chatt2chatt

Cache hit rate

92%

Input served from cache

Higher than 9% of developers

Cache reuse

246.3×

Reads per cached token

Higher than 94% of developers

Cost per 1M tokens

$0.89

Blended cost across all tokens

Lower than 37% of developers

Output share

1%

Tokens generated as output

Higher than 96% of developers

Parallel tools

8%

Days with 2+ tools · 1.1 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

1.7

Distinct models used each day

Daily cost variation

1.3

Coefficient of variation; lower is steadier

Active days in span

77%

First to last active day