anthonysuherli

Cache hit rate

95%

Input served from cache

Higher than 48% of developers

Cache reuse

23.1×

Reads per cached token

Higher than 49% of developers

Cost per 1M tokens

$0.90

Blended cost across all tokens

Lower than 39% of developers

Output share

1%

Tokens generated as output

Higher than 92% of developers

Parallel tools

7%

Days with 2+ tools · 0.8 avg/day

Models per active day

2.9

Distinct models used each day

Daily cost variation

1.0

Coefficient of variation; lower is steadier

Active days in span

55%

First to last active day