datafndr

Cache hit rate

98%

Input served from cache

Higher than 96% of developers

Cache reuse

2145.6×

Reads per cached token

Higher than 97% of developers

Cost per 1M tokens

$1.29

Blended cost across all tokens

Lower than 22% of developers

Output share

0%

Tokens generated as output

Higher than 44% of developers

Parallel tools

29%

Days with 2+ tools · 1.3 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

1.6

Coefficient of variation; lower is steadier

Active days in span

86%

First to last active day