Private AI planning tool
Context Window Calculator
Check whether input tokens plus reserved output fit a model context window, and see remaining capacity and maximum-output warnings.
Provider limits verified 2026-07-29. Kimi's public model pages do not state a separate maximum-output limit, so those presets only check the total context window.
Planning a model context budget
A context window must hold both the request input and the generated response. Reserving output space before filling the prompt helps prevent truncation or rejected requests.
The maximum output limit is checked separately because it may be much smaller than the total context window. Custom mode lets you evaluate another model without waiting for this page's built-in list to change.
Does this upload my files?
No. Everything on this page runs locally in your browser, so your files are never uploaded to a conversion server. Close the tab and nothing is left behind.
After any required processing engine has loaded, repeated conversions can keep working offline. You can verify the claim with the site's reproducible browser privacy audit.
FAQ
What should reserved output include?
Reserve the maximum response size your application should allow. The input plus reserved output must fit inside the model's context window.
Why check the maximum output separately?
A request can fit inside the total context window while still requesting more output than the model permits in one response.
Does this call the selected model?
No. It only compares the numbers you enter against locally stored model limits.