samscarrow

Cache hit rate

95%

Input served from cache

Higher than 44% of developers

Cache reuse

39.5×

Reads per cached token

Higher than 71% of developers

Cost per 1M tokens

$0.88

Blended cost across all tokens

Lower than 41% of developers

Output share

1%

Tokens generated as output

Higher than 89% of developers

Parallel tools

23%

Days with 2+ tools · 1.2 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.0

Distinct models used each day

Daily cost variation

2.2

Coefficient of variation; lower is steadier

Active days in span

40%

First to last active day