TokenLanding

What are LLM API tokens?

LLM APIs charge and limit usage in tokens—chunks of text the model reads. Learn why token count differs from characters and words, and how it affects your bill.

2026-04

TL;DR

Tokens are chunks of text (~4 characters) that LLM APIs use for billing and rate limits. Token count differs from word count and directly affects your bill.

Why not just count characters or words?

Tokenizers split text differently per model family. English averages roughly four characters per token, but code, Chinese, or long URLs can be denser or sparser. APIs standardize on tokens so limits and invoices line up with what the model actually processes.

What shows up on your invoice

Most bills list input tokens and output tokens separately. Hidden context—like long system prompts or retrieved documents—still counts toward context window limits. That is why "we only sent a short question" can still burn a large prompt when RAG is enabled. For a detailed walkthrough of how providers price these tokens, see the AI token pricing guide.

Blended products and honesty

Some vendors blend premium and economy capacity behind one meter. If that applies to you, say so in plain language—see hybrid token lanes and our disclosure.

FAQ

+What is a token in LLM APIs?
A token is a chunk of text—roughly 4 characters or 0.75 words in English—that LLM APIs use as the basic unit for billing and rate limits.
+Why does token count differ from word count?
Tokenizers split text into subword pieces, not whole words. Common words may be one token, but longer or rare words get split into multiple tokens. This makes token count different from word count.
+How do tokens affect my LLM API bill?
LLM APIs charge per token for both input and output. Output tokens cost more. The total token count of your prompts plus completions directly determines your bill.

Ready to cut your token bill?

Token Landing — hybrid AI tokens, Claude-class UX, saner spend

Related reading