Calculator
200K context surcharge calculator
How the >200K (and OpenAI >272K) context cliff reprices one large request: base rates versus long-context rates.
Estimated cost (notional)
$4.80
Long-context rates apply; $2.50 at base rates
How the estimate works
Enter the token mix of ONE request. When input, cache reads, and cache writes together cross the model's published threshold (200K for Grok, Gemini, and Claude Sonnet 4.5; 272K for OpenAI), the WHOLE request is billed at the long-context rates — the same rule JP the Cat applies to each real turn. Totals summed across many turns never trip the surcharge on their own.
Common questions
- Is this calculator accurate?
- It uses the same published per-token rates JP prices real usage at, so it is close — but it cannot know your exact cache reuse, which is the biggest swing factor.
Track your real cost with JP the Cat
A live menu-bar total, priced to the cent from your local logs — including the cache-write split most tools miss.
Download MeowPrefer Homebrew? Install the same signed, notarized app from JP's public tap.
brew tap 8bittts/jpthecat
brew trust 8bittts/jpthecat
brew install --cask jpthecat