yohanreddy

Cache hit rate

97%

Input served from cache

Higher than 74% of developers

Cache reuse

53.5×

Reads per cached token

Higher than 80% of developers

Cost per 1M tokens

$0.77

Blended cost across all tokens

Lower than 57% of developers

Output share

1%

Tokens generated as output

Higher than 90% of developers

Parallel tools

22%

Days with 2+ tools · 1.3 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.9

Distinct models used each day

Daily cost variation

1.3

Coefficient of variation; lower is steadier

Active days in span

55%

First to last active day