Prompt caching savings

Cached Input Pricing Calculator

Use this cached input pricing calculator to estimate savings when part of your prompt is reused across many LLM requests.

Calculate Cached Input Pricing Cost

Estimate how cached input pricing can reduce LLM API costs for repeated system prompts, instructions and shared context.

No API key required. Your transcript stays in your browser.

Workload type

Provider

Model

Paste your prompt, transcript or content

Characters: 0Words: 0Estimated input tokens: 0Estimated token count

Output type

Output tokens are estimated based on the selected summary type and input length.

Monthly Interactions

Number of AI summarization requests expected each month.

Advanced Settings

System Instruction Tokens

Tokens used by the system prompt or recurring instructions in every interaction.

Cached Input Percentage

Percentage of input tokens expected to use provider prompt caching.

Paste sample content above to compare model costs.

Cached input helps repeated prompts

Some models offer lower pricing for cached or reused input tokens. This matters for apps that send the same system instructions, policy text or tool schema on many requests.

Enter stable prompt content as system instruction tokens and adjust cached input percentage in Advanced Settings to estimate the impact.

Reusable input	Good caching candidate?	Reason
System prompt	Yes	Often repeated on every request
Tool schema	Yes	Usually stable across calls
User message	No	Usually different each request