Hieu Tran

Cache hit rate

96%

Input served from cache

Higher than 67% of developers

Cache reuse

167.4×

Reads per cached token

Higher than 92% of developers

Cost per 1M tokens

$0.83

Blended cost across all tokens

Lower than 47% of developers

Output share

0%

Tokens generated as output

Higher than 80% of developers

Parallel tools

81%

Days with 2+ tools · 1.8 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

3.0

Distinct models used each day

Daily cost variation

1.3

Coefficient of variation; lower is steadier

Active days in span

68%

First to last active day