g80siddh

Cache hit rate

97%

Input served from cache

Higher than 70% of developers

Cache reuse

45.9×

Reads per cached token

Higher than 73% of developers

Cost per 1M tokens

$1.25

Blended cost across all tokens

Lower than 21% of developers

Output share

1%

Tokens generated as output

Higher than 89% of developers

Parallel tools

45%

Days with 2+ tools · 1.6 avg/day

Models per active day

2.7

Distinct models used each day

Daily cost variation

1.1

Coefficient of variation; lower is steadier

Active days in span

92%

First to last active day