Search anything... (Ctrl + K)
Search...
Ctrl K
AI Usage & Tokens Consumption
Granular telemetry of language model inferences, input tokens, cached tokens, and vector lookups.
11.2M
Total Input Tokens
$112.00 billed
7.2M
Total Output Tokens
$144.00 billed
$412.50
KV Cache Hit Savings
58.4% cache hit
142,500
Vector Search Queries
$14.25 billed
Daily Token Volume (Last 30 Days)
Tracking daily input vs output generation across all running agent instances.
Input Tokens
Output Tokens
Daily Average: 613,330 tokens / day
Peak Day: Oct 31 with 1,240,000 tokens during Q4 campaign blast
Model Consumption & Cost Breakdown
Detailed API cost attribution per foundational LLM architecture.
| Model Provider & Architecture | Total Requests | Prompt Tokens | Completion Tokens | Cache Hit % | Monthly Spend | Actions |
|---|---|---|---|---|---|---|
|
OA
OpenAI GPT-4o
gpt-4o-2024-08-06 • Tier 1 Flagship
|
84,200 | 5.8M | 3.2M | 64.2% | $164.20 | |
|
OA
OpenAI GPT-4o-mini
gpt-4o-mini • Fast Intent Triage
|
148,500 | 3.1M | 2.4M | 72.1% | $24.80 | |
|
ANT
Anthropic Claude 3.5 Sonnet
claude-3-5-sonnet • Coding & Complex Logic
|
42,100 | 1.8M | 1.2M | 51.0% | $82.40 | |
|
ANT
Anthropic Claude 3 Haiku
claude-3-haiku • Sub-second sentiment
|
65,400 | 850k | 620k | 68.5% | $9.60 | |
|
VEC
Text-Embedding-3-Large
3,072 dimensions • Pinecone vector sync
|
142,500 | 4.2M | — | 100% Retr | $14.25 |