Live Gemini AI Usage & Credit Optimization

Real token consumption and cost telemetry from PostgreSQL (36 recorded API calls).

Total Tokens Consumed

18,000

36 API calls

Estimated Token Cost

$0.0140

Billed to Google AI Studio

Avg Latency per Request

15ms

Observed API latency

Cached Tokens

Context cache savings

Live Usage Breakdown by Model Tier

gemini-2.5-flash

7,000 tokens • 14 requests

$0.0010

gemini-3-flash-preview

4,000 tokens • 8 requests

$0.0008

gemini-3.1-pro-preview

5,000 tokens • 10 requests

$0.0119

gemini-3.1-flash-lite

2,000 tokens • 4 requests

$0.0004