Koushik

Cache hit rate

91%

Input served from cache

Higher than 7% of developers

Cache reuse

36.1×

Reads per cached token

Higher than 68% of developers

Cost per 1M tokens

$0.95

Blended cost across all tokens

Lower than 35% of developers

Output share

1%

Tokens generated as output

Higher than 98% of developers

Parallel tools

21%

Days with 2+ tools · 1.2 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.7

Distinct models used each day

Daily cost variation

1.2

Coefficient of variation; lower is steadier

Active days in span

64%

First to last active day