swgn100k

Cache hit rate

95%

Input served from cache

Higher than 41% of developers

Cache reuse

37.3×

Reads per cached token

Higher than 67% of developers

Cost per 1M tokens

$1.43

Blended cost across all tokens

Lower than 18% of developers

Output share

1%

Tokens generated as output

Higher than 88% of developers

Parallel tools

69%

Days with 2+ tools · 1.8 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

3.2

Distinct models used each day

Daily cost variation

1.4

Coefficient of variation; lower is steadier

Active days in span

95%

First to last active day