eliminated

Cache hit rate

96%

Input served from cache

Higher than 59% of developers

Cache reuse

33.5×

Reads per cached token

Higher than 62% of developers

Cost per 1M tokens

$0.82

Blended cost across all tokens

Lower than 45% of developers

Output share

1%

Tokens generated as output

Higher than 90% of developers

Parallel tools

22%

Days with 2+ tools · 1.2 avg/day

Models per active day

2.0

Distinct models used each day

Daily cost variation

1.1

Coefficient of variation; lower is steadier

Active days in span

36%

First to last active day