Stewart LI

Cache hit rate

96%

Input served from cache

Higher than 64% of developers

Cache reuse

5995.7×

Reads per cached token

Higher than 99% of developers

Cost per 1M tokens

$0.68

Blended cost across all tokens

Lower than 71% of developers

Output share

0%

Tokens generated as output

Higher than 49% of developers

Parallel tools

31%

Days with 2+ tools · 1.3 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.6

Distinct models used each day

Daily cost variation

3.2

Coefficient of variation; lower is steadier

Active days in span

67%

First to last active day