Token
定義
A token is the fundamental unit of text that large language models process. In English, one token is roughly 3/4 of a word (100 tokens ≈ 75 words). LLM providers charge based on token consumption: input tokens (your prompt and context) plus output tokens (the model's response). Understanding tokens is essential for managing AI costs and staying within model context windows.
Token Tracking in JieGou
JieGou tracks input and output tokens for every recipe run and workflow execution. This data feeds into per-recipe, per-workflow, and per-department cost dashboards. With BYOK, tokens are billed directly to your provider account at their standard rates.
Context Windows
Each LLM has a maximum context window — the total number of tokens it can process in one request (prompt + response). Claude supports up to 200K tokens, GPT-4 up to 128K. JieGou's RAG system is designed to stay within these limits by retrieving only the most relevant document chunks.
相關術語
AI 配方
了解什麼是 AI 配方以及它們如何在 JieGou 中運作。配方是可重複使用的單一操作 AI 建構模組，具有結構化的輸入和輸出。
BYOK（自帶金鑰）
了解 BYOK 對 AI 自動化的意義。自帶金鑰讓您將自己的 LLM API 金鑰連接到 JieGou，實現完全的成本控制和資料隱私。
Large Language Model (LLM)
A large language model (LLM) is an AI system trained on text data that can understand and generate human language, powering tasks like writing, analysis, and reasoning.