Phantom

Cache hit rate

96%

Input served from cache

Higher than 65% of developers

Cache reuse

25.5×

Reads per cached token

Higher than 53% of developers

Cost per 1M tokens

$0.72

Blended cost across all tokens

Lower than 65% of developers

Output share

0%

Tokens generated as output

Higher than 83% of developers

Parallel tools

3%

Days with 2+ tools · 1.0 avg/day

Models per active day

2.8

Distinct models used each day

Daily cost variation

0.8

Coefficient of variation; lower is steadier

Active days in span

100%

First to last active day