Files
nexus/wiki/concepts/Token.md

23 lines
757 B
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "Token"
type: concept
tags: [token, llm, pricing, metering]
aliases: [Token, Tokens, 分词, 词元]
last_updated: 2025-12-20
---
## Definition
Token大语言模型的基本输入单元可以认为是一个单词或一个短语。是模型计费和性能计算的基础单位。
## Key Facts
- 英文1 个字符 ≈ 0.3 个 Token
- 中文1 个字符 ≈ 0.6 个 Token即中文 Token 消耗约是英文的 2 倍)
- Token 数量直接影响 API 调用成本和响应延迟
- Tokenization分词是将自然语言文本转换为 Token 序列的过程
## Connections
- [[Large Language Model]] ← 计量单位 ← [[Token]]
## Sources
- [[大模型相关术语和框架总结llm-mcp-prompt-rag-vllm-token-数据蒸馏]]