JHLee

Cache hit rate

94%

Input served from cache

Higher than 31% of developers

Cache reuse

783.1×

Reads per cached token

Higher than 96% of developers

Cost per 1M tokens

$0.55

Blended cost across all tokens

Lower than 90% of developers

Output share

0%

Tokens generated as output

Higher than 80% of developers

Parallel tools

23%

Days with 2+ tools · 1.2 avg/day

Parallel machines

32%

Days with 2+ machines · 1.3 avg, 2 max

Models per active day

1.6

Distinct models used each day

Daily cost variation

1.5

Coefficient of variation; lower is steadier

Active days in span

59%

First to last active day