Build with AI · Chapter 9 of 13
Cheap tokens do not automatically make a profitable product
Work through one fictional delivery budget, including retries, checking and finding customers.
About 5 minutes · school-level background
Edition 2026-10-28.1 · Checked 2026-10-28
What you will understand
Calculate a simple cost per accepted job and identify the assumptions that could overturn a business idea.
In this lesson
- The missing line in a cheerful calculation
- Read a price announcement with the conditions attached
- Build the first budget one step at a time
- Put retries and rejected jobs back into the picture
- Revenue is not the amount left over
- Use scenarios to find the fragile assumption
- Keep the budget attached to the promise
Build the idea
The missing line in a cheerful calculation
You read that an AI answer can cost a fraction of a penny. You imagine selling a useful report for several pounds and keeping almost everything. Then the first customer asks for a correction, a website cannot be read, and you spend twenty minutes explaining the output. The model bill was real, but it was only one part of delivery. A business needs to cover the work required to produce something the customer accepts.
A token is a small unit used by a model to represent text or other supported information. It is not always a word. Providers may charge differently for input, output, cached information and tools. An input is what you send to the model; an output is what it generates. Long source documents can make the input much larger than the final answer. Always check the current product’s actual billing definitions before estimating a real bill.
Inputs and model output
Retries and other tools
Human checking and repair
Cost of one accepted job
A simplified reading aid. Follow the article for sources, conditions and limits.
What the source reports
Read a price announcement with the conditions attached
Anthropic’s Haiku 5.5 announcement promotes economical high-volume work, but its listed prices have conditions, including prompt size. A headline rate is therefore not a complete delivery budget. The calculation below uses invented prices and workloads so you can inspect the reasoning without mistaking a classroom example for a current vendor quote.
Original report: Anthropic: Claude Haiku 5.5
Worked teaching example
Build the first budget one step at a time
Suppose a fictional task uses ten thousand input tokens and two thousand output tokens. Assume an invented input price of one pound per million tokens and an output price of five pounds per million. Ten thousand is one hundredth of a million, so the input costs one penny. Two thousand is one five-hundredth of a million, so the output also costs one penny. The model charge for one attempt is two pence.
Now add a fictional three-pence tool charge per attempt. That makes five pence before review. Suppose every delivered job receives three minutes of human checking valued at twelve pounds per hour. Three minutes is one twentieth of an hour, so checking costs sixty pence. With one attempt per accepted job, delivery costs sixty-five pence before fixed expenses, customer acquisition, refunds and tax. The review line is twelve times the model-and-tool line.
Pause and predict which improvement helps more in this example: halving the model charge or cutting review from three minutes to two. Halving the two-pence model charge saves one penny. Removing one minute of review saves twenty pence at the stated hourly value. This does not mean review should be skipped. It means a clearer output that is quicker to check could matter more than a cheaper model. Quality and review time must be measured together.
Worked teaching example
Put retries and rejected jobs back into the picture
Suppose one job in five needs a second complete attempt, and all jobs are eventually accepted. For every one hundred accepted jobs, you now pay for one hundred and twenty attempts. At five pence per attempt, that is six pounds, or six pence per accepted job. If review still averages three minutes per accepted job, the total is sixty-six pence. We are explicitly assuming that retry handling does not increase review time; change that assumption if your observations say otherwise.
If ten out of one hundred attempted jobs never become acceptable, divide total spending by ninety accepted jobs, not one hundred requests. This denominator matters. A service can appear cheap when it counts every generated response as a success. Track attempted work, accepted work and abandoned work separately. A failed job may still teach you something, but a customer buying an accepted deliverable has not received the promised result.
Build the idea
Revenue is not the amount left over
Imagine an illustrative price of two pounds per accepted job and a variable delivery cost of sixty-six pence. Subtracting gives one pound and thirty-four pence before fixed costs and other expenses. This is a simple contribution calculation, not net profit. If monthly fixed costs were twenty pounds, fifteen such accepted jobs would contribute twenty pounds and ten pence, barely covering that fixed amount under these assumptions.
Finding customers also costs time or money. If you spend ten pounds to obtain a customer who buys only one two-pound job, the acquisition cost overwhelms that sale. If they repeatedly buy useful work, the picture may change. You need actual repeat behaviour to justify that assumption. Do not build a forecast around customers returning indefinitely simply because the spreadsheet allows you to type a large number.
Use the idea
Use scenarios to find the fragile assumption
Make three columns: a base case, more retries, and more review. Keep the assumptions visible above each calculation. For example, if average review rises from three minutes to eight, review costs one pound and sixty pence. Add the six-pence attempt cost from the retry scenario and the two-pound illustrative price leaves thirty-four pence before fixed and acquisition costs. The arithmetic shows where the idea is sensitive.
Then ask what you could observe cheaply. Time yourself checking ten fictional or permissioned examples. Record the corrections, not just the average duration. Find whether one input type creates most of the extra work. You might narrow the service to clear public documents, improve the output table or stop serving a category that cannot be checked economically. Those decisions are more useful than arguing about a model’s price in isolation.
Use the idea
Keep the budget attached to the promise
A low-cost service can be a good idea if it solves a real problem at an acceptable quality and the whole delivery process is sustainable. Your next artifact is a small cost sheet with units, assumptions and observed values separated. Keep the model version and pricing date with it. When a provider changes prices or your process changes, update the relevant lines and rerun the scenarios. The sheet should help you make a decision, not manufacture confidence in a business you have not tested.
Words you can now use
- Token
- A unit used to represent model input or output; not a fixed number of words.
- Variable cost
- A cost that changes with the amount of work delivered.
- Fixed cost
- A cost paid over a period that does not change with each extra job within the assumed capacity.
- Contribution
- Revenue minus the variable costs included in the calculation; not necessarily profit.
Check your understanding
At twelve pounds an hour, review rises from three to eight minutes. How much extra review cost is that per job?
Show the explanation
Five extra minutes is one twelfth of an hour. At twelve pounds an hour it costs one additional pound. Review becomes £1.60 rather than £0.60; with £0.06 attempt cost, a £2 illustrative price leaves £0.34 before other expenses.
Read the original sources
- Anthropic: Claude Haiku 5.5Vendor announcement · Published 2026-10-07 · Checked 2026-10-28
Try it with your own assistant
Select and copy this bounded exercise. A normal chat assistant is enough to start.
Copy the fictional cost assumptions into a spreadsheet. Calculate base cost, a retry scenario and a higher-review scenario. Keep model charges, review time, fixed costs and customer acquisition separate. Replace assumptions only with your own measured values.
Keep the task brief, supplied inputs, checked output and unresolved questions together. Using this exercise does not submit anything to WRS.