一些免费AI模型，及在 VS Code 中使用

VS Code 中添加 AI 模型

Visual Studio Code（简称 VS Code）官方文档 Bring your own language model key[1] 中介绍了在 VS Code 中添加更多语言模型的方法，包括 内置提供商（Built-in providers）[2]、扩展（Extensions）[3]、自定义端点（Custom endpoint）[4] 三种方式。

自定义端点支持三种 API 类型：Chat Completions[5]、Responses[6] 和 Messages[7]。

添加模型步骤如下：

1. 切换模型处选择其他模型后的配置图标：

models

1. 选择添加模型，然后选择自定义端点（Custom Endpoint）：

add-models

1. 为模型输入组名，这是在模型选择器和语言模型编辑器中显示的分组标签。组名后续可修改。
2. 输入端点的 API 密钥，秘钥会以密文形式存储。
3. 选择 API 类型：

api-type

1. 之后 VS Code 会打开一个 chatLanguageModels.json 文件，调用模型具体的模型名称（id）和完整 url 需在此文件中填写。有关配置属性的详细信息，请参阅 Model configuration reference[8]。

下面是调用 Anthropic Messages API 的配置示例：

[
  {
    "name": "Anthropic",
    "vendor": "customendpoint",
    "apiKey": "YOUR_API_KEY",
    "apiType": "messages",
    "models": [
      {
        "id": "claude-sonnet-4-6",
        "name": "Claude Sonnet 4.6",
        "url": "https://api.anthropic.com/v1/messages",
        "toolCalling": true,
        "vision": true,
        "maxInputTokens": 200000,
        "maxOutputTokens": 64000
      }
    ]
  }
]

下面是调用 OpenAI Chat Completions API 的配置示例：

[
  {
    "name": "LocalHost",
    "vendor": "customendpoint",
    "apiKey": "${input:chat.lm.secret.xxxxxx}",
    "apiType": "chat-completions",
    "models": [
      {
        "id": "model1",
        "name": "Local Model 1",
        "url": "http://localhost:8000/v1/chat/completions",
        "toolCalling": true,
        "vision": true,
        "maxInputTokens": 128000,
        "maxOutputTokens": 16000
      },
      {
        "id": "model2",
        "name": "Local Model 2",
        "url": "http://localhost:8000/v1/chat/completions",
        "toolCalling": true,
        "vision": true,
        "maxInputTokens": 128000,
        "maxOutputTokens": 16000
      }
    ]
  }
]

Debug

在 VS Code GitHub Copilot Chat 中使用自定义模型可能会遇到请求失败的报错，如：

Sorry, your request failed. Please try again.
Client Request Id: 95903bd3-e7d5-435f-a842-45bcf985940b
Reason: token expired or invalid: 403: Error: token expired or invalid: 403 at qG._provideLanguageModelResponse (/Applications/Visual Studio Code.app/Contents/Resources/app/extensions/copilot/dist/extension.js:1690:14362) at process.processTicksAndRejections (node:internal/process/task_queues:104:5) at async qG.provideLanguageModelResponse (/Applications/Visual Studio Code.app/Contents/Resources/app/extensions/copilot/dist/extension.js:1690:15327)

Meta: Sorry, your request failed. Please try again. #253136[9] 给出了一些解决方案，如重试请求、更换模型、检查日志（CTRL + SHIFT + U 打开输出面板，选择 GitHub Copilot Chat 查看日志）等。

output

output

Free Models

参考资料

[1]

Bring your own language model key: https://code.visualstudio.com/docs/agent-customization/language-models#_bring-your-own-language-model-key

[2]

内置提供商（Built-in providers）: https://code.visualstudio.com/docs/agent-customization/language-models#_add-a-model-from-a-built-in-provider

[3]

扩展（Extensions）: https://code.visualstudio.com/docs/agent-customization/language-models#_add-a-model-provider-extension

[4]

自定义端点（Custom endpoint）: https://code.visualstudio.com/docs/agent-customization/language-models#_add-a-custom-endpoint-model

[5]

Chat Completions: https://developers.openai.com/api/reference/chat-completions/overview

[6]

Responses: https://developers.openai.com/api/reference/responses/overview

[7]

Messages: https://platform.claude.com/docs/en/api/messages

[8]

Model configuration reference: https://code.visualstudio.com/docs/agent-customization/language-models#_model-configuration-reference

[9]

Meta: Sorry, your request failed. Please try again. #253136: https://github.com/microsoft/vscode/issues/253136