Tokens and context windows
Models read tokens, not characters, and they can only see a fixed window of them. Both your bill and your failures come back to this.
- 12m
- Intermediate
Video by IBM Technology · YouTube
Check your understanding
3 questions. Unlocks when you finish the video.
Overview
What this lesson covers
- Understand tokenisation and why cost is per token
- Budget a prompt against the context window
- Recognise the failure modes of an overflowing context
This lesson sits in LLM Fundamentals, part of Building AI Apps with LLMs. It assumes what came before it and leads directly into the next lesson in the module.
In this lesson you will:
- Understand tokenisation and why cost is per token
- Budget a prompt against the context window
- Recognise the failure modes of an overflowing context
Resources
Your notes will live here
Note taking is not available yet. Nothing you type would be saved, so the tab stays read-only for now.