# RTK saves tokens, not money

> A $1,500 benchmark on Terminal-Bench 2.1 shows the most popular AI-cost-cutting tool barely moves the bill, and sometimes raises it.
- Title: RTK saves tokens, not money · Quesma | Shortify
- Summary: A $1,500 benchmark on Terminal-Bench 2.1 shows the most popular AI-cost-cutting tool barely moves the bill, and sometimes raises it. Removed terminal output…
- Keywords: ai coding, benchmarks, token costs, claude code, developer tools, technology, startups, RTK, saves, tokens, money, Quesma
- Source: Quesma — https://quesma.com/blog/does-rtk-make-ai-coding-cheaper
- Author: Bartosz Kotrys, Jacek Migdal
- Published: 2026-09-11T08:00:00+00:00
- Read time: 2 min
- Topics: ai coding, benchmarks, token costs, claude code, developer tools, technology, startups
## 79k stars, one big claim
RTK filters terminal output before an AI agent reads it. One X post claiming it cuts Claude Code tokens by 60% hit 313,000 views.
## The README says otherwise
RTK's own docs draw the line the social posts erase. JetBrains ran SkillsBench and found no savings at all.

> RTK cuts up to 90% of the bash output your agent reads. […] it is not the same as cutting your bill by 90%.
## What RTK actually does
It rewrites Git, test, package and file commands into terser output. An ls -la loses the owner and date, keeping names, sizes and permission bits.
## The test setup
Claude Code with Fable 5.0 and OpenCode with DeepSeek V4 Pro, five runs each way per task on Terminal-Bench 2.1. Final count: 1,740 attempts, over $1,500 in tokens.
## A 5% swing each way
Total spend fell 5% for Fable and rose 5% for DeepSeek. Pass rates dipped slightly with RTK, by 1% and 2%.
## Weight every task equally
One expensive task can drown out dozens of cheap ones. Averaging per-task changes, Fable was 1% more expensive and DeepSeek rose 17%.
## One task carried it all
Almost all of Fable's savings came from winning-avg-corewars, where RTK finished in half the turns. Across every other task, savings were under 1%.
## The savings counter lies
RTK's gain metric is raw bytes minus filtered bytes, divided by four. It reported 349 million tokens saved across DeepSeek runs, an 89% cut, with no cheaper tasks to show for it.
## Credit for output never asked for
In train-fasttext the agent ran head -1 twice. RTK compared those two one-line reads against the whole file and claimed 120.5 million tokens saved each time.

> Those two calls accounted for 69% of the comparison's savings counter
## A rewrite loop that cost 9x
A find flag RTK 0.45.0 did not support got rewritten into a command that refused to run. The agent hit 339 consecutive errors in 12 minutes. Fixed in 0.46.0, after these runs.
## Terminal output is a sliver
Without RTK, terminal output was 7% of Fable's input tokens and 26% of DeepSeek's. Read, Grep and Glob are separate tools that bypass RTK entirely.
## Caching already did the work
After each turn the context is cached, so later reads cost a tenth of normal input for Fable and a thirtieth for DeepSeek. Cache reads were 94% of input but 30% of the bill.
## More turns eat the savings
DeepSeek turns held 7% less input each, but there were 18% more of them. One extra turn can cost more than all the compression saved.
## Key takeaway

Removed terminal output is not saved money. Judge a token-saving tool by the total bill per passing task, not by the savings counter it prints.