a

Cache hit rate

96%

Input served from cache

Higher than 65% of developers

Cache reuse

25.3×

Reads per cached token

Higher than 53% of developers

Cost per 1M tokens

$0.70

Blended cost across all tokens

Lower than 68% of developers

Output share

1%

Tokens generated as output

Higher than 92% of developers

Parallel tools

0%

Days with 2+ tools · 0.0 avg/day

Models per active day

2.1

Distinct models used each day

Daily cost variation

1.0

Coefficient of variation; lower is steadier

Active days in span

61%

First to last active day