Bora Arslan

Cache hit rate

96%

Input served from cache

Higher than 57% of developers

Cache reuse

27.2×

Reads per cached token

Higher than 56% of developers

Cost per 1M tokens

$1.24

Blended cost across all tokens

Lower than 23% of developers

Output share

1%

Tokens generated as output

Higher than 96% of developers

Parallel tools

3%

Days with 2+ tools · 1.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.8

Distinct models used each day

Daily cost variation

1.2

Coefficient of variation; lower is steadier

Active days in span

14%

First to last active day