ChatGPTNextWeb / ChatGPTNextWeb/NextChat

[Bug] max_tokens 参数理解有误

Open
#5,451 3 comments 0 reactions 1 assignee Claimed by @DDMeaqua View on GitHub
bug
Dominant language
TypeScript
Stars
88.8k
Forks
59.1k
PR merge metrics
No merged PRs in 30d

Description

### 📦 Deployment Method

Vercel

### 📌 Version

all

### 💻 Operating System

Windows

### 📌 System Version

all

### 🌐 Browser

Chrome

### 📌 Browser Version

all

### 🐛 Bug Description

![image](https://github.com/user-attachments/assets/8fd9c639-aca5-432b-bee9-f424b857b5b7)
上图中是错误的理解,正确的是:**模型本次可以生成的最多token数** 或者说 **一次大模型调用生成的令牌数量的上限,包括可见输出token和 [推理token](https://platform.openai.com/docs/guides/reasoning)。**

---

参见:
![image](https://github.com/user-attachments/assets/63876b8e-79a3-4fab-92b0-b4b5dcd77b9d)

https://community.openai.com/t/clarification-for-max-tokens/19576/4

---

另外
https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_tokens
![image](https://github.com/user-attachments/assets/277309c4-22f1-41b3-b056-0596f0627680)

### 📷 Recurrence Steps

_No response_

### 🚦 Expected Behavior

_No response_

### 📝 Additional Information

_No response_

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.