rawatpranjal

Cache hit rate

95%

Input served from cache

Higher than 35% of developers

Cache reuse

31.9×

Reads per cached token

Higher than 61% of developers

Cost per 1M tokens

$0.89

Blended cost across all tokens

Lower than 38% of developers

Output share

1%

Tokens generated as output

Higher than 96% of developers

Parallel tools

25%

Days with 2+ tools · 1.3 avg/day

Models per active day

1.9

Distinct models used each day

Daily cost variation

1.8

Coefficient of variation; lower is steadier

Active days in span

45%

First to last active day