Will It Fit?

Paste your prompt and see instantly whether it fits inside each model's context window — before you hit the API. Everything is counted in your browser; your text never leaves this page.

Your text

14 words · 86 characters

Reserve for the answer: 2,000 tokensThe model needs room to reply. Bigger answers need a bigger reserve.

Your text

tokens (+2,000 reserved)

Fits in

29 / 29

models checked

Smallest window that fits

Claude Haiku 4.5

200K context

Model	Context window	Usage	Status
Claude Haiku 4.5 Anthropic	200K	1.0%	Fits · 198,000 left
GPT-5.4 Mini OpenAI	400K	0.5%	Fits · 398,000 left
GPT-5.4 Nano OpenAI	400K	0.5%	Fits · 398,000 left
Claude Fable 5.1 Anthropic	1M	0.2%	Fits · 998,000 left
Claude Mythos 5.1 (limited availability) Anthropic	1M	0.2%	Fits · 998,000 left
Claude Fable 5 Anthropic	1M	0.2%	Fits · 998,000 left
Claude Sonnet 5 Anthropic	1M	0.2%	Fits · 998,000 left
Claude Mythos 5 (limited availability) Anthropic	1M	0.2%	Fits · 998,000 left
Claude Opus 5 Anthropic	1M	0.2%	Fits · 998,000 left
Claude Opus 4.8 Anthropic	1M	0.2%	Fits · 998,000 left
Claude Sonnet 4.6 Anthropic	1M	0.2%	Fits · 998,000 left
Gemini 3.8 Flash Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 3.7 Flash Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 3.6 Flash Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 3.5 Flash Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 3.5 Flash-Lite Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 3.1 Pro Preview Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 3.1 Flash-Lite Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 2.5 Pro Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 2.5 Flash Google	1,048K	0.2%	Fits · 1,046,000 left
Gemini 2.5 Flash-Lite Google	1,048K	0.2%	Fits · 1,046,000 left
GPT-6 Astra OpenAI	1,050K	0.2%	Fits · 1,048,000 left
GPT-5.6 Sol OpenAI	1,050K	0.2%	Fits · 1,048,000 left
GPT-5.6 Terra OpenAI	1,050K	0.2%	Fits · 1,048,000 left
GPT-5.6 Luna OpenAI	1,050K	0.2%	Fits · 1,048,000 left
GPT-5.5 OpenAI	1,050K	0.2%	Fits · 1,048,000 left
GPT-5.5 Pro OpenAI	1,050K	0.2%	Fits · 1,048,000 left
GPT-5.4 OpenAI	1,050K	0.2%	Fits · 1,048,000 left
GPT-5.4 Pro OpenAI	1,050K	0.2%	Fits · 1,048,000 left

Token counts use a GPT-style tokenizer (cl100k_base) as an estimate — Claude and Gemini tokenizers split text slightly differently. Counts include your reserved output tokens.

Context window FAQ

Will my prompt fit in the context window?

Paste your text above and the checker counts its tokens, adds your reserved output tokens, and compares the total against 29 models' context windows. Green means it fits; red shows exactly how many tokens over it is.

What counts toward the context window?

Everything the model sees: your system prompt, conversation history, the text you paste, plus the tokens you reserve for the answer. Use the reserve slider to leave room for the reply.

Why do token counts differ between models?

Each model family uses its own tokenizer, so the same text splits into slightly different token counts. This checker uses a GPT-style tokenizer as a close estimate; Claude and Gemini counts may vary a little.

What happens if my text does not fit?

Most APIs reject the request with a context-length error. Some truncate the oldest content instead, which can silently remove your system prompt or early conversation turns.

How many tokens should I reserve for the output?

It depends on the task. A short classification needs a few hundred; a long summary or code generation can need several thousand. The default reserve is 2,000 tokens.

Does this tool upload my text?

No. Token counting runs in a Web Worker inside your browser. Your text never leaves your device.