Analytics
Deep dive into your AI gateway usage, costs, and performance
Total Requests
47,420
+18%
Avg Latency
0.83s
-12%
Total Tokens
1,037,484
+23%
Cost Savings
€41
Request Volume by Model
Cost Savings Over Time
Model Usage Distribution
OpenAI GPT-5.2
38%€6,993
Anthropic Claude 4.6
28%€5,152
Meta Llama 4
18%€3,312
Google Gemini 3
16%€2,944
Latency by Model (ms)
Risk Level Trend
Top Request Categories
Financial decisions80085 req
Compliance documentation58008 req
Customer communication42069 req
Insurance processing31337 req
Healthcare assessments13370 req
Document analysis8008 req
Support operations6969 req
Credit scoring4200 req
Research analytics1337 req
Legal document analysis420 req
Investment analysis404 req
Translation69 req
Regulatory analysis42 req
Performance Summary
99.7%
Success Rate
3 errors in 47k requests
0.78s
Avg Response Time
Gateway overhead: 47ms
23%
Cache Hit Rate
11,204 cached responses
99.99%
Uptime (30d)
4.3s total downtime