Context windows, explained

What is a context window — and how big is yours?

A context window is the maximum number of tokens an AI model can process in a single request. It includes your instructions, the conversation, retrieved documents, tool results, and the model’s reply. Current models range from 200,000 to about 1,050,000 tokens — roughly one book to ten.

Free · no sign-upRegistry re-verified Aug 16, 2026.23 models tracked
Human-scale equivalents

What actually fits in 200K to 1M tokens

Context sizeEnglish wordsWhat that is
2,000 tokens≈ 1,500 wordsa long email thread or meeting notes
8,192 tokens≈ 6,100 wordsa lengthy technical guide
32,000 tokens≈ 24,000 wordsa whitepaper with appendices
128K tokens (131,072)≈ 98,000 wordsa full novel
200K tokens≈ 150,000 wordsa 300–500 page book — Claude Haiku/Sonnet-class window
500K tokens≈ 375,000 wordsa large codebase review — Grok-class window
1M tokens≈ 750,000 wordsabout ten novels — current flagship windows

Word equivalents use the standard 1 token ≈ 0.75 words planning ratio. The window is shared: instructions, history, evidence, and the answer all draw from the same budget.

The living registry

Every model’s context window, Aug 16, 2026

ModelProviderContext windowMax outputLong-context pricing
GPT-5.6 SolGPT-5.6OpenAI1,050,000 (1.05M)128,000Tiers above 272K
GPT-5.6 TerraGPT-5.6OpenAI1,050,000 (1.05M)128,000Tiers above 272K
GPT-5.6 LunaGPT-5.6OpenAI1,050,000 (1.05M)128,000Tiers above 272K
Gemini 3.1 Pro PreviewGemini 3.1Google1,048,576 (1.05M)65,536Tiers above 200K
Gemini 3.6 FlashGemini 3.6Google1,048,576 (1.05M)65,536Standard rates
Gemini 3.7 FlashGemini 3.7Google1,048,576 (1.05M)65,536Standard rates
Gemini 3.5 Flash-LiteGemini 3.5Google1,048,576 (1.05M)65,536Standard rates
Kimi K3Kimi K3Moonshot1,048,576 (1.05M)Standard rates
DeepSeek V4 ProDeepSeek V4DeepSeek1,048,576 (1.05M)384,000Standard rates
DeepSeek V4 FlashDeepSeek V4DeepSeek1,048,576 (1.05M)390,000Standard rates
Claude Fable 5Fable 5Anthropic1,000,000 (1M)128,000Standard rates
Claude Mythos 5Mythos 5Anthropic1,000,000 (1M)128,000Standard rates
Claude Opus 5Opus 5Anthropic1,000,000 (1M)128,000Standard rates
Claude Sonnet 5Sonnet 5Anthropic1,000,000 (1M)128,000Standard rates
Qwen 3.8 MaxQwen 3.8Alibaba1,000,000 (1M)131,000Standard rates
Llama 4 MaverickLlama 4Meta1,000,000 (1M)Standard rates
Grok 4.6Grok 4.6xAI500,000 (500K)128,000Tiers above 200K
Grok 4.5Grok 4.5xAI500,000 (500K)128,000Tiers above 200K
Kimi K2.7 CodeKimi K2.7Moonshot262,144 (262K)Standard rates
Mistral Large 3Mistral LargeMistral262,144 (262K)Standard rates
Command ACommand ACohere256,000 (256K)64,000Standard rates
Claude Haiku 4.5Haiku 4.5Anthropic200,000 (200K)64,000Standard rates
Sonar ProSonarPerplexity200,000 (200K)Standard rates

Windows verified from provider documentation. Long-context tiers apply higher per-token rates above the listed input size — the context-window calculator applies them automatically.

Plain-English answers

Context window questions

What is a context window?

A context window is the maximum number of tokens a model can process in a single request. It covers system instructions, conversation history, retrieved documents, tool definitions, and the space for the model’s reply. Mainstream models currently offer between 200,000 and about 1,050,000 tokens.

What fits in a 200K context window?

Roughly 150,000 English words — a 300-to-500-page book, a mid-sized codebase, or about 400 pages of extracted PDF text. The window is shared with the model's answer, so effective document capacity is somewhat less.

Do all models have a 1 million token context?

No. In August 2026, Anthropic's Fable/Mythos/Opus/Sonnet, OpenAI's GPT-5.6 family, Google's Gemini lineup, Kimi K3, and DeepSeek V4 all offer roughly 1M-token windows. Grok 4.6/4.5 top out at 500K, Kimi K2.7 Code at 262K, Cohere Command A at 256K, and several models at 200K.

Does a bigger context window cost more?

Often, yes — beyond the obvious per-token input cost. Several providers apply long-context tiers: OpenAI doubles input above 272K tokens, xAI doubles rates at 200K+ prompts, and Gemini 3.1 Pro charges $4/$18 above 200K instead of $2/$12.