John Silva

Cache hit rate

97%

Input served from cache

Higher than 78% of developers

Cache reuse

1647.0×

Reads per cached token

Higher than 97% of developers

Cost per 1M tokens

$0.69

Blended cost across all tokens

Lower than 71% of developers

Output share

0%

Tokens generated as output

Higher than 52% of developers

Parallel tools

3%

Days with 2+ tools · 1.0 avg/day

Parallel machines

10%

Days with 2+ machines · 1.1 avg, 3 max

Models per active day

2.6

Distinct models used each day

Daily cost variation

4.2

Coefficient of variation; lower is steadier

Active days in span

63%

First to last active day