Customer Impact

SEO & GEO

What is a token in AI? An explanation for marketers

Copy for AI

A token is the smallest piece of text an AI model splits language into.

Often that’s a word, but it can also be part of a word, a punctuation mark or a space.

Everything a language model does, from reading your question to building an answer, happens in tokens. Not in letters, and not in words.

Below: how tokenization works, why you pay per token and what it means for AI visibility.

What is a token exactly?

A token is the building block a language model uses to process text: a fragment the model treats as one unit.

A model doesn’t read sentences the way we do. It first chops text into a series of tokens, then works only with those pieces.

How big a token is varies. Short, common words like “the” or “and” are usually a single token. Longer or rarer words get split into several pieces.

As a rule of thumb, one token in English is roughly four characters. So a word like “tokenization” can easily be two or three tokens.

Here’s the key thing to remember: the model doesn’t think in words or meanings the way you do. It thinks in these numerical building blocks.

Each token gets a number. Based on that sequence of numbers, the model predicts which next piece is most likely.

That’s how an answer takes shape, token by token.

How does tokenization work?

Tokenization is the process that converts text into a series of tokens before the model gets to work with it.

It follows a fixed system the model learned during training. So the same text is always chopped up the same way.

The system looks for common text patterns. Frequent words and word parts get their own token, while rare words fall apart into smaller pieces. That explains a few things that seem odd at first sight:

  • Spaces and punctuation count. A space before a word often belongs to that token, and a period or comma can be its own token.
  • Numbers and code split differently. A long number or a piece of programming code is sometimes broken into a surprising number of tokens.
  • Languages differ. Languages that appear less in the training data are on average chopped into more tokens, which makes them “more expensive” to process.

But tokenization has nothing to do with meaning. That comes in a later step, which we explain in what embeddings are for marketers.

Why are costs and limits measured in tokens?

Tokens are a language model’s unit of computation. So both its price and its limits are expressed in them.

If you use an AI model through an API, you usually pay per thousand tokens. And you pay for two streams: the tokens you put in (your question plus context) and the tokens the model gives back (the answer).

A model’s working-memory limit is measured in tokens too. That limit is called the context window: the maximum number of tokens a model can weigh at once for one answer.

Anything outside it simply doesn’t exist for the model at that moment.

How that works, and why a large window isn’t the same as a good memory, is covered in what a context window is.

Here’s what that means for you. An AI system always has limited space. Your content shares that space with the user’s question and with fragments from other sources.

So compact, clear text takes up fewer tokens and is easier to carry along.

What do tokens mean for your AI visibility?

For your visibility, it isn’t the number of tokens on your page that counts. It’s whether your core answer is up front and compact, so a model can pick it up and cite it efficiently.

When someone asks ChatGPT, Perplexity or Google AI Overviews a question, the system retrieves relevant pieces of the web. It converts them into tokens and places them together in the context window, alongside other sources.

That means your content is competing for limited space.

So here’s the lesson:

A long page where the real answer only comes at the bottom burns lots of tokens before the core comes into view. It risks having that very part left out.

Content that gives a complete, self-contained answer up front is cheaper to process. It’s also more likely to actually end up in the AI answer.

This ties in with the broader approach in our guide on generative engine optimization.

In practice: put the answer at the top of each section, write in clear chunks that each answer one question, and be dense where you can.

Not to save tokens, but because clear, compact content beats verbose text.

Don’t fixate on tokens

Your token count is a technical measure, not a growth metric.

Some tools love to show how many tokens a text contains. But that number says nothing about whether you’ll get found or chosen.

What does count is whether your content brings the right B2B buyer to you. In B2B, with long sales cycles and several decision-makers, one qualified lead outweighs a hundred mentions.

That’s why we don’t steer on tokens, impressions or other vanity figures at Customer Impact. We steer on leads and revenue.

Want to tackle this properly? That’s what our GEO service for AI search engines does, where tokens and context windows are one part of the GEO craft.

Frequently asked questions

Is a token the same as a word?

No. A token is often a word, but short words are usually a single token and longer or rarer words are split into multiple tokens. Spaces and punctuation can also be separate tokens. As a rule of thumb, one token corresponds roughly to a few characters.

How many tokens are in an average text?

Roughly, a hundred words of English is about 130 to 150 tokens. The exact number depends on the model and on how rare the words are.

Why do I pay per token with an AI model?

Because tokens are the unit of computation a model works with. Every token you input and every token the model gives back costs computing power. Providers pass that cost on per number of tokens, usually per thousand, split into input and output.

Should I optimize my content on token count?

No, that is not a meaningful goal. Optimize for clarity and for a complete answer that is up front. That automatically makes your content efficient to process and increases your chance of an SEO and AI citation, without having to steer on a token counter.

Ready to become visible in AI?

Where do you stand today with your content and your findability in AI search engines? We’ll tell you where your biggest opportunities are.

We’re a small team and we move fast. Tell us where you stand today and you’ll get concrete steps, not a report that gathers dust.

Free website scan

Enter your website and get an automatic scan within minutes, with concrete technical and SEO improvements. No sales pitch.

Where should we send your report?

We only use your details for your scan. No spam, unsubscribe anytime.