NanduRajak

Cache hit rate

98%

Input served from cache

Higher than 90% of developers

Cache reuse

45.8×

Reads per cached token

Higher than 75% of developers

Cost per 1M tokens

$0.80

Blended cost across all tokens

Lower than 51% of developers

Output share

1%

Tokens generated as output

Higher than 89% of developers

Parallel tools

100%

Days with 2+ tools · 2.0 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

3.4

Distinct models used each day

Daily cost variation

0.3

Coefficient of variation; lower is steadier

Active days in span

100%

First to last active day