RayKeeper

Cache hit rate

98%

Input served from cache

Higher than 94% of developers

Cache reuse

50.9×

Reads per cached token

Higher than 79% of developers

Cost per 1M tokens

$0.96

Blended cost across all tokens

Lower than 35% of developers

Output share

0%

Tokens generated as output

Higher than 86% of developers

Parallel tools

0%

Days with 2+ tools · 1.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.3

Distinct models used each day

Daily cost variation

0.8

Coefficient of variation; lower is steadier

Active days in span

72%

First to last active day