Context window
The context window is the maximum amount of text - measured in tokens - that a model can take into account in one request, including the conversation, documents and its own reply.
A larger window lets a model work with long documents or whole codebases at once. Roughly, 1,000 tokens is about 750 English words. Using more of the window usually costs more and can be slower.
Related ranking: Longest context
- 1.Grok 4.20 xAI2,000,000
- 2.Grok 4.20 Multi-Agent xAI2,000,000
- 3.Llama 4 Scout Meta1,310,720
- 4.GPT-5.6 Sol OpenAI1,050,000
- 5.GPT-5.6 Terra OpenAI1,050,000
Ranked by maximum context window (tokens) as listed by the API provider. Source: OpenRouter. Full ranking
Explanation written by AI Stats Live editors; last reviewed 29 Sep 2026. Examples and rankings update automatically from the sources listed on the methodology page.