AI by Hand ✍️

AI by Hand ✍️

Fixed Overhead

Paying for the same tokens ten times

Prof. Tom Yeh's avatar
Prof. Tom Yeh
May 28, 2026
∙ Paid

Library › Token Problems

  1. Tokenization

  2. Subword Tokens

  3. Non-Word Tokens

  4. Token Ratio

  5. Headroom

  6. Token Pricing

  7. Prompt and Completion

  8. The Billing Line

  9. Asymmetric Pricing

  10. Words to Cents

  11. Token Mix

  12. Usage Forecast

  13. Standing Instructions

  14. Fixed Overhead

  15. Budget Ceiling

  16. Token Allowance

  17. Two Speeds

  18. Output Bound

  19. Rate Cards

  20. Usage Audit

What does it cost to repeat the same instructions on every call? The model has no memory between turns, so the system prompt is re-sent in full each time, adding a fixed cost regardless of what the user asks. A longer system prompt means a larger per-call tax. For agents with detailed instructions, this fixed cost can add up to a significant share of the total bill.

Paid members: the worksheet and its printable PDF are below ↓

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2026 Tom Yeh · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture