KimJoongWan

Cache hit rate

95%

Input served from cache

Higher than 50% of developers

Cache reuse

3348.9×

Reads per cached token

Higher than 98% of developers

Cost per 1M tokens

$1.82

Blended cost across all tokens

Lower than 13% of developers

Output share

1%

Tokens generated as output

Higher than 87% of developers

Parallel tools

2%

Days with 2+ tools · 1.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.1

Distinct models used each day

Daily cost variation

1.4

Coefficient of variation; lower is steadier

Active days in span

31%

First to last active day