Know what a scripted run costs before you start it
Lesson 3 of 7 · The working week
By the end you can work out what a scripted run will cost from a price you copied and dated yourself, and write a cap the script obeys.
1 · Learn the move · Constraints + negative instructions
A script that sends every export through a model is cheap once and expensive two hundred times. Before the big run, do the arithmetic on paper: what one call uses, times the number of calls, times the price. The price is the one number the model must never supply. Prices change, and a model will state an old one with full confidence. Copy it from the provider's current pricing page, write the date you read it, and give it to the model as an input. Then ask for the arithmetic shown line by line, a monthly figure at your real run rate, and a cap: the count or spend at which the script stops and asks. If any input is missing, the answer is [NEEDS: ...], not an estimate.
Work out what this run costs. Price, copied from the provider's pricing page on [date]: [paste]. One call uses about [N] input and [M] output tokens (from a test call). Calls per run: [count]. Runs per month: [count]. Show the arithmetic line by line. Never supply or adjust a price yourself; if any input is missing, write [NEEDS: ...]. Then write a stop rule I can paste into the script: the count at which it stops and asks.
Vendor notes, dated
Prices and plan names move. Each note says when it was looked up, whether a person has confirmed it, and the day it comes due. Past that day, treat it as a question.
- Claude. Claude Pro is $20 a month billed monthly, or $17 a month billed annually. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- ChatGPT. ChatGPT Plus is $20 a month. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Google Gemini. Google Gemini's paid consumer plan is Google AI Pro at $19.99 a month; Google AI Ultra starts at $99.99 a month. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Anthropic. Anthropic's consumer plans (Free, Pro, Max) may use chats to train models under a setting the user controls, with five-year retention when training is on and 30 days when it is off; Claude for Work, Education, Government and the API are excluded. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Anthropic. Anthropic's usage policy, effective 2025-09-15, requires a qualified human reviewer and disclosure of AI use for housing, legal and financial decisions. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- OpenAI. OpenAI's consumer plans train on chats unless the Improve the model setting is turned off, and a Temporary Chat is not used for training; Enterprise, Business, Edu and API data are not used by default. [S] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Google Gemini. Google Gemini Apps keeps activity 18 months by default, keeps human-reviewed chats up to three years, and tells users not to enter confidential information. [P] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Microsoft Copilot. Microsoft Copilot on a personal account may use chats to train models unless the user opts out; Entra and Microsoft 365 work accounts are excluded. [S] Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- Benchling. Benchling's academic plan is free; its pricing page shows no paid prices and routes labs to a demo. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
- protocols.io. protocols.io's Open Research plan is free, with unlimited public protocols and two private ones. Researched Oct 6, 2026, not yet confirmed by a person, recheck by Dec 15, 2026.
2 · Your turn. You write the prompt
You have a script that sends each plate-reader export to a model to check the layout and flag drifting wells. One test call worked. The full backlog is 240 exports, and after that about 60 a month. Your PI asked, in passing, what it will cost. You don't know, and you would rather know before the backlog run than after.
Write the prompt for this scenario as given, or swap in a real one from your own work. The score works the same either way.
Remember: the AI sees only your prompt, not this page. If the situation isn't in your prompt, it doesn't exist.
Optional. These shape the output when you run your prompt below, not your score.