Check whether the whole job fits before you paste it.
Reserve output space and a safety margin, then see whether your instructions and source material fit inside the documented context window.
- Outcome
- A comfortable, tight or over-limit verdict with exact remaining capacity
- Time
- Under 1 minute
- Privacy
- Local by default; optional private save
You choose what to keep.
Calculations run locally without provider requests or input analytics. Refreshing clears working values. Only “Confirm & save snapshot” sends the displayed numbers/choices and your title to private, encrypted account storage. Nothing is automatically saved.
Build a context budget.
The example limit is not a claim about any model. Replace it with the current documented limit for your exact model and mode.
Comfortable fit
80,800 usable tokens remain after the requested output and safety reserve.
- Usable context
- 1,08,800
- Required
- 28,000
- Safety reserve
- 19,200
- Use of budget
- 25.7%
If it is tight
- Remove duplicated conversation history and irrelevant source material.
- Split the work at a stable checkpoint instead of truncating the expected output.
- Count with the tokenizer used by the exact model when precision matters.
Keep this decision
Saving is optional. Calculations are free; signed-in users can keep a private snapshot. Premium and Team can compare snapshots and export briefs.
My saved calculations →Estimate first. Verify the changing facts next.
The utility makes its assumptions and arithmetic visible. Before spending money or changing a live system, replace example values with current first-party information and preserve a rollback path.
- 01Enter the exact jobUse real workload values, not an aspirational maximum.
- 02Read the boundarySee what the calculator deliberately does not infer.
- 03Verify at sourceConfirm current limits, prices, records or plan terms.
- 04Make a controlled decisionRecord the owner, evidence and rollback before action.