Free tool / build
Will it fit in memory?
Paste a document and see which models can read it in one go, how much room is left and how many pieces you would need.
No sign-up / runs in your browser
Check the window before you hit the wall.
The window covers your prompt and the answer together. Some models cap the reply lower than this.
Paste your text to see which models can read it in one go.
Context windows are the maximum a model accepts, taken from the same price list as our other tools and checked 17 October 2026. Models read less reliably near the limit, so “tight” starts at 80% used. Token counts are exact for OpenAI models and estimated (about ±15%) for others.
How it works
Three steps, no sign-up.
- 01
Paste text or enter a size
Paste the document, or type a token count you already know.
- 02
Set room for the reply
The context window covers your prompt and the answer together, so leave space for the reply.
- 03
Read the table
See which models fit, which are tight, and how many pieces a too-big document needs.
Questions people ask
What is a context window?
The largest amount of text, measured in tokens, that a model can take in one request. It includes your prompt, the conversation so far, tool results and the model's own answer.
Why leave room for the reply?
The window is shared. If your prompt fills it, the model has no space left to answer, and the request fails or the answer is cut off.
Is a bigger window always better?
Larger windows cost more to fill and models can miss details buried in the middle of very long inputs. Often it is better to retrieve only the relevant parts.
What should I do if my document does not fit?
Split it into pieces, summarise older parts, or retrieve only the relevant sections. The table shows how many pieces each model would need.
How do I know when my agent's prompt is growing?
Tracify records the size of every call, so you see a prompt creeping toward the limit before it fails.
More free tools
- Agent log checker
Paste a log or trace. See where it failed, what was slow and what wasted tokens.
- Token counter
Paste text. See the token count and price on GPT, Claude, Gemini and Llama.
- Model price comparison
Every model's price in one table, plus what your app costs per month on each.
- Prompt cost checker
Paste a prompt. Get a shorter, cheaper version and what it costs on each model.
Now measure the real thing.
Send a first trace and see the true cost, speed and failures of every run.