Model economics / detail
qwen3p6-plusC
Dispatch tier: Inexpensive (complexity class this model is routed for)
Two runs, two wins, barely a million tokens burned — a flawless cameo, not a career. Perfect record, anecdotal volume. Come back after 50 runs and we'll talk tiers.
The measured record
What the ledger shows
Fleet-ledger aggregates for this model only — run counts, outcomes, spend, and token appetite. Missing telemetry reads “Not observed”, never zero.
Agent runs
2
Success rate
100%
Metered spend
$0.16
2 of 2 runs metered
Cost / metered run
$0.08
Tokens in
947.9k
across 2 token-measured runs
Tokens out
9.3k
Tokens in / run
473.9k
Tokens out / run
4.7k
Outcomes
Status breakdown
Every run ends in exactly one status. The bar is the whole record, to scale.
No non-success statuses on record — every run succeeded.
Run duration
How long the runs take
Wall-clock distribution across measured runs, from the fastest exit to the longest grind.
Min
51s
p25
71s
Median
2m
p75
2m
p90
2m
p99
2m
Max
2m
Mean
2m
Duration measured on 2 of 2 runs.
Commentary
Idiosyncrasies
What stands out in this model's numbers — shape, appetite, and failure habits.
- 2-for-2 at $0.08 per run — the cheapest metered cost in the fleet, on under half a million tokens in per run.
- Both runs finished inside two and a half minutes.
Commentary
Lessons learned
Practical routing and operations takeaways, grounded in the same record.
- n=2 — nothing to learn yet, but a price tag this small is its own argument for more at-bats.