[Bug] grok-2-image 模型报错

[aaron0713]

📦 部署方式

Docker

📌 软件版本

2.15.8

💻 系统环境

Other Linux

📌 系统版本

6.1.0-9-amd64

🌐 浏览器

Chrome

📌 浏览器版本

134.0.6998.118

🐛 问题描述

安装方式及环境说明： 使用yidadaa/chatgpt-next-web:latest 新装的 Docker，版本号应该是2.16，但是安装好运行起来之后，还是显示2.15.8，并且提示有更新2.16.。

问题： 模型grok-2-vision可以正常使用，但是切换到 模型 grok-2-image-1212 之后就提示错误 { "code": "Some requested entity was not found", "error": "The model grok-2-image-1212 does not exist or your team XXXX does not have access to it. Please ensure you're using the correct API key. If you believe this is a mistake, please contact support and quote your team ID and the model name." }

以验证模型可用，相同的key在python中调用成功

client = OpenAI(base_url="https://api.x.ai/v1", api_key=XAI_API_KEY)
response = client.images.generate(model="grok-2-image-1212",prompt="A cat in a tree",n=4)
for image in response.data:
  print(image.url)

📷 复现步骤

No response

🚦 期望结果

No response

📝 补充信息

No response

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

Title: [Bug] grok-2-image model error

[cfs4819]

grok-2-image-1212似乎是一个生图模型，nextchat配置下的模型一般是对话模型，因此nextchat中对x的支持模型列表如下

const xAIModes = [
  "grok-beta",
  "grok-2",
  "grok-2-1212",
  "grok-2-latest",
  "grok-vision-beta",
  "grok-2-vision-1212",
  "grok-2-vision",
  "grok-2-vision-latest",
];

暂没有对生图模型grok-2-image-1212的支持，但你仍然可以通过插件的方式使用它

grok-2-vision是一个带有图像理解的对话模型，因此可以使用。

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

grok-2-image-1212 seems to be a raw graph model. The model under nextchat configuration is generally a dialogue model. Therefore, the list of supported models for x in nextchat is as follows

const xAIModes = [
  "grok-beta",
  "grok-2",
  "grok-2-1212",
  "grok-2-latest",
  "grok-vision-beta",
  "grok-2-vision-1212",
  "grok-2-vision",
  "grok-2-vision-latest",
];

There is no support for the raw graph model grok-2-image-1212, but you can still use it through plug-ins.

grok-2-vision is a conversational model with image understanding and therefore can be used.

[aaron0713]

grok-2-image-1212似乎是一个生图模型，nextchat配置下的模型一般是对话模型，因此nextchat中对x的支持模型列表如下

const xAIModes = [ "grok-beta", "grok-2", "grok-2-1212", "grok-2-latest", "grok-vision-beta", "grok-2-vision-1212", "grok-2-vision", "grok-2-vision-latest", ]; 暂没有对生图模型grok-2-image-1212的支持，但你仍然可以通过插件的方式使用它

grok-2-vision是一个带有图像理解的对话模型，因此可以使用。

我开启了MCP插件，但是MCP Market是空的，我需要自己写插件吗

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

grok-2-image-1212 seems to be a raw graph model. The model under nextchat configuration is generally a dialogue model. Therefore, the list of supported models for x in nextchat is as follows

const xAIModes = [ "grok-beta", "grok-2", "grok-2-1212", "grok-2-latest", "grok-vision-beta", "grok-2-vision-1212", "grok-2-vision", "grok-2-vision-latest", ]; There is no support for the raw graph model grok-2-image-1212, but you can still use it through plug-ins

grok-2-vision is a conversational model with image understanding and therefore can be used.

I enabled the MCP plugin, but the MCP Market is empty. Do I need to write the plugin myself?

[cfs4819]

现在MCP还没稳定，我在尝试的时候会导致一些错误。你可以通过 “发现” -> "plugins"->"新建"来创建一个支持x.ai绘图的插件。你可以参考x.ai的api文档以及flux的绘图插件编写这个插件的openapi schema，flux的绘图插件的地址在这里

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

Now that MCP is not stable, I will cause some errors when trying. You can create a plugin that supports x.ai drawing by "Discover" -> "plugins"->"New". You can refer to the x.ai API documentation and flux drawing plug-in to write the openapi schema of this plug-in. The address of the flux drawing plug-in is [here] (https://github.com/ChatGPTNextWeb/NextChat-Awesome-Plugins/blob/main/plugins/flux/openapi.json)

[aaron0713]

现在MCP还没稳定，我在尝试的时候会导致一些错误。你可以通过 “发现” -> "plugins"->"新建"来创建一个支持x.ai绘图的插件。你可以参考x.ai的api文档以及flux的绘图插件编写这个插件的openapi schema，flux的绘图插件的地址在这里

谢谢，我去试试看

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

Now that the MCP is not stable, I will cause some errors when trying. You can create a plugin that supports x.ai drawing by "Discover" -> "plugins"->"New". You can refer to the x.ai API documentation and flux drawing plug-in to write the openapi schema of this plug-in. The address of the flux drawing plug-in is [here] (https://github.com/ChatGPTNextWeb/NextChat-Awesome-Plugins/blob/main/plugins/flux/openapi.json)

Thanks, I'll try it