150M Tokens in One Week: My Codex Usage with RTK
After consuming 350M tokens last week, adding RTK brought it down to 150M — a 57% reduction. Real usage data and experience.
150M Tokens in One Week: My Codex Usage with RTK
Background
Last week I logged 350M tokens consumed over 11 days and mentioned I'd try RTK to optimize. One week later, the results are in: 150M tokens.
Same workflow — Codex 5.4 and 5.3-codex mixed, the same write-review-revise loop, similar project complexity. The only change: RTK.
Data Comparison
| Metric | Last Week (No RTK) | This Week (With RTK) | Change |
|---|---|---|---|
| Token consumption | 350M | 150M | -57% |
| Models used | 5.4 + 5.3-codex | 5.4 + 5.3-codex | Same |
| Workflow | Write-review-revise loop | Same | Same |
| Dev tasks | Feature work, doc iteration, code review | Same | Same |
From 350M down to 150M — 200M tokens saved. RTK's compression performed better than I expected.
RTK Experience
Biggest takeaway: invisible, but effective
Honestly, after a week with RTK, I barely notice it's there. It's a transparent proxy — AI tools do exactly what they did before, and output quality feels unchanged.
But when you check the usage stats, the difference speaks for itself.
Where compression shines
git diff/git status: Large project diffs are extremely verbose. RTK compresses them into a concise version that AI can understand just as well- Test output: Massive repetitive pass/fail logs get folded, keeping only key information
- Error logs: Stack traces get truncated to essential frames instead of stuffing the entire call chain into context
- File listings:
find,lsoutputs get grouped by directory with deduplication
Where it doesn't make much difference
- Direct coding conversations — token usage is already low, not much to compress
- Short command outputs — minimal difference before and after compression
What the saved tokens mean
- Cost cut in half. At last week's burn rate, a month would be over a billion tokens. The savings are real money
- Context window lasts longer. The same context window fits more conversation turns, so long tasks don't get truncated as easily
- Less anxiety about context limits. No more worrying "this diff is too long, will it blow up the context"
Conclusion
Last week I said "next week's post will have the test results — let's see if RTK is a cost-saver or just hype." The verdict is clear: it's a cost-saver.
57% token reduction, zero learning curve (rtk init and you're done), virtually no impact on the development experience. For anyone heavily using Codex or similar AI coding tools, RTK is essentially a must-install.