ahron0520

Cache hit rate

96%

Input served from cache

Higher than 64% of developers

Cache reuse

50.6×

Reads per cached token

Higher than 79% of developers

Cost per 1M tokens

$1.38

Blended cost across all tokens

Lower than 19% of developers

Output share

1%

Tokens generated as output

Higher than 89% of developers

Parallel tools

41%

Days with 2+ tools · 1.4 avg/day

Parallel machines

73%

Days with 2+ machines · 1.8 avg, 3 max

Models per active day

3.2

Distinct models used each day

Daily cost variation

1.1

Coefficient of variation; lower is steadier

Active days in span

91%

First to last active day