One 3-hour session ate 18% of my Kimi Code WEEKLY quota. Support says it's "normal." So I audited Claude and Codex on the same machine —the numbers say otherwise.

View original

ClaudeModel releasePlans & limitsOpen source

Heat trend

New

Latest 24h versus previous 24h · 7-day curve

The percentage is based on available heat signal, not comment count or independent people.

Why it matters

Claude model activity is surfacing — worth tracking for capability changes, ecosystem impact, and availability.

AI summary

A developer reported that a single 3-hour session with Kimi Code consumed 18% of their WEEKLY quota, which support deemed "normal." However, an audit comparing Kimi Code with Claude Code and Codex on the same machine revealed significant discrepancies. Kimi Code processed 10.2M tokens, consuming ~90% of the WEEKLY quota, while Claude Code processed 677M tokens over 5 weeks with a cheaper plan, suggesting an issue with Kimi Code's quota economics rather than model quality.