Token

A token is the unit of text a language model processes. It’s neither a word nor a character, it’s a chunk somewhere in between, defined by the model’s tokenizer.

For English text, a rough rule of thumb: 1 token ≈ 4 characters ≈ 0.75 words. So a 1,000-word document is roughly 1,300-1,400 tokens. A short email might be 200 tokens. A novel is 100,000+.

Numbers, code, and non-English text tokenise differently, sometimes more efficiently, sometimes less.

Why tokens matter

You are billed per token. As at October 2026, Claude API pricing in USD per million tokens (Anthropic pricing):

Model	Input ($/1M)	Output ($/1M)
Claude Opus 5.5	$4	$20
Claude Sonnet 5.5	$2	$10
Claude Haiku 4.5	$1	$5

In AUD (US$1 ≈ A$1.44, RBA, 02/10/2026), Sonnet 5.5 costs roughly A$2.88 / A$14.40 per million input/output tokens, before GST and any card foreign-transaction fee.

A rough illustration of an hour-long coding session on Sonnet 5.5, ignoring caching discounts:

• 80k input tokens × US$2/M = US$0.16 input cost
• 12k output tokens × US$10/M = US$0.12 output cost
• Total: about US$0.28, or roughly A$0.40

Multiply across sessions to estimate monthly spend, or use the Claude Code monthly cost estimator.

Output tokens cost 5x input

This is the single most important pricing fact. Asking for longer outputs (verbose explanations, full files rewritten when you only need a diff) costs 5x as much per token as the input you send. Concise output is good economics as well as good UX.

Counting tokens

• Anthropic’s tokenizer: available via the API (count_tokens endpoint) or in their Python/TS SDKs.
• Rule of thumb: divide character count by 4.
• For code: similar to English, slightly fewer characters per token because of operators and indentation.

Related terms

• Prompt
• Context window
• Prompt caching