Unverified50% confidenceFactExact time
A token is the smallest unit by which large language models process text, roughly corresponding to half to one English word or half a Chinese character.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedOne English word is approximately 1-2 tokens in large language models76% similarUnverified一个Token大致对应3/4个英文单词或更少的中文字符，商业模型按输入与输出Token分别计费72% similarUnverified同等语义内容下，文言文所需Token数量可能仅为白话文的1/3到1/270% similarUnverifiedIn large language models, one English word typically corresponds to 1–2 tokens, one Chinese character typically corresponds to 1.5–2.5 tokens, and GPT-4's single-conversation context window is approximately 128,000 tokens.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64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/943322API
curl https://kongchang.com/api/v1/knowledge/claims/943322MCP
get_claim(id=943322)