Jaerong Ahn

Cache hit rate

77%

Input served from cache

Higher than 1% of developers

Cache reuse

22.7×

Reads per cached token

Higher than 47% of developers

Cost per 1M tokens

$0.69

Blended cost across all tokens

Lower than 70% of developers

Output share

1%

Tokens generated as output

Higher than 93% of developers

Parallel tools

0%

Days with 2+ tools · 1.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

3.9

Distinct models used each day

Daily cost variation

1.0

Coefficient of variation; lower is steadier

Active days in span

78%

First to last active day