easyAI Engineering

What are tokens and why do they matter for cost and limits?

Q: What are tokens and why do they matter for cost and limits?

**TL;DR.** Tokens are the **sub-word units** a model reads and writes (~4 English characters each). They are the currency of everything: **pricing** (per input/output token), **context limits**, and **latency** (one forward pass per output token). inter view pad _is _great ! <line class='d-edge' x1='196' y

540 views

Understand the problem

Tokenization is the unit of everything: pricing, context limits, latency and even model quirks.

tokenstokenizationpricingfundamentals

Attempt it yourself

Sketch your approach before reading the solution — that's what interviews test.

Stuck? AI Nudge Available

Get a conceptual hint to guide your logic without spoiling the final implementation.

Study the solution

The solution is waiting

Give it an honest attempt first — then compare your thinking with the full walkthrough.

Read the code

Counting tokens before sending

import { countTokens } from "@anthropic-ai/tokenizer";

const prompt = buildPrompt(docs, question);
const n = countTokens(prompt);

// budget check before the call, not after the invoice
if (n > MAX_INPUT_BUDGET) {
  docs = rankAndTrim(docs, MAX_INPUT_BUDGET - countTokens(question));
}

Join the discussion

Discussion (0)

No responses yet. Be the first to share what you think.

What is RAG and why use it instead of fine-tuning for knowledge?

What are evals and why does every LLM feature need them?