Your LLM never reads your words — it reads tokens. And almost every surprise on your AI bill traces back to that one fact. Here's the breakdown 👇 Here's the thing almost nobody internalizes about large language models: Claude never reads your words.
Source: [Dev.to](https://dev.to/thestackunderflow_3b3b3b6/how-llm-tokens-work-and-why-they-explain-your-ai-bill-46b)