Lil Z

Cache hit rate

96%

Input served from cache

Higher than 53% of developers

Cache reuse

63.5×

Reads per cached token

Higher than 84% of developers

Cost per 1M tokens

$0.58

Blended cost across all tokens

Lower than 87% of developers

Output share

0%

Tokens generated as output

Higher than 64% of developers

Parallel tools

73%

Days with 2+ tools · 2.5 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

5.2

Distinct models used each day

Daily cost variation

1.3

Coefficient of variation; lower is steadier

Active days in span

83%

First to last active day