Prompt Caching Calculator | Claude and OpenAI

Prompt caching calculator for Claude and OpenAI APIs. Compare cache write, cache read and uncached input costs, and find your break-even hit rate. Free.

Also known as: prompt caching calculator · prompt caching cost calculator · claude prompt caching pricing · anthropic prompt caching cost · openai cached input pricing · cache write vs cache read cost · prompt caching break even · llm prompt caching savings · cached input token pricing

api and http tools

finance calculators

calculators

Model and Traffic

min 512 tokens

Model

Cache lifetime

Cached prefix tokens

system prompt, tools, documents

Uncached input tokens

the part that changes per request

Output tokens

per response

Requests per day

sharing the same prefix

Cache hit rate (%)

requests that read the cache

US-only or regional data residency

Adds 10% to every token price: Claude's inference_geo on 4.6 and later models, OpenAI's regional processing endpoints.

Savings

Monthly cost with and without caching, the cost of a hit and a miss, and the hit rate where caching starts paying off will appear here.

About Prompt Caching Calculator

A prompt caching calculator shows what caching a long system prompt, tool list or document set actually saves on an LLM API bill. Cache writes cost more than normal input and cache reads cost a small fraction of it, so the answer depends on how often requests hit the cache. Enter your prompt sizes, traffic and hit rate to compare monthly cost with and without caching on Claude and OpenAI models.

Key Features

List prices for current Claude and OpenAI models, including cache writes for every cache lifetime
Monthly cost with and without caching, plus the cost of a single hit, miss and blended request
Break-even hit rate: the share of requests that must hit the cache before caching pays off
Warns when a prefix is below the model's minimum cacheable length and silently will not cache
Handles Claude Haiku 5.5's higher rates for prompts over 100,000 tokens and the 1.1x US-only inference price
Custom mode with hourly storage pricing for Gemini, Bedrock or any other provider

Use Cases

Decide whether a 20,000-token support-bot system prompt is worth caching at 5,000 requests a day
Choose between Claude's 5-minute and 1-hour cache, or OpenAI's 30-minute and 12-hour cache
Show a finance team what a 90% cache hit rate saves before an agent goes to production
Estimate the cost of a RAG app that reuses the same retrieved documents across a session
Compare the cached cost of Claude Opus 5.5 and GPT-6.1 Sol for the same coding agent
Check that a short prompt clears the minimum cacheable length before you add cache_control

Supported Formats

Claude API

OpenAI API

US dollars per 1M tokens

30-day month

Related Keywords

prompt caching calculator

prompt caching cost calculator

claude prompt caching pricing

anthropic prompt caching cost

openai cached input pricing

cache write vs cache read cost

prompt caching break even

llm prompt caching savings

cached input token pricing

How much does prompt caching save?

For a long, stable prefix with a high hit rate, most of the input bill. On most Claude models a cache read costs 10% of the normal input price (5% on Claude Opus 5.5 and Sonnet 5.5, 2.5% on Fable 5.1), while a 5-minute cache write costs 1.25x and a 1-hour write 2x. OpenAI's newest models charge 1.25x for a 30-minute write and 2.5x for a 12-hour write, with reads at 10% (5% on GPT-6.1 Sol). So a 5-minute cache pays for itself once roughly one request in five reads it, and every hit after that is close to free. The savings only apply to the cached prefix: output tokens and the part of the prompt that changes on every request are billed normally. Hit rate is the number to watch. Any byte that changes in the prefix, such as a timestamp in the system prompt or tools listed in a different order, turns a hit into a full-price write.

Privacy & Security

All processing happens locally in your browser. Your data never leaves your computer, ensuring complete privacy and security.

Liked this tool?

DevToolLab is free to use. If this calculator saved you some time today, please consider supporting our work.

Buy us a coffee ☕

Frequently asked questions

What is Prompt Caching Calculator used for?

Prompt caching calculator for Claude and OpenAI APIs. Compare cache write, cache read and uncached input costs, and find your break-even hit rate. Free.

Is Prompt Caching Calculator free to use?

Yes. Prompt Caching Calculator is completely free with no usage limits, and there is no paid tier required to use it.

Do I need an account to use Prompt Caching Calculator?

No. Prompt Caching Calculator works immediately in your browser with no signup, login, or email address required.

Related Tools

Percentage Calculator | Find Percentages Online Free

Calculate percentages easily: find X% of Y, what percent X is of Y, percentage change, and increase/decrease by percentage.

encoding and decoding tools

math calculators

Age Calculator | Calculate Exact Age from Birthday Online

Calculate your exact age in years, months, days, hours, and minutes. Find your zodiac sign, day of birth, and countdown to next birthday.

cron and scheduling tools

date and time tools

Date Duration Calculator | Days Between Dates Online Free

Calculate the duration between two dates or add/subtract time periods from a date. Count workdays, weekends, and total days.

date and time tools

math calculators

More Tools You Might Like

Pastebin Online | Share Code & Text Snippets Free

Popular

Share code snippets, logs, and text with a shareable link. Syntax highlighting for 30+ languages, expiration controls, and password protection for Pro users.

text tools

password and key generators

math calculators

utilities

Use Tool

URL Tracker & Link Shortener | Track Clicks

Popular

Create short, trackable URLs with detailed click analytics. Track visitor location, devices, referrers, and more. Password protection & QR codes included.

text tools

password and key generators

url and link tools

networking

Use Tool

Webhook Receiver & Inspector | Test HTTP Webhooks

Popular

Generate a unique URL to easily test, receive and inspect HTTP webhooks in real-time. View request headers, query parameters, JSON payloads, and more.