farias_77

Cache hit rate

95%

Input served from cache

Higher than 52% of developers

Cache reuse

28.5×

Reads per cached token

Higher than 59% of developers

Cost per 1M tokens

$0.74

Blended cost across all tokens

Lower than 60% of developers

Output share

1%

Tokens generated as output

Higher than 95% of developers

Parallel tools

2%

Days with 2+ tools · 1.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.7

Distinct models used each day

Daily cost variation

2.3

Coefficient of variation; lower is steadier

Active days in span

32%

First to last active day