Dean Shabi

Cache hit rate

96%

Input served from cache

Higher than 58% of developers

Cache reuse

264.3×

Reads per cached token

Higher than 95% of developers

Cost per 1M tokens

$0.72

Blended cost across all tokens

Lower than 64% of developers

Output share

0%

Tokens generated as output

Higher than 51% of developers

Parallel tools

33%

Days with 2+ tools · 1.4 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.2

Distinct models used each day

Daily cost variation

2.7

Coefficient of variation; lower is steadier

Active days in span

84%

First to last active day