Will it fit the context window?
Paste a long document, a codebase dump or a chat history and see, for every model, how much of the context window it fills once the answer is added, and by how much it is over.
How to use the context window checker
- Paste the full text you plan to send, or drop a file on the editor.
- Set the expected answer length; it counts towards the window too.
- Check the bars in the Context window column.
- Shorten the text, or pick a model whose window fits.
What you get
- Window use as a bar for every model
- How many tokens over the limit, when it does not fit
- Answer length included in the check
- Models without a published window marked as such
About the context window checker
Leave room for the answer
The context window holds both what you send and what the model writes. A prompt that fills the window leaves no room for a reply, so the check adds your expected answer length.
Bigger is not always better
Models can miss details in the middle of very long inputs, and long inputs cost more. Send the parts that matter when you can.
Frequently asked questions
- What is a context window?
- The maximum number of tokens a model can consider at once: your instructions, the material you include, the conversation so far and its own answer.
- Are these limits exact?
- They are the published limits; some models have smaller limits on certain plans. The token count is exact for OpenAI models and estimated for others.
- Is my text uploaded?
- No. Everything runs in your browser.