Show HN: Claude Code's $200 plan is a 17× subsidy on the raw API

A developer reverse-engineered their own Claude Code logs to reveal that 64% of the $3,371 monthly bill at Opus 4.7 list rates goes to re-reading the same context every turn, not generating new content. Hidden reasoning tokens account for 84% of output costs and 60% of all re-read data, with caching already serving 98% of input yet failing to eliminate the re-read overhead. The analysis shows Claude Code's $200 plan represents a 17× subsidy on raw API costs, as the same workload without caching would cost approximately $22,630.

Reverse-engineer a month of your own local Claude Code logs ~/.claude/projects/ / .jsonl into where the tokens, time, and cost actually go — and run it on yours. Reads only local logs ; nothing is sent anywhere. What it found one month of my own logs — 181 sessions, 25,564 model calls : You don't pay to generate, you pay to re-read.~29M unique tokens →4.35B billed ~150× , because every turn re-sends the whole ~173K-token context.- The bill is 84% input / 16% output— and re-reading the same context is64%of it.- The biggest line is the one you never see: hidden reasoningis 84% of outputand~60% of everything re-read.~$3,371for the month at Opus 4.7 list rates. Caching already serves 98% of input — and re-reading isstill64% of the bill.Full write-up all the tables, the why, the main-thread-vs-subagent split → coralbricks.ai/blog/claude-code-token-xray pip install -r requirements.txt just tiktoken python3 token time breakdown.py python3 cost.py python3 main vs sidecar.py python3 reread breakdown.py tiktoken is OpenAI's tokenizer, not Claude's, so token proportionsare reliable to ~±15%, not Claude-exact. The billed-token counts in cost.py come straight from the API usage blocks and are exact. From cost.py on my logs, priced at Opus 4.7 list rates: | Line item | Cost | Share | |---|---|---| | Input — re-reading context cache reads | $2,176 | 64% | | Input — cache writes | $682 | 20% | | Input — fresh uncached | $2 | 0% | | Output — reasoning | $429 | 13% | | Output — tool calls + summaries | $82 | 2% | Total | $3,371 | 100% | Caching is the only thing keeping it sane — without it the same work lists at ~$22,630 ~7× . Your numbers will differ; that's the point. Run it on yours. — the headline table: tokens marked input/output token time breakdown.py and wall-clock time per activity reasoning, running commands, writing tool calls, subagents, summaries, reading/searching, editing plus the passive-context rows system prompt + tools, attachments, the typed prompt, injected reminders . One pass, so tokens and time stay consistent. Reasoning isn't stored in plaintext only an encrypted signature , so it's recovered by subtraction: output − tool calls − summaries . Time is reconstructed from event timestamps.— billed token totals cache reads / cache writes by TTL / fresh input / output priced at Opus 4.7 list rates, plus the no-caching counterfactual. cost.py — splits the human-driven main thread from spawned subagents logged under nested main vs sidecar.py /subagents/ .jsonl ; reports billed tokens, per-model mix, cache-hit rate, turns per agent per session for the main thread, per subagent for the sidecar , and cost for each, plus the combined total.— per-activity reread breakdown.py cumulative input: replays each session's context growth to show what each kind of context costs once it's re-read every turn. Reports unique vs re-read tokens per activity reasoning is the biggest re-read line . The replay is scaled to the measured billed input exact ; the per-activity split is a model. - One person's month on one machine — directional, not a benchmark. Claude Code is dynamic, so your split will differ. That's the point: run it on yours. - A generation-time gap also includes the model reading its context before it writes; Bash time is real execution commands auto-approved , but code run in the background or a separate terminal isn't counted. - The system-prompt row is estimated from each session's first cache write. If this helped you see where your Claude Code tokens, time, and cost actually go, please ⭐ the repo https://github.com/Coral-Bricks-AI/coral-ai — it helps others find it. Curious what your re-read share comes out to. Apache 2.0 — see the repository LICENSE /Coral-Bricks-AI/coral-ai/blob/main/LICENSE .