Unverified50% confidenceFactExact time
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
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
GPT-5.6接入Devin：编程智能体性能与成本效率双突破
rss7/9/2026
Related Claims
VerifiedIn large language models, output tokens are typically 2–3 times more expensive than input tokens.73% similarPartially VerifiedOne English word is approximately 1-2 tokens in large language models73% similarUnverifiedAPIs are billed per token; one token corresponds to approximately 3/4 of an English word or 1–2 Chinese characters.73% similarUnverifiedLarge language models are billed by the number of tokens, with 1 token equaling approximately 4 English characters or 1–2 Chinese characters.72% 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72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/488257API
curl https://kongchang.com/api/v1/knowledge/claims/488257MCP
get_claim(id=488257)