Home › Free Tools › Prompt Caching Savings Calculator
Free toolPrompt Caching Savings Calculator
Caching bills the repeated start of your prompts at a fraction of the input price. Estimate what it's worth on your traffic.
Defaults use GPT-6.1 Sol's list prices. Anthropic charges cache writes at 1.25x the base price for 5 minutes and 2x for 1 hour; set the write premium to match.
Prices to use
- GPT-6.1 Sol: $2.00 input, $0.10 cached.
- Claude Sonnet 5.5: $2.00 input, $0.10 cache reads, writes 1.25x or 2x.
- Gemini 3.8 Flash: $0.75 input, $0.075 cached, until January 1, 2027.
More in the LLM pricing comparison. If your hit rate is low, read why caching isn't working.
Frequently asked questions
How much does prompt caching save?
Cached input costs a fraction of the normal input price, such as $0.10 vs $2.00 on GPT-6.1 Sol. The saving depends on how much of your input repeats.
Do cache writes cost extra?
On Anthropic, yes: 1.25x the base input price for a 5-minute cache and 2x for a 1-hour cache.
Want us to find your 20%?
Book a free 15-minute API cost teardown. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.
Get a Free 15-Minute API Cost Teardown