Context window

← All terms · AI providers and models

Also called Context limit, Token limit

The maximum amount of text (measured in tokens) an AI model can process and remember in a single interaction.

What it is

A context window dictates how much information you can feed an AI model at one time. If a conversation or document exceeds this limit, the model will "forget" the earliest information provided. Modern frontier models support context windows of 1 to 2 million tokens, enabling the ingestion of entire codebases.

When you would use it

You constantly monitor the context window to ensure your agent doesn't "forget" its original instructions during a long, multi-step orchestration task.

Common operations

• Pasting entire software repositories into a prompt for architectural review.
• Maintaining long-running conversational agent loops without losing state.

Related terms

• Token
• Tool loop exhaustion
• RAG

Where this is taught

• Retrieval memory for long-context work