mperepelitsyn

Cache hit rate

96%

Input served from cache

Higher than 66% of developers

Cache reuse

30.4×

Reads per cached token

Higher than 61% of developers

Cost per 1M tokens

$0.97

Blended cost across all tokens

Lower than 34% of developers

Output share

1%

Tokens generated as output

Higher than 92% of developers

Parallel tools

47%

Days with 2+ tools · 1.5 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.6

Distinct models used each day

Daily cost variation

1.3

Coefficient of variation; lower is steadier

Active days in span

93%

First to last active day