ChatGPTNextWeb / ChatGPTNextWeb/NextChat

[Bug] Hope to be able to specify the vendor for custom models

Open
#6,498 1 comment 0 reactions 0 assignees View on GitHub
bug
Dominant language
TypeScript
Stars
88.8k
Forks
59.1k
PR merge metrics
No merged PRs in 30d

Description

### 📦 部署方式

Vercel

### 📌 软件版本

Latest

### 💻 系统环境

Windows

### 📌 系统版本

Any

### 🌐 浏览器

Chrome

### 📌 浏览器版本

Any

### 🐛 问题描述

Currently, all custom models are treated as "OpenAI," causing requests to be sent to the wrong place, and the API directly returns that the model cannot be found. I hope it will be possible to specify the model provider.
For example, a format like this could be used: `model@provider` or `provider:model`

### 📷 复现步骤

Open the settings, enter a custom model name, such as xAI's grok3-mini, then try chatting to see how frustrating it can be

### 🚦 期望结果

You can use a format similar to `grok3-mini@XAI` or `XAI:grok3-mini` to add custom models

### 📝 补充信息

_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.