---
id: "prereq-llm-token-economics"
type: "prerequisite"
source_timestamps: ["00:12:24", "00:19:29"]
tags: ["economics", "llm-basics"]
related: ["concept-predictive-token-budgeting", "concept-transcript-compaction"]
reason: "Required to understand why transcript compaction and predictive budgeting are critical for production systems."
sources: ["s46-anthropic-25b-leak"]
sourceVaultSlug: "s46-anthropic-25b-leak"
originDay: 46
---
# Understanding LLM Token Economics

## Why This Matters
To understand the necessity of [[concept-predictive-token-budgeting|predictive budgeting]] and [[concept-transcript-compaction|transcript compaction]], you must understand:

- how LLM **context windows** work (finite token capacity per call)
- how **token usage scales costs linearly** (and sometimes super-linearly with longer context)
- how **input vs. output tokens** are typically priced differently

## Required Knowledge
- A token is roughly ¾ of a word in English; counts vary by tokenizer.
- Each conversation turn includes the *entire* prior context — costs grow as conversations lengthen, hence the need for compaction.
- Provider-side per-token pricing means runaway loops can cost real money quickly.

## Why It's a Prerequisite
Without this baseline, the cost-management primitives in the source read as arbitrary engineering rather than economic necessity.