Glossary
Context window
In short
The amount of text a model can consider at once, measured in tokens, covering both your input and its output.
Everything a model works with at a given moment, your prompt, any documents you include, and the answer it generates, has to fit inside its context window. Run past it and the model loses track of the earliest material.
Bigger windows make it practical to reason over long documents or large amounts of material in one pass. Some models now handle hundreds of thousands or even a million tokens.
In LLMWeave
When a task involves a lot of material, a weave can route it to a model with a large context window so the whole thing fits in one pass.
Related terms
Tokens
The chunks of text models read and write, roughly a few characters each, and the unit most model pricing is based on.
Model routing
Sending each task, or each part of a task, to the model best suited for it, rather than using one model for everything.
Reasoning model
A model built to work through problems step by step before answering, rather than responding in a single pass.
Try multi-model on your task
One prompt, several models, one answer. Free to start, no card.
Get started