apinrdw

Cache hit rate

97%

Input served from cache

Higher than 85% of developers

Cache reuse

38.4×

Reads per cached token

Higher than 70% of developers

Cost per 1M tokens

$1.11

Blended cost across all tokens

Lower than 27% of developers

Output share

1%

Tokens generated as output

Higher than 92% of developers

Parallel tools

3%

Days with 2+ tools · 1.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.9

Distinct models used each day

Daily cost variation

0.8

Coefficient of variation; lower is steadier

Active days in span

61%

First to last active day