Module 1 · Lab 1 · 20 min · Start here

📧 Understand and Estimate LLM Costs

💡 No code, no signup. Everything recalculates live from real published token prices. Change any number and watch what happens.

Exercise 2 · Right-Sizing Your Model Choice

Goal: decide which email types actually need an expensive model.

Route each email type to a model

Drag a model chip onto each email type — or select a chip and press Enter on a target.

Exercise 3 · What Volume Does

Goal: see how a fraction of a cent becomes a budget line.

Emails per day — 100

Monthly cost by volume

Exercise 4 · The Cost of Being Wrong

Goal: find the point where the cheap model stops being the cheap option.

Cheaper models miss things. A missed detail in a finance email costs someone time to catch and fix. Token cost is only half the bill — total cost = tokens + remediation. Move the sliders and watch the winner change.

Cost to fix one missed detail — $2.00

Analyst time to catch and correct it. $2 ≈ a couple of minutes.

Emails per day — 100

Assumed miss rate

Illustrative rates for the lab, not measured benchmarks. Your own numbers should come from sampling your real output.

Total monthly cost of ownership

Tokens vs. remediation

🔍 Find the crossovers. Drag the fix-cost slider from $0 upward. There are three regimes — one model is cheapest in each. Note where the winner flips; those two numbers are the real output of this exercise.

Exercise 5 · Your Call

Challenge: your CFO sets the constraints. Design a routing mix that satisfies all of them.

Constraints

Monthly budget ($)

Emails per day

Minimum quality (%)

Cost to fix a miss ($)

Your routing mix

—

Result

Total / month

—

Quality

—

Verdict

—

Against your constraints

Your justification (100+ words)

0 words