Models & PromptingLetter C1 min read
In plain English
The maximum amount of text a model can process in a single request, including prompt and retrieved context.
Full definition
Context windows are measured in tokens. Larger windows support longer documents and multi-turn conversations, while smaller windows require stronger retrieval and summarization strategies.
AshnaAI routes work across models with different context limits so you can balance cost, speed, and depth per task.
Continue learning
LLM routing: match tasks to models
Read the full article on the AshnaAI blog.
Open articleRelated terms
Ready to put these concepts to work?
AshnaAI helps you build AI agents without code—search, automate, and deploy with the terms you just learned.
Continue exploring
Back to full glossary