Zyksa

Cache hit rate

97%

Input served from cache

Higher than 84% of developers

Cache reuse

98.6×

Reads per cached token

Higher than 90% of developers

Cost per 1M tokens

$0.31

Blended cost across all tokens

Lower than 98% of developers

Output share

0%

Tokens generated as output

Higher than 46% of developers

Parallel tools

70%

Days with 2+ tools · 1.8 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.9

Distinct models used each day

Daily cost variation

1.9

Coefficient of variation; lower is steadier

Active days in span

67%

First to last active day