n4nAI

Topic

Tokens & Tokenization

7 posts on tokens & tokenization — part of glossary on the n4n AI blog.

GlossaryDefinition

What is a token in AI? A plain-English definition

A precise technical definition of tokens in AI, covering tokenization mechanics, vocabulary design, context limits, and practical implications for LLM engineering.

5 min read
GlossaryComparison

Tokens vs words: the real difference, with examples

Understand the practical difference between tokens and words for LLM engineering — billing, context limits, latency, and multilingual behavior with concrete examples.

5 min read
GlossaryAnalysis

How tokenizer choice changes your inference bill

Tokenizer choice directly changes token counts — and your inference bill. A practical breakdown of how BPE vs Unigram, code vs prose, and multilingual text shift costs across models.

6 min read
GlossaryGuide

How tokenization turns text into numbers

A practical guide to how tokenization works in LLMs, covering BPE, WordPiece, special tokens, and engineering tradeoffs with code examples.

4 min read
GlossaryHow-to

How to count tokens before sending an API request

Learn how to count tokens locally before making LLM API calls to control costs, avoid truncation, and optimize context windows.

4 min read
GlossaryDefinition

How many tokens is one word, on average?

A precise answer to how many tokens a word averages, with tokenizer mechanics, model differences, and practical estimation techniques for LLM engineers.

5 min read
GlossaryTutorial

Byte pair encoding explained with real examples

Learn byte pair encoding from scratch with runnable Python code — build a BPE tokenizer step by step and see exactly how subword tokenization works.

4 min read