Context windows · July 2026

How much fits in each model'scontext window?

A context window is the total amount of text (measured intokens) a model can read and write in a single request. Bigger windows mean you can feed in longer documents, entire codebases, or whole books — and still get a response. Here is how the major models compare in 2026.

All models compared

Values calculated from each model's context window using the standard ratio of 1 token ≈ 0.75 English words, 500 words per page, and ~90,000 words (120K tokens) per novel.

ModelContextWordsPagesNovelsEquivalent
GPT-5.6 Sol1.05M787,5001,5748.8~8.75 novels — the Bible + Harry Potter
GPT-5.6 Terra1.05M787,5001,5748.8~8.75 novels — the Bible + Harry Potter
GPT-5.6 Luna1.05M787,5001,5748.8~8.75 novels — the Bible + Harry Potter
Claude Fable 51M750,0001,4998.3~8 novels — nearly the full Bible
Claude Opus 4.81M750,0001,4998.3~8 novels — nearly the full Bible
Claude Sonnet 51M750,0001,4998.3~8 novels — nearly the full Bible
Gemini 3.1 Pro1M750,0001,4998.3~8 novels — nearly the full Bible
Gemini 3.5 Flash1M750,0001,4998.3~8 novels — nearly the full Bible
Gemini 3 Flash1M750,0001,4998.3~8 novels — nearly the full Bible
GPT-5.5 Pro400K300,0006003.3~3 novels — one War and Peace
GPT-5.5400K300,0006003.3~3 novels — one War and Peace
Claude Haiku 4.5200K150,0003001.7~1.7 novels

What each context window holds

1.05M tokens

GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna

  • 787,500 words
  • 1,574 single-spaced pages
  • 8.8 average novels
  • The entire Bible + most of Harry Potter

1M tokens

Claude Fable 5, Claude Opus 4.8, Claude Sonnet 5, Gemini 3.1 Pro, Gemini 3.5 Flash, Gemini 3 Flash

  • 750,000 words
  • 1,499 single-spaced pages
  • 8.3 average novels
  • Nearly the entire King James Bible

400K tokens

GPT-5.5 Pro, GPT-5.5

  • 300,000 words
  • 600 single-spaced pages
  • 3.3 average novels
  • About one War and Peace

200K tokens

Claude Haiku 4.5

  • 150,000 words
  • 300 single-spaced pages
  • 1.7 average novels
  • Roughly 1.5 copies of The Great Gatsby

Frequently asked questions

What is a context window?

The context window is the maximum number of tokens a model can process in a single request, including both your input (the prompt, documents, images you send) and the model's output (the response it generates). Think of it as the model's working memory — everything it can "see" at once.

Which AI model has the largest context window?

As of July 2026, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna have the largest context windows at 1.05M tokens (1,050,000 tokens). That fits roughly 787,500 words — equivalent to about 8.8 average novels.

Can I use the full context window?

Not entirely for input, because the model's output tokens count against the context window too. If a model has a 1M-token context window and you need a 2,000-token response, your input is effectively capped at 998,000 tokens. Most providers also set a separate maximum output length (typically 8K–32K tokens) that is smaller than the full window.