Hello644

Cache hit rate

95%

Input served from cache

Higher than 52% of developers

Cache reuse

27.7×

Reads per cached token

Higher than 57% of developers

Cost per 1M tokens

$1.09

Blended cost across all tokens

Lower than 27% of developers

Output share

0%

Tokens generated as output

Higher than 80% of developers

Parallel tools

25%

Days with 2+ tools · 1.3 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.1

Distinct models used each day

Daily cost variation

0.7

Coefficient of variation; lower is steadier

Active days in span

67%

First to last active day