Do output compression tools still matter with newer AI models?

We tried to answer this question by validating one of the most popular tool in this area: RTK (Rust Token Killer).

We used Claude Code with Fable 5.0, and OpenCode with DeepSeek V4 Pro 0813 through OpenRouter on Terminal-Bench 2.1

Research and results:

https://quesma.com/blog/does-rtk-make-ai-coding-cheaper/