What Does 26 Trillion Tokens Look Like?

Monthly leaderboards now show autonomous agents burning tens of trillions of tokens. Each orb below is an app category sized by monthly token burn — tap orbs to inspect, and use the sliders to translate trillion-token scale into dollars, books, and human lifetimes.

Tap an orb
to inspect its token appetite
drag to orbit · tap orbs to select

Token Scale Translator

Est. monthly spend
Equivalent books
Years for a human to read
Tokens per second

Why agents devour tokens

A chat reply might use 2k tokens. One agent step re-sends the entire conversation + tool outputs as input every iteration. A 50-step coding session can consume 5–10M tokens — 2,500× a chat message. Persistent-memory agents with 40+ tools multiply this further.

The input/output asymmetry

Agent workloads are typically 90–98% input tokens (context re-reads) and only 2–10% output. That's why providers price input 3–5× cheaper and why prompt caching — reusing identical context prefixes — can cut agent bills by 50–90%.

Are the numbers inflated?

Skeptics note token counts can be gamed: retries, cache reads counted as usage, and synthetic-data generation all inflate figures. Healthy skepticism: check whether a leaderboard counts cached input separately before treating tokens as adoption proof.

The math in this tool

Books assume ~90k tokens each (≈70k words). Human reading: 250 words/min ≈ 333 tokens/min, no sleep. Cost = tokens × blended $/1M. At 26T tokens and $0.80/1M, that's $20.8M/month of compute.

Enjoy this tool? Build your own with Super