cjleemesotes

Cache hit rate

97%

Input served from cache

Higher than 79% of developers

Cache reuse

37.9×

Reads per cached token

Higher than 70% of developers

Cost per 1M tokens

$0.87

Blended cost across all tokens

Lower than 42% of developers

Output share

0%

Tokens generated as output

Higher than 72% of developers

Parallel tools

32%

Days with 2+ tools · 1.3 avg/day

Models per active day

2.3

Distinct models used each day

Daily cost variation

0.7

Coefficient of variation; lower is steadier

Active days in span

75%

First to last active day