reyanatifbsse-2021a-alt

Cache hit rate

98%

Input served from cache

Higher than 89% of developers

Cache reuse

86.3×

Reads per cached token

Higher than 87% of developers

Cost per 1M tokens

$0.81

Blended cost across all tokens

Lower than 46% of developers

Output share

1%

Tokens generated as output

Higher than 97% of developers

Parallel tools

6%

Days with 2+ tools · 1.1 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.2

Distinct models used each day

Daily cost variation

1.2

Coefficient of variation; lower is steadier

Active days in span

28%

First to last active day