Free AI template
Cost estimate for an AI feature
A prompt, the expected reply length and traffic, and what it costs per call, per day and per month on each model.
It opens with this template loaded and runs in your browser. You don't need an account to use it; a free account saves your work and exports it.
The job it does
When someone asks "what will this AI feature cost?": put in your prices and traffic, and set a budget the prompt must fit. It comes with its own checks, so after you change it you can see at a glance that it still does the job.
How to use it with your own data
Edit the price table with your provider's prices, and the calls per day with your own traffic.
What's inside
This is the template exactly as the AI Lab opens it, read-only. Open it to run it, change it and export it.
- About 116 tokens
- 200-token reply, 5,000 calls a day
What a document-summary feature costs: the prompt, a 200-token reply and 5,000 calls a day, on each model in the price table. Put in your provider's prices and your traffic; the criterion keeps the prompt within budget.
- The prompt is at most 400 tokens
- At most $1.00 per 1,000 calls
- The prompt passes the linter (no errors or warnings)
You are an assistant that writes short, accurate summaries for busy managers.
# Task
Summarise the document in the <doc> tags.
# Context
<doc>
{{input}}
</doc>
# Rules
- Use only facts from the document; if something is unclear, say "unclear".
- At most 5 bullet points, each under 25 words.
# Output format
Three sections with these headings: Summary (bullets), Decisions (bullets), Next steps (bullets with an owner each).| Model | Per call | Per day | Per month |
|---|---|---|---|
| Large frontier model | $0.00375 | $18.75 | $563 |
| Mid-size model | $0.00037 | $1.83 | $54.96 |
| Small fast model | $0.00009 | $0.43 | $13.05 |
| Open model on your own server | $0 | $0 | $0 |
The lesson behind it
Learn why it works, with a podcast and a quiz for each lesson.
More AI templates
Prompt review
A support prompt in parts (role, task, context, rules, format, an example) that passes the linter, with its token count and cost.
Eval set for a chatbot
Replies a bot really gave, labelled good or bad, and checks that agree with every label, exportable as CSV.
Structured output with a schema
An extraction prompt, the JSON Schema its replies must follow, and sample replies that should and should not pass.