Token Economics

How one developer out-eats a whole chat plan

A viral post asked: how can a single software developer consume more tokens than a top-tier AI subscription includes? The answer isn't fraud — it's arithmetic. Agents re-read context on every step. Drag the sliders and watch the burn.

Each cube = 1M tokens/day. Pink tower: agentic coding. Green tower: chat use. Drag to rotate.

Four multipliers chat users never see

1

Context is re-sent every step

LLM APIs are stateless. A 40-step agent session with 60k tokens of files, history, and instructions in context re-transmits that payload 40 times: 2.4M input tokens for one task — even though you only "chatted" once. Prompt caching discounts the cost, but the tokens are still processed and metered.

2

Tool output is input

Every file read, grep result, test log, and stack trace comes back into the model as input tokens. A single failing test suite can dump 20k tokens of logs into context — then get re-sent on all subsequent steps (multiplier 1 compounds it).

3

Retries and self-correction

Agents try, fail, read the error, and try again. A task that a human describes in 50 tokens can take an agent 15 attempts. Failure is cheap in dollars but expensive in tokens — and it's invisible in the "one prompt" mental model.

4

Parallel agents & background jobs

Power users run 3–10 agents concurrently, plus scheduled jobs (CI review, issue triage) that consume tokens while they sleep. Multiply everything above by the fleet size and 24h uptime.

Worked example: the honest napkin math

One refactoring task: 60k context × 40 steps = 2.4M input plus ~150k output. Eight tasks a day → ~20M tokens/day, or ~600M tokens/month for one engaged developer. Run three parallel agents and you're near 2B tokens/month — per person.

So when vendors report trillions of tokens processed, you don't need inflated-metrics theories to explain it: 100 developers at 2B/month = 200B tokens/month from a single mid-size customer. The skepticism in the original post is healthy — but the multiplication checks out. The right question isn't "are the numbers real?" — it's "how much of that burn is productive vs. retry waste?"

Enjoy this tool? Build your own with Super