Models don't read words — they read tokens. A Chinese character is typically 1-2 tokens; an English word is 1-3. The context window is the token limit per request. Inference is using a model; training is teaching one. What you do every day is inference.
Models charge by tokens, not characters. The BPE algorithm starts from individual bytes and repeatedly merges the most frequent adjacent pair to build a vocabulary. English 'understanding' might be 1-2 tokens, but Chinese '理解' could take 2-3 — same meaning, higher cost.
Claude Code loads the system prompt, MEMORY.md, CLAUDE.md, MCP tool names, and skill descriptions before you type your first word. This post breaks down the startup context, what each of six extension features costs, and how to control auto-compaction with /compact, /autocompact, and autoCompactWindow.