← All Tools
Context-Window Fit Checker
Paste a prompt — or drop a stack of files — and instantly see which model context windows can hold it, leaving room for the response.
100% client-side. Files are read by your browser via
FileReader and never leave your device. No data is sent anywhere.
Add files
Drop text files here
or · .txt, .md, .json, .csv, .log, .py, .js, .go etc
Response budget
Reserve room for the model's reply. Most chat sessions need 500-2000 tokens; agentic / verbose JSON outputs may need 4-8k.
tokens reserved
Fit by model
| Model | Context | Fill (input + budget) | Verdict |
|---|
What "fits" really means
- Input + reserved output must fit within the advertised context. We add the response budget to the input estimate before comparing.
- Effective recall degrades long before the hard limit. Anthropic and Google publish "needle-in-a-haystack" benchmarks showing usable recall well below 100% for very long contexts.
- Costs scale linearly with input tokens. Use the Token Counter tool to price the call.
- Some vendors charge more for prompts above a threshold (e.g. Gemini 2.5 Pro > 200k tokens) — double-check the pricing tier you'll hit.