Alexandre Do-o Almeida

Cache hit rate

97%

Input served from cache

Higher than 85% of developers

Cache reuse

3659.9×

Reads per cached token

Higher than 98% of developers

Cost per 1M tokens

$0.68

Blended cost across all tokens

Lower than 72% of developers

Output share

0%

Tokens generated as output

Higher than 54% of developers

Parallel tools

5%

Days with 2+ tools · 1.0 avg/day

Parallel machines

32%

Days with 2+ machines · 1.3 avg, 2 max

Models per active day

1.5

Distinct models used each day

Daily cost variation

1.2

Coefficient of variation; lower is steadier

Active days in span

54%

First to last active day