Unverified50% confidenceFactExact time
The ratio of bytes to tokens varies greatly across different tokenizers and character sets: English text is about 4 bytes/token, Chinese about 1.5–3 bytes/token, and JSON Schema commonly falls between 3.5–4.5.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAPIs are billed per token; one token corresponds to approximately 3/4 of an English word or 1–2 Chinese characters.72% similarUnverifiedUnder naive byte-level tokenization, Bengali is compressed to an average of approximately 1.4 characters per token, compared to approximately 3.9 for English, causing the linguistic balance of the corpus to be inverted.66% similarUnverified对于英文代码1个token大约对应4个字符，100万token的上下文窗口大约等同于75万个英文单词66% similarUnverified4K tokens大约相当于3000个英文单词，100万tokens相当于约75万个英文单词65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034699API
curl https://kongchang.com/api/v1/knowledge/claims/1034699MCP
get_claim(id=1034699)