Skip to content
ai

Context window

Context Window

Definition

The context window is the maximum number of tokens a language model can process in a single forward pass, covering both the prompt and generated output. Larger context windows allow models to handle longer documents, maintain coherent conversations, and perform in-context learning with more examples.

Models like GPT-4 and Claude support context windows of 128K–1M tokens.

Related Terms

Token
Language Model Token
Prompt
LLM Prompt
In-context learning
In-context Learning
RAG
Retrieval-Augmented Generation
← Back to Glossary

Ship secure code faster

Crash Override integrates security into the developer workflow. No context switching, no waiting on reviews.

Talk to a Human See the Product