RTK reports token savings, but our cost benchmarks disagree
An analysis of the 'Rust Token Killer' (RTK) tool suggests that its claims of significantly reducing AI coding costs are often overstated or ineffective. Benchmarking tests showed that while the tool compresses terminal output, it does not consistently lead to cheaper or higher-quality AI coding sessions.
Why it matters
This highlights the gap between viral developer tools and actual performance, warning users to verify efficiency claims before integrating them into production workflows.
Download PNG RTK (Rust Token Killer) filters and compresses terminal output before the AI agent reads it. With over 79k GitHub stars today, RTK is one of the most popular tools to make AI coding cheaper.
One X post saying RTK could cut Claude Code tokens by up to 60% reached 313K views.
Yet JetBrains’s SkillsBench run found no savings . The README has a disclaimer:
RTK cuts up to 90% of the bash output your agent reads. […] it is not the same as cutting your bill by 90%.
So “less terminal output” is not the same as “cheaper AI coding”. It can help, be a no-op, or backfire (more turns or lower quality). In this post, we present our findings after several days and over $1,500 spent on tokens.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in