Tokens in Chinese (Traditional)
How many tokens does Chinese (Traditional) text use, compared with English? We measured the same copy in both languages with OpenAI's two main tokenizers.
What the numbers say
The same website copy is 200 tokens in English and 265 tokens in Chinese (Traditional) on the newer o200k_base encoding, a ratio of 1.32×. On the older cl100k_base encoding the Chinese (Traditional) copy needs 397 tokens, which is 1.99× the English count of 200. At the same price per token, the same message costs about 1.32× as much in Chinese (Traditional) on the newer encoding. Among the 29 non-English languages we measured, Chinese (Traditional) ranks number 18 from the cheapest.
The newer encoding made a real difference: o200k_base used 33% fewer tokens than cl100k_base for Chinese (Traditional), compared with 34% across all the non-English languages in the data. That is less than average, so Chinese (Traditional) gained less from the newer vocabulary than most.
Traditional Chinese needs 1.30× the tokens of Simplified Chinese on o200k_base (265 against 204), and 1.35× on cl100k_base. Part of that is the character forms, part is the different wording.
Why Chinese (Traditional)? Traditional Chinese uses the older, more complex character forms used in Taiwan and Hong Kong. Many of those forms appear less often in training text than their simplified counterparts, so some are split into more byte-level tokens. Wording also differs from Simplified Chinese, so the two cannot be compared character for character.
East Asian scripts have thousands of characters, each of which is three bytes in UTF-8. A tokenizer cannot include every character as its own piece, so common characters get a single token and rarer ones are broken into byte-level pieces. At the same time these languages need far fewer characters to say the same thing, which is why total cost, not characters per token, is the number to compare.
How a Chinese (Traditional) sentence is split into tokens
This is the tagline of this site in Chinese (Traditional). Each shaded block is one token (or a few tokens that together make one character) on o200k_base.
32 characters become 29 tokens on o200k_base and 43 tokens on cl100k_base. The English tagline, "Copy text on one device and paste it on another — no app, no account.", is 69 characters and 17 tokens on o200k_base and 17 on cl100k_base.
Want to see your own text? Paste it into the token calculator and compare the two tokenizers.
Chinese (Traditional) next to English and the closest languages
| Language | Characters | Tokens o200k_base | Tokens cl100k_base | × English o200k_base | × English cl100k_base |
|---|---|---|---|---|---|
| EnglishEnglish | 902 | 200 | 200 | 1.00× | 1.00× |
| TurkishTürkçe | 930 | 262 | 342 | 1.31× | 1.71× |
| NorwegianNorsk | 943 | 263 | 301 | 1.31× | 1.50× |
| Korean한국어 | 474 | 263 | 382 | 1.31× | 1.91× |
| Chinese (Traditional)繁體中文 | 317 | 265 | 397 | 1.32× | 1.99× |
| PolishPolski | 915 | 267 | 313 | 1.33× | 1.56× |
See all 30 languages, with a chart and CSV and JSON downloads, on token cost by language.
What it means for your bill
API prices are per token, so the ratio is also a price ratio. If a prompt costs $1.00 in English on o200k_base, the equivalent Chinese (Traditional) prompt costs about $1.32, and about $1.99 on cl100k_base. A document of 1,000 Chinese (Traditional) characters is roughly 836 tokens on o200k_base. These are estimates from one sample: translated text is never exactly the same length as the original, and your text may be formal, technical or full of names, which changes the ratio.
To turn tokens into money, enter your provider's input and output prices per million tokens in the token calculator. For how pricing works, see how LLM API pricing works.
How to use fewer tokens with Chinese (Traditional) text
- Use a model with the newer tokenizer. For Chinese (Traditional), o200k_base used 33% fewer tokens than cl100k_base in this sample, so a GPT-4o-class model needs fewer tokens than an older one for the same text.
- Count before you send. Paste a typical message into the token calculator to see the real count, then multiply by the number of requests.
- Keep fixed instructions short. A system prompt that is sent with every request is paid for every time. Writing the standing instructions in English is often cheaper per token than in Chinese (Traditional); test that answers stay as good as you need.
- Cut what is not needed. Remove greetings, repeated context and long examples. The guide to reducing token usage has more.
- Be careful with emoji, rare characters and unusual formatting. They are often split into several byte-level tokens each.
Frequently asked questions
How many tokens is Chinese (Traditional) text?
In our measurement, the same website copy that is 200 tokens in English (902 characters) is 265 tokens in Chinese (Traditional) on o200k_base (317 characters) and 397 tokens on cl100k_base. As a rule of thumb, 1,000 characters of Chinese (Traditional) come to about 836 tokens on o200k_base and about 1252 on cl100k_base.
Is Chinese (Traditional) more expensive than English in GPT-4o?
Slightly to noticeably, depending on the text. On o200k_base, the encoding used by GPT-4o and newer OpenAI models, the Chinese (Traditional) copy needs 1.32× the English token count, so at the same price per token the same message costs about 1.32× as much. It was 1.99× on the older cl100k_base.
Which tokenizer is better for Chinese (Traditional)?
o200k_base needed 33% fewer tokens than cl100k_base for Chinese (Traditional) in this sample. Across all 29 non-English languages in the data, the average saving was 34%, so Chinese (Traditional) improved less than average.
Why does Chinese (Traditional) need more tokens than English?
Traditional Chinese uses the older, more complex character forms used in Taiwan and Hong Kong. Many of those forms appear less often in training text than their simplified counterparts, so some are split into more byte-level tokens. Wording also differs from Simplified Chinese, so the two cannot be compared character for character. East Asian scripts have thousands of characters, each of which is three bytes in UTF-8. A tokenizer cannot include every character as its own piece, so common characters get a single token and rarer ones are broken into byte-level pieces. At the same time these languages need far fewer characters to say the same thing, which is why total cost, not characters per token, is the number to compare.
Does this apply to Claude, Gemini or Llama?
Not directly. Other providers train their own tokenizers, so counts and ratios differ. These figures describe two OpenAI encodings only. Use your provider's own token counter before relying on a number for billing.
How was this measured?
We counted the tokens of the site's own copy in each language (tagline, two about paragraphs and four how-to steps) with the o200k_base and cl100k_base encodings from gpt-tokenizer 4.0.0, on 2026-10-12, and divided by the English count. It is one sample of marketing-style text, so other kinds of text, such as code or legal prose, will give different ratios.
Other languages and guides
Other languages: Japanese · Korean · Chinese (Simplified) · Hindi · Bengali · Thai · Russian · Vietnamese · Greek · Turkish · Indonesian · German · Spanish · Portuguese · French