Tokens in Chinese (Simplified)

What the numbers say

The same website copy is 200 tokens in English and 204 tokens in Chinese (Simplified) on the newer o200k_base encoding, a ratio of 1.02×. On the older cl100k_base encoding the Chinese (Simplified) copy needs 295 tokens, which is 1.48× the English count of 200. So on the newer encoding Chinese (Simplified) costs only a modest amount more than English. Among the 29 non-English languages we measured, Chinese (Simplified) ranks number 1 from the cheapest.

The newer encoding made a real difference: o200k_base used 31% fewer tokens than cl100k_base for Chinese (Simplified), compared with 34% across all the non-English languages in the data. That is less than average, so Chinese (Simplified) gained less from the newer vocabulary than most.

Simplified Chinese is the cheapest language in our data on the newer encoding, at 1.02× English, while Traditional Chinese needs 1.32×. The two are written differently, so they cannot be compared character for character.

Why Chinese (Simplified)? Simplified Chinese packs a lot of meaning into each character and has no spaces between words, so the same message is far shorter in characters than in English. Frequent characters tend to be one token each.

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.

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 (Simplified) prompt costs about $1.02, and about $1.48 on cl100k_base. A document of 1,000 Chinese (Simplified) characters is roughly 658 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 (Simplified) text

1. Use a model with the newer tokenizer. For Chinese (Simplified), o200k_base used 31% 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.
2. Count before you send. Paste a typical message into the token calculator to see the real count, then multiply by the number of requests.
3. 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 (Simplified); test that answers stay as good as you need.
4. Cut what is not needed. Remove greetings, repeated context and long examples. The guide to reducing token usage has more.
5. Be careful with emoji, rare characters and unusual formatting. They are often split into several byte-level tokens each.