TC5-Tian

Cache hit rate

95%

Input served from cache

Higher than 39% of developers

Cache reuse

18.5×

Reads per cached token

Higher than 35% of developers

Cost per 1M tokens

$1.41

Blended cost across all tokens

Lower than 19% of developers

Output share

0%

Tokens generated as output

Higher than 77% of developers

Parallel tools

22%

Days with 2+ tools · 1.2 avg/day

Parallel machines

0%

Days with 2+ machines · 1.0 avg, 1 max

Models per active day

2.8

Distinct models used each day

Daily cost variation

0.6

Coefficient of variation; lower is steadier

Active days in span

90%

First to last active day