Context Window Visualizer

See how much each model can process in a single request.

Compare context window sizes across every major LLM in one interactive visualization. See which models can handle entire codebases, novels, or long document collections. Covering GPT-5.4 (1.05M tokens), Gemini 3.1 Pro (1M tokens), Claude Opus 4.6 (200K tokens), and more.

Context Window Sizes by Model

What Fits in Each Context Window?

Document TypeTokensWords
A tweet70~53
A short email375~281
A 5-page PDF3.5K~2,625
A blog post (1,000 words)1.5K~1,125
A 50-page report35K~26,250
A full codebase (10K LOC)114K~85,500
A novel (80K words)120K~90,000

All Model Context Windows

ModelProviderContext Window≈ WordsMax Output
Grok 4.1 FastxAI2M~1,500,00016K
GPT-5.4OpenAI1.1M~787,500128K
GPT-5.4 ProOpenAI1.1M~787,500128K
Llama 4 MaverickMeta1.0M~786,43265.5K
GPT-4.1OpenAI1.0M~785,68232.8K
GPT-4.1 miniOpenAI1.0M~785,68232.8K
GPT-4.1 nanoOpenAI1.0M~785,68232.8K
Gemini 3.1 ProGoogle1M~750,00065.5K
Gemini 3.1 Flash LiteGoogle1M~750,00065.5K
Gemini 3 FlashGoogle1M~750,00065.5K
Gemini 2.5 ProGoogle1M~750,00065.5K
Gemini 2.5 FlashGoogle1M~750,00065.5K
Gemini 2.5 Flash LiteGoogle1M~750,00065.5K
Nova PremierAmazon1M~750,00032.8K
Nova 2 LiteAmazon1M~750,00032.8K
GPT-5.3 CodexOpenAI400K~300,000128K
GPT-5.2OpenAI400K~300,000128K
GPT-5.2 ProOpenAI400K~300,000128K
GPT-5.1OpenAI400K~300,000128K
GPT-5OpenAI400K~300,000128K
GPT-5 ProOpenAI400K~300,000128K
GPT-5 miniOpenAI400K~300,000128K
GPT-5 nanoOpenAI400K~300,000128K
Llama 4 ScoutMeta327.7K~245,76032.8K
Nova ProAmazon300K~225,0005.1K
Nova LiteAmazon300K~225,0005.1K
Mistral Large 3Mistral262.1K~196,60832.8K
Devstral 2Mistral262.1K~196,60832.8K
Grok 4xAI256K~192,00032.8K
Grok Code FastxAI256K~192,00032.8K
CodestralMistral256K~192,00032.8K
Command ACohere256K~192,0008.2K
o3OpenAI200K~150,000100K
o3 ProOpenAI200K~150,000100K
o4 miniOpenAI200K~150,000100K
o3 miniOpenAI200K~150,000100K
o1OpenAI200K~150,000100K
Claude Opus 4.6Anthropic200K~150,000128K
Claude Sonnet 4.6Anthropic200K~150,00064K
Claude Opus 4.5Anthropic200K~150,00064K
Claude Sonnet 4.5Anthropic200K~150,00064K
Claude Haiku 4.5Anthropic200K~150,00064K
Claude Sonnet 4Anthropic200K~150,00064K
Claude Haiku 3.5Anthropic200K~150,0008.2K
Grok 3xAI131.1K~98,30416.4K
Grok 3 minixAI131.1K~98,30416.4K
Mistral Medium 3.1Mistral131.1K~98,30432.8K
Pixtral LargeMistral131.1K~98,30432.8K
Mistral Small 3.2Mistral131.1K~98,30432.8K
Mistral NemoMistral131.1K~98,30432.8K
GPT-4oOpenAI128K~96,00016.4K
GPT-4o miniOpenAI128K~96,00016.4K
DeepSeek V3.2DeepSeek128K~96,0008.2K
DeepSeek V3.2 ReasonerDeepSeek128K~96,00064K
Nova MicroAmazon128K~96,0005.1K
Command RCohere128K~96,0004.1K
Command R7BCohere128K~96,0004.1K
Magistral MediumMistral40K~30,00032.8K

Why Context Window Size Matters

A model's context window determines how much text it can process in a single request — including your prompt, any documents you provide, and the model's response. Larger context windows enable processing entire codebases, long legal documents, or multi-chapter reports without splitting them into chunks. However, larger contexts typically cost more and may increase latency. GPT-5.4 leads with 1,050,000 tokens, followed by Gemini 3.1 Pro at 1,000,000 and Claude Opus 4.6 at 200,000.

What Fits in Each Context Size

A 128K context window (GPT-4o, DeepSeek-R1) holds approximately 96,000 words — equivalent to a full novel. A 200K context window (Claude models) holds about 150,000 words or a thick technical manual. A 1M+ context window (GPT-5.4, Gemini 3.1 Pro) holds roughly 750,000 words — enough for multiple textbooks or an entire medium-sized codebase. Understanding these capacities helps you choose the right model for your document processing needs.

Frequently Asked Questions

Which LLM has the largest context window in 2026?
GPT-5.4 and GPT-5.2 have the largest context windows at 1,050,000 tokens (approximately 787,000 words). Gemini 3.1 Pro and Gemini 3 Flash follow closely at 1,000,000 tokens. Grok 4.1 also supports 1,000,000 tokens.
Can I fit an entire codebase in an LLM context window?
A medium codebase of 10,000 lines of code is approximately 114,000 tokens, which fits in any model with a 128K+ context window. Larger codebases of 50,000+ lines may require GPT-5.4 (1.05M tokens) or Gemini 3.1 Pro (1M tokens). Note that long context pricing multipliers may apply.
Does a larger context window cost more?
Not directly — you pay per token used, not per context window size. However, some providers like OpenAI and Google apply long context pricing multipliers when you exceed certain thresholds. GPT-5.4 charges 2x for input tokens beyond 272K. Gemini 3.1 Pro charges 2x beyond 200K tokens.
What is a context window in LLM terms?
A context window is the maximum number of tokens an LLM can process in a single request. It includes everything: your system prompt, user message, any documents or examples you include, and the model's generated response. Once you exceed the context window, the model cannot process the additional text.

Context window sizes sourced from official provider documentation. Effective usable context may be slightly less than the maximum due to system overhead.