mSounak

Cache hit rate

95%

Input served from cache

Higher than 48% of developers

Cache reuse

23.5×

Reads per cached token

Higher than 49% of developers

Cost per 1M tokens

$1.16

Blended cost across all tokens

Lower than 24% of developers

Output share

0%

Tokens generated as output

Higher than 86% of developers

Parallel tools

2%

Days with 2+ tools · 1.0 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

1.9

Coefficient of variation; lower is steadier

Active days in span

37%

First to last active day