How do you count tokens before calling an API?
PICTURE THIS: A SENTENCE BECOMES TOKENS
The model does not read letters like humans. It reads these pieces, then predicts the next one.
Simple meaning
Use the same tokenizer the model uses, such as tiktoken for many OpenAI models.
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
question about Tokens.
trade-offs, and what you would actually do on a GenAI / LLM project - not buzzwords.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1Use the same tokenizer
the model uses, such as tiktoken for many OpenAI models.
- 2Character heuristics like four
characters per token are only rough.
- 3Count messages after chat-template
formatting, including tools and retrieved context.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
Use the same tokenizer the model uses, such as tiktoken for many OpenAI models. Character heuristics like four characters per token are only rough.