What is context engineering?
Select and manage the information available to a model.
AI Engineering tool
Estimate how instructions, retrieved material, and reserved output consume an AI context window.
Runs in your browser with editable illustrative assumptions. It does not call a model, send entered content to a server, or produce a current market quote.
Interactive calculator
Your request uses 19,200 tokens before any conversation history or tool output is added.
This is a planning budget, not a provider-specific guarantee. History, tool results, hidden reasoning, and provider limits can change the usable allowance.
Starting values are illustrative defaults you can edit — not live ComputeTape Market benchmark prices. Replace them with a real quote.
How to use it
Reserve output before filling the input budget. A large context window is not a reason to send every document, history item, or tool result.