Application-active

Total API Calls

125,430

+12.5%

Tokens Used

2.4M

+8.3%

Total Cost

$342.50

-8.2%

Avg Response Time

245ms

-15ms
Token Usage Over Time
Model Distribution
API Usage by Endpoint
Endpoint Requests Avg Tokens Avg Latency Cost Status
/chat/completions 68,240 1,850 320ms $185.40 Active
/embeddings 34,120 512 85ms $42.30 Active
/images/generations 8,450 -- 2,400ms $67.60 Active
/audio/transcriptions 5,820 -- 1,200ms $23.10 Active
/moderations 6,300 340 45ms $3.80 Active
/fine-tuning 2,500 4,200 -- $20.30 Rate Limited
Cost by Model
Recent API Calls
Timestamp Model Endpoint Input Tokens Output Tokens Latency Cost Status
2 min ago GPT-4o /chat/completions 1,240 856 285ms $0.032 200
5 min ago Claude Sonnet /chat/completions 2,100 1,430 410ms $0.045 200
8 min ago GPT-4o Mini /chat/completions 890 620 145ms $0.004 200
12 min ago Gemini Pro /embeddings 512 -- 62ms $0.001 200
15 min ago GPT-4o /chat/completions 3,500 2,100 520ms $0.078 200
18 min ago Claude Sonnet /chat/completions 4,200 -- -- $0.000 429
22 min ago DALL-E 3 /images/generations -- -- 2,340ms $0.040 200
25 min ago GPT-4o /moderations 340 12 38ms $0.001 200
30 min ago Claude Sonnet /chat/completions 1,800 1,250 380ms $0.038 200
35 min ago GPT-4o Mini /embeddings 256 -- 45ms $0.0005 200