Y

Cache hit rate

95%

Input served from cache

Higher than 46% of developers

Cost per 1M tokens

$0.74

Blended cost across all tokens

Lower than 61% of developers

Output share

0%

Tokens generated as output

Higher than 83% of developers

Parallel tools

9%

Days with 2+ tools · 1.1 avg/day

Parallel machines

16%

Days with 2+ machines · 1.2 avg, 2 max

Models per active day

2.3

Distinct models used each day

Daily cost variation

1.1

Coefficient of variation; lower is steadier

Active days in span

53%

First to last active day