What are AI Tokens?

Tokens are the small chunks of text an AI model reads and writes. A token is typically a short word or a piece of a word. Model pricing, speed and context limits are all measured in tokens rather than words.

Updated July 22, 2026·4 min read·~7 min to learn·The Tool Money Lab editorial team
On this page

Definition

A token is the unit of text an LLM processes — typically 3-4 characters or roughly three-quarters of an English word. Prompts, replies and pricing are all measured in tokens.

Simple explanation

Instead of reading whole words, an LLM reads pieces called tokens. 'ChatGPT' might be split into 'chat' and 'GPT'. Numbers, punctuation and rare words often use multiple tokens.

You never need to count tokens by hand — but knowing they exist explains why some prompts are surprisingly expensive.

Why it matters

Everything about running an LLM — cost, speed, context limits — is measured in tokens. If you build with AI, tokens are the meter.

How it works

  1. 1
    Tokenise
    Text is split by a tokenizer into vocabulary IDs.
  2. 2
    Feed
    The model processes IDs, not characters.
  3. 3
    Generate
    It outputs one token at a time.
  4. 4
    Bill
    You are charged per input token and per output token.

Real examples

Products named for illustration only. Inclusion is not an endorsement.

  • OpenAI pricing
    Charged per million input and output tokens, priced separately.
  • Anthropic pricing
    Same input/output split, often with cache discounts.

Advantages

  • Consistent unit across models and providers.
  • Enables usage-based pricing at fine granularity.

Limitations

  • Token counts are hard to estimate by eye.
  • Different tokenizers count the same text differently.
  • Costs balloon on long documents if not planned for.

Common misunderstandings

  • Claim
    One token equals one word.
    Reality
    Often it does, but many words split into multiple tokens.
  • Claim
    Only inputs cost money.
    Reality
    Outputs usually cost more per token than inputs.

Frequently asked questions

How many tokens is a page of text?

Roughly 500-800 tokens per standard page.

Why do outputs cost more?

Generating a token is more compute-intensive than reading one.

Can I reduce token usage?

Yes — concise prompts, targeted retrieval and short reply formats all help.

The Tool Money Lab perspective

The teams that treat tokens as a budget line item are the same teams that ship AI features on time and on cost. Ignoring token accounting is the fastest way to build a product that cannot scale.

Conclusion

Tokens are the atoms of language models: the unit of reading, writing, cost and speed.

Design for token efficiency and the economics of AI features stay predictable.

Keep learning
Relevant reviews
Relevant comparisons
Buying guides
From our editorial team
Intelligence Brief

Stay Ahead of AI

Receive our weekly Intelligence Brief. Independent AI reviews, comparisons, new tools and practical recommendations delivered every Friday.

  • New AI tools
  • Honest reviews
  • Best AI deals
  • New comparisons
  • Industry trends
  • No spam.