queries · 13:00
681K queries · 14:00
626K queries · 15:00
754K queries · 16:00
892K queries · 17:00
819K queries · 18:00
718K queries · 19:00
782K queries · 20:00
846K queries · 21:00
883K queries · 22:00
810K queries · 23:00