Interactive LLM API Cost Calculator

Estimate your monthly AI API spending based on query volume, token length, and prompt caching ratios. Compare costs instantly across 8+ frontier and open-weights models.

⚙️ Usage Parameters

Primary Model

Input Tokens / Query 5,000

Output Tokens / Query 2,000

Queries / Day 500

Working Days / Month 22

Prompt Caching Hit Rate 50%

Estimated Total Spend

$2.80

~$0.13 / day

Uncached Input Cost: $0.41

Cached Input Savings: -$0.18

Output Token Cost: $2.57

💡 Optimization Insight: Gemini 3.1 Flash provides 2M token context at the lowest industry price point.

Model Cost Comparison Matrix

Model	Input / Output (1M)	Est. Monthly Total	Vs Selected