ENGINEERING FIELD NOTES

FIELD GUIDE / MODEL ROUTING · SEPTEMBER 2026

Spend on the
decisions that matter.

A starting guide to cost-conscious distributed-system engineering with Luna, Terra, Sol, and Astra.

THE OPTIMIZATION TARGETTotal cost per
accepted result.

01 / CHOOSE THE SCOPE

Match the model to the work.

These are hypotheses to test on your own engineering tasks, not capability guarantees.

Swipe or scroll the table to see examples and checks →

Starting routing policy by task scope
Start withGood starting scopeExample assignmentAcceptance check
LunaMechanical workNarrow, easily verified enumeration and summaries of verified findings.List timeout configuration and every call site that uses it.Complete coverage, file references, and no unsupported conclusions.
TerraLocal implementationA clear contract, a bounded change, and a known expected result.Implement specified retry and timeout behavior; add a known-bug regression test.The regression fails before the fix and passes after; the contract holds.
SolAcross componentsImplementation or investigation spanning several parts of a system.Trace duplicate message processing and implement an established idempotency design.Evidence connects the components; replay and failure checks cover the design.
AstraArchitecture & judgmentAmbiguity, consistency guarantees, transaction boundaries, ordering, recovery, and critical review.Decide where the transaction ends and how recovery preserves the invariant.Explicit assumptions, tradeoffs, failure scenarios, and defensible guarantees.

02 / KEEP THE LOOP SHORT

Delegate a contract.
Review the evidence.

Use meaningful checkpoints: after investigation, before a design becomes implementation, and before accepting the result.

COUNT THE WHOLE JOB

Worker + coordinator + retries
+ review & rework

Accepted results

Measure comparable total spend. Track human review time and latency alongside it.

  1. Establish the invariants.

    State required behavior before choosing a model. What must remain true under duplicate delivery, timeout, partial failure, and recovery?

  2. Delegate one bounded outcome.

    Provide relevant context, scope, constraints, and acceptance checks. Make the worker’s authority to change the design explicit.

  3. Ask for a short, evidenced report.

    Require findings or changes, checks performed, file references, and unresolved uncertainty. Concision should preserve the evidence.

  4. Correct once, then reassess.

    Give one targeted correction. Escalate repeated failure or new design decisions; do not keep retrying a task whose scope has changed.

  5. Accept against the contract.

    Review at the planned checkpoints. Count a result as accepted only when its checks and required behavior are satisfied.

03 / A SMALL EXPERIMENT

Equal scores. Different costs.

Ten simple trivia questions per model. Three fresh agents each. Medium reasoning throughout.

10/10

All four models
All answers correct

What the run demonstrated

Luna had the lowest API-equivalent estimate in this trial. No corrections or retries were needed. Simple trivia did not expose a quality advantage for the larger models.

This is not an engineering benchmark. The routing policy above is a proposed starting point, not a finding of this experiment.

Swipe or scroll the table to see every column →

Agent-only estimates · 19 September 2026 · USD
ModelTotal tokensAPI-equivalent costRelative to LunaScore
Luna148,345$0.008642881.00×10/10
Terra107,072$0.0557586.45×10/10
Sol107,067$0.111736812.93×10/10
Astra94,301$0.14024216.23×10/10

Matched prompts ≠ matched context

Corresponding agents received identical assigned prompts, with no conversation-history fork and no tools. Full input sizes and cache coverage still differed; their cause was not isolated. Cache coverage especially favored Astra. Ratios are specific to these runs.

Estimates ≠ subscription deductions

Standard short-context API rates were applied to measured counters. Coordinator and voice usage are excluded. These figures are not actual Codex charges or subscription allowance deductions.

Inspect counters, rates, and assumptions
Measured token counts; reasoning is included in output
ModelUncached inputCached inputOutputReasoning subset
Luna29,206118,784355249
Terra18,69388,320590
Sol18,81588,192600
Astra4,76789,472620

Medium reasoning is a setting, not a fixed token budget. Cache-write counts were zero. Each request was below the long-context threshold. No regional surcharge or fast-mode premium is assumed.

Report’s price assumptions · USD per million tokens
Model / official sourceUncached inputCached inputOutput
Luna ↗$0.20$0.02$1.20
Terra ↗$2.00$0.20$12.00
Sol ↗$4.00$0.40$20.00
Astra ↗$10.00$1.00$50.00

Estimate = (uncached input × input rate + cached input × cache rate + output × output rate) / 1,000,000. Rates are the report’s dated assumptions, not a live price feed.

Hypothetically removing all cache discounts yields Luna $0.030024, Terra $0.214734, Sol $0.429228, and Astra $0.945490. This is a sensitivity calculation, not a second measurement; input sizes still differ.

The ten questions were divided 4 / 3 / 3 across each model’s agents. Each agent replied once. Earlier exploratory runs are excluded. Download measured counters (JSON); private agent identifiers are omitted.

Read the full experiment.

Two-page report with method, counters, rates, and limitations.

Download report PDF ↓

04 / VALIDATE ON REAL WORK

Make your own acceptance rate
the next data point.

Repeat representative engineering tasks with controlled context and cache conditions. Record accepted outcomes, retries, review effort, latency, and coordinator overhead. Update the routing policy when that evidence changes.