Cost, capacity, and reliability · Lesson 1 of 14 · 9 min

Read token cost inputs

Token cost inputs separate input and output rates, their units and the model revision. This case uses fictional training rates, not a provider price quote.

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-001.json. Separate the recorded facts from your assumptions.
Hint & worked example
Token cost inputs separate input and output rates, their units and the model revision. This case uses fictional training rates, not a provider price quote.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-cost-reliability-001.json
```
Common mistake to avoid: Publish these fixture rates as the live price for every model.
2
Isolate the deciding signal
Select the real_provider_quote field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Label the rates as fictional training values rather than a current provider quote.
A successful JSON query isolates real_provider_quote.
```
jq .real_provider_quote /opt/ai-lab/cases/aiops-cost-reliability-001.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: label-training-rates, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-cost-reliability-001-decision.txt.
Hint & worked example
Label the rates as fictional training values rather than a current provider quote.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'label-training-rates' > /home/learner/lab/aiops-cost-reliability-001-decision.txt
```
Common mistake to avoid: Publish these fixture rates as the live price for every model.

Understand the pattern

Token cost inputs separate input and output rates, their units and the model revision. This case uses fictional training rates, not a provider price quote.

Interpret the evidence

Label the rates as fictional training values rather than a current provider quote.

A tempting mistake

Publish these fixture rates as the live price for every model.

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-001.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "input_rate_per_million": 1,
  "output_rate_per_million": 3,
  "currency": "training USD",
  "real_provider_quote": false
}

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

$ jq .real_provider_quote /opt/ai-lab/cases/aiops-cost-reliability-001.json

false

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

$ printf '%s\n' 'label-training-rates' > /home/learner/lab/aiops-cost-reliability-001-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 “label-training-rates” to stop being the justified action. Do not silently replace missing evidence with a guess.

Explain it

What does the evidence in “Read token cost inputs” justify?Label the rates as fictional training values rather than a current provider quote.Publish these fixture rates as the live price for every model.Make the change now and gather the missing evidence afterward.

Apply it elsewhere

A colleague concludes: “Publish these fixture rates as the live price for every model.” What should you do?Accept it because the training command completed.Treat this fixture as a live measurement.Reject that conclusion; return to the case evidence and its stated limits.

Keep the momentum.

Complete the lab, then explain and apply the pattern.

Next: Estimate request cost 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