AI article
Our Claude Code agent's median run used 79.8M tokens, 97% of them cache reads. How many does one run of yours use?
Community description: Thirteen full runs of our Claude Code agent, each started by the same short go-ahead prompt from its...
Dev.to | Oct 7, 2026 | Rulestack
Automated excerpt
Total per run: median 79. 8M, smallest 12. 3M, largest 182. 9M. Output: median 167,540 tokens per run, about 0. 2% of the total. Uncached input: a median of 1,176 tokens per run.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.