Cost, capacity, and reliability · Lesson 2 of 14 · 5 min

Estimate request cost

A token cost estimate multiplies each token count by its corresponding per-token rate. Convert per-million rates before summing input and output estimates.

Open the lab Course map

Mastery 0/3Run itExplain itApply it

learner@clairos:~ $

↑ history · Tab complete · Ctrl+C cancel · Esc, Tab to leaveExit 0

Your objectives

Hints are always available. Wrong turns never cost XP.

1
Read the case evidence
Read /opt/ai-lab/cases/aiops-cost-reliability-002.json. Separate the recorded facts from your assumptions.
Hint & worked example
A token cost estimate multiplies each token count by its corresponding per-token rate. Convert per-million rates before summing input and output estimates.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-cost-reliability-002.json
```
Common mistake to avoid: Use per-million rates as if they were prices for a single token.
2
Isolate the deciding signal
Select the estimated_cost field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Record the fictional case estimate of 0.0016 units, not 1.6 or 1600.
A successful JSON query isolates estimated_cost.
```
jq .estimated_cost /opt/ai-lab/cases/aiops-cost-reliability-002.json
```
Common mistake to avoid: Using a different case or an unrelated signal as the justification.
3
Record your operational decision
Choose the justified code: record-estimate-0-0016, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-cost-reliability-002-decision.txt.
Hint & worked example
Record the fictional case estimate of 0.0016 units, not 1.6 or 1600.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'record-estimate-0-0016' > /home/learner/lab/aiops-cost-reliability-002-decision.txt
```
Common mistake to avoid: Use per-million rates as if they were prices for a single token.

Understand the pattern

A token cost estimate multiplies each token count by its corresponding per-token rate. Convert per-million rates before summing input and output estimates.

Interpret the evidence

Record the fictional case estimate of 0.0016 units, not 1.6 or 1600.

A tempting mistake

Use per-million rates as if they were prices for a single token.

All names, measurements, prices, versions, and thresholds in this exercise are fictional training data. The evidence supports this bounded scenario, not a claim about a live provider.

Worked example and expected result

$ cat /opt/ai-lab/cases/aiops-cost-reliability-002.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "input_tokens": 1000,
  "output_tokens": 200,
  "input_rate_per_million": 1,
  "output_rate_per_million": 3,
  "estimated_cost": 0.0016
}

Exit status: 0. The command completed successfully in the training fixture.

$ jq .estimated_cost /opt/ai-lab/cases/aiops-cost-reliability-002.json

0.0016

Exit status: 0. The command completed successfully in the training fixture.

$ printf '%s\n' 'record-estimate-0-0016' > /home/learner/lab/aiops-cost-reliability-002-decision.txt

(no output; exit 0)

Exit status: 0. The command completed successfully in the training fixture.

Try a variation

Name the assumption that would have to change for “record-estimate-0-0016” to stop being the justified action. Do not silently replace missing evidence with a guess.

Explain it

What does the evidence in “Estimate request cost” justify?Use per-million rates as if they were prices for a single token.Make the change now and gather the missing evidence afterward.Record the fictional case estimate of 0.0016 units, not 1.6 or 1600.

Apply it elsewhere

A colleague concludes: “Use per-million rates as if they were prices for a single token.” What should you do?Treat this fixture as a live measurement.Reject that conclusion; return to the case evidence and its stated limits.Accept it because the training command completed.

Keep the momentum.

Complete the lab, then explain and apply the pattern.

Next: Compare model cost profiles Try an incident drill

Anonymous lesson and mastery progress lasts for this session. Sign in to keep synced lesson XP between sessions; mastery stays device-local. No speed bonus, lost lives, or hint penalties.

Keep learning

Case methodology: evidence, limits, decision