The Model Menu and the API
The price sheet, and how to read it. What each of the four models costs per million tokens, and why output is always five times input. How much text a million tokens actually holds, and the tokenizer change that means a lower rate isn't automatically a lower bill. Then the part that pays for the book: prompt caching, which breaks even after a single read, and the Batch API's flat fifty per cent, which stack. It ends with one fully worked example - a real job at $112.75 a month taken to $11.49 without changing the prompt or the model - with every figure computed rather than estimated.
What is inside
How this book is built, and why you can trust it.
- Every model name, price, limit and feature was checked against the vendor's own published documentation
- Every number in a worked cost example was computed, not estimated
- One idea per chapter, in plain English
- Five challenges with a full answer key, and a glossary
Cheat sheet 07: Thinking, Effort, Models and Cost
A two page revision sheet on this topic, printed front and back. Product facts checked against the vendor docs.
Save with the Advanced Claude bundle
All 9 books in this series, 31% off buying them one by one.
More from Advanced Claude
One email when a new book lands
No schedule, no filler. Just the new titles and the odd free chapter.