Free online tools
LLM context window calculator
Paste a text or enter the size of a document in pages, words or lines of code. You will see how much of the context window it takes and which models can hold it.
Estimated tokens: …
| Model | Window (tokens) | Used | Fits |
|---|---|---|---|
| GPT-5 nano | 400,000 | … | |
| GPT-5.4 | 400,000 | … | |
| Claude Sonnet | 1,000,000 | … | |
| Gemini Pro | 1,000,000 | … |
Context windows are approximate. The token count for Claude and Gemini is an approximation.
Your data never leaves your browser. Nothing is sent to a server.
How to use it
- Choose how to enter the data: pasted text, pages, words or lines of code.
- Paste the text or enter a number.
- Read the token count and the share of the window for each model.
- If it does not fit, split the document or use a model with a larger window.
What a context window is
It is the maximum number of tokens a model can see at once: your instructions, pasted documents, the conversation history and its own reply. Past the limit the request is rejected or the older part of the conversation is dropped.
Leave room for the reply
The window also includes the generated reply, so a document that fills 95 percent of it leaves the model little space. Keep a reserve of at least a dozen percent of the window, and more for long answers.
An estimate, not a measurement
The pages, words and lines of code modes rely on averages: five hundred words per page and about one and a half tokens per word. That gives an order of magnitude. For an exact value, paste the text.
Frequently asked questions
Need more than a tool?
If there is a bigger project behind it, a website, a shop or an app, describe it in a short brief. We reply with specifics and no obligation.
Describe your project