jessewilliams1

Cache hit rate

97%

Input served from cache

Higher than 86% of developers

Cache reuse

54.5×

Reads per cached token

Higher than 80% of developers

Cost per 1M tokens

$0.71

Blended cost across all tokens

Lower than 67% of developers

Output share

0%

Tokens generated as output

Higher than 68% of developers

Parallel tools

55%

Days with 2+ tools · 1.5 avg/day

Parallel machines

1%

Days with 2+ machines · 1.0 avg, 2 max

Models per active day

2.1

Distinct models used each day

Daily cost variation

0.9

Coefficient of variation; lower is steadier

Active days in span

79%

First to last active day