frorong

Cache hit rate

95%

Input served from cache

Higher than 45% of developers

Cache reuse

7805.6×

Reads per cached token

Higher than 99% of developers

Cost per 1M tokens

$0.63

Blended cost across all tokens

Lower than 79% of developers

Output share

0%

Tokens generated as output

Higher than 70% of developers

Parallel tools

1%

Days with 2+ tools · 1.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.4

Distinct models used each day

Daily cost variation

2.7

Coefficient of variation; lower is steadier

Active days in span

48%

First to last active day