LLM Cost Optimization

Compare input and output pricing across Gemini 1.5 Pro, Claude 3.5 Sonnet, and GPT-4o. Adjust the sliders to see how prompt caching affects your API budgets.

LLM Cost & Caching Calculator

Input Tokens50,000

Output Tokens10,000

Prompt Cache Match50%

Gemini 1.5 ProGoogle

Standard Call$0.1125

With Prompt Caching$0.0891

Saves $0.0234 (21% Off)

Claude 3.5 SonnetAnthropic

Standard Call$0.3000

With Prompt Caching$0.2325

Saves $0.0675 (23% Off)

GPT-4oOpenAI

Standard Call$0.4000

With Prompt Caching$0.3375

Saves $0.0625 (16% Off)