You're offline

Some features may be unavailable. Changes will sync when you reconnect.

Platform Metrics

Performance, cost, and reliability across all your agents

Total API Calls

7,570

+12% vs last period

Total LLM Cost

$14.52

+8% vs last period

Avg Latency (P95)

1,443ms

-5% vs last period

Error Rate

0.42%

-18% vs last period

API Calls & Cost Over Time

Model Mix

gpt-4o-mini
48%
claude-3-haiku
22%
gemini-flash
18%
gpt-4o
8%
claude-3-sonnet
4%

P95 Latency (ms)

Error Count by Day