ros/claude-code-router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update doc

Browse Source
This commit is contained in:
jinhui.li
2025-07-17 12:06:22 +08:00
parent df21270a7e
commit f7f6943d31
3 changed files with 466 additions and 208 deletions
Download Patch File Download Diff File Expand all files Collapse all files

361
README.md
View File

@@ -1,94 +1,145 @@
# Claude Code Router
> This is a tool for routing Claude Code requests to different models, and you can customize any request.
[中文版](README_zh.md)
> A powerful tool to route Claude Code requests to different models and customize any request.
![](screenshoots/claude-code.png)
## Usage
## ✨ Features
1. Install Claude Code
- **Model Routing**: Route requests to different models based on your needs (e.g., background tasks, thinking, long context).
- **Multi-Provider Support**: Supports various model providers like OpenRouter, DeepSeek, Ollama, Gemini, Volcengine, and SiliconFlow.
- **Request/Response Transformation**: Customize requests and responses for different providers using transformers.
- **Dynamic Model Switching**: Switch models on-the-fly within Claude Code using the `/model` command.
- **GitHub Actions Integration**: Trigger Claude Code tasks in your GitHub workflows.
- **Plugin System**: Extend functionality with custom transformers.
## 🚀 Getting Started
### 1. Installation
First, ensure you have [Claude Code](https://docs.anthropic.com/en/docs/claude-code/quickstart) installed:
```shell
npm install -g @anthropic-ai/claude-code
```
2. Install Claude Code Router
Then, install Claude Code Router:
```shell
npm install -g @musistudio/claude-code-router
```
3. Start Claude Code by claude-code-router
### 2. Configuration
```shell
ccr code
```
Create and configure your `~/.claude-code-router/config.json` file. For more details, you can refer to `config.example.json`.
4. Configure routing
Set up your `~/.claude-code-router/config.json` file like this:
The `config.json` file has several key sections:
- **`PROXY_URL`** (optional): You can set a proxy for API requests, for example: `"PROXY_URL": "http://127.0.0.1:7890"`.
- **`LOG`** (optional): You can enable logging by setting it to `true`. The log file will be located at `$HOME/.claude-code-router.log`.
- **`Providers`**: Used to configure different model providers.
- **`Router`**: Used to set up routing rules. `default` specifies the default model, which will be used for all requests if no other route is configured.
Here is a comprehensive example:
```json
{
"PROXY_URL": "http://127.0.0.1:7890",
"LOG": true,
"Providers": [
{
"name": "openrouter",
// IMPORTANT: api_base_url must be a complete (full) URL.
"api_base_url": "https://openrouter.ai/api/v1/chat/completions",
"api_key": "sk-xxx",
"models": [
"google/gemini-2.5-pro-preview",
"anthropic/claude-sonnet-4",
"anthropic/claude-3.5-sonnet",
"anthropic/claude-3.7-sonnet:thinking"
"anthropic/claude-3.5-sonnet"
],
"transformer": {
"use": ["openrouter"]
}
"transformer": { "use": ["openrouter"] }
},
{
"name": "deepseek",
// IMPORTANT: api_base_url must be a complete (full) URL.
"api_base_url": "https://api.deepseek.com/chat/completions",
"api_key": "sk-xxx",
"models": ["deepseek-chat", "deepseek-reasoner"],
"transformer": {
"use": ["deepseek"],
"deepseek-chat": {
// Enhance tool usage for the deepseek-chat model using the ToolUse transformer.
"use": ["tooluse"]
}
"deepseek-chat": { "use": ["tooluse"] }
}
},
{
"name": "ollama",
// IMPORTANT: api_base_url must be a complete (full) URL.
"api_base_url": "http://localhost:11434/v1/chat/completions",
"api_key": "ollama",
"models": ["qwen2.5-coder:latest"]
},
{
"name": "gemini",
// IMPORTANT: api_base_url must be a complete (full) URL.
"api_base_url": "https://generativelanguage.googleapis.com/v1beta/models/",
"api_key": "sk-xxx",
"models": ["gemini-2.5-flash", "gemini-2.5-pro"],
"transformer": {
"use": ["gemini"]
}
},
{
"name": "volcengine",
// IMPORTANT: api_base_url must be a complete (full) URL.
"api_base_url": "https://ark.cn-beijing.volces.com/api/v3/chat/completions",
"api_key": "sk-xxx",
"models": ["deepseek-v3-250324", "deepseek-r1-250528"],
"transformer": {
"use": ["deepseek"]
}
},
}
],
"Router": {
"default": "deepseek,deepseek-chat",
"background": "ollama,qwen2.5-coder:latest",
"think": "deepseek,deepseek-reasoner",
"longContext": "openrouter,google/gemini-2.5-pro-preview"
}
}
```
### 3. Running Claude Code with the Router
Start Claude Code using the router:
```shell
ccr code
```
#### Providers
The `Providers` array is where you define the different model providers you want to use. Each provider object requires:
- `name`: A unique name for the provider.
- `api_base_url`: The full API endpoint for chat completions.
- `api_key`: Your API key for the provider.
- `models`: A list of model names available from this provider.
- `transformer` (optional): Specifies transformers to process requests and responses.
#### Transformers
Transformers allow you to modify the request and response payloads to ensure compatibility with different provider APIs.
- **Global Transformer**: Apply a transformer to all models from a provider. In this example, the `openrouter` transformer is applied to all models under the `openrouter` provider.
```json
{
"name": "openrouter",
"api_base_url": "https://openrouter.ai/api/v1/chat/completions",
"api_key": "sk-xxx",
"models": [
"google/gemini-2.5-pro-preview",
"anthropic/claude-sonnet-4",
"anthropic/claude-3.5-sonnet"
],
"transformer": { "use": ["openrouter"] }
}
```
- **Model-Specific Transformer**: Apply a transformer to a specific model. In this example, the `deepseek` transformer is applied to all models, and an additional `tooluse` transformer is applied only to the `deepseek-chat` model.
```json
{
"name": "deepseek",
"api_base_url": "https://api.deepseek.com/chat/completions",
"api_key": "sk-xxx",
"models": ["deepseek-chat", "deepseek-reasoner"],
"transformer": {
"use": ["deepseek"],
"deepseek-chat": { "use": ["tooluse"] }
}
}
```
- **Passing Options to a Transformer**: Some transformers, like `maxtoken`, accept options. To pass options, use a nested array where the first element is the transformer name and the second is an options object.
```json
{
"name": "siliconflow",
// IMPORTANT: api_base_url must be a complete (full) URL.
"api_base_url": "https://api.siliconflow.cn/v1/chat/completions",
"api_key": "sk-xxx",
"models": ["moonshotai/Kimi-K2-Instruct"],
@@ -97,99 +148,27 @@ ccr code
[
"maxtoken",
{
"max_tokens": 16384 // for siliconflow max_tokens
"max_tokens": 16384
}
]
]
}
}
],
"Router": {
"default": "deepseek,deepseek-chat", // IMPORTANT OPENAI_MODEL has been deprecated
"background": "ollama,qwen2.5-coder:latest",
"think": "deepseek,deepseek-reasoner",
"longContext": "openrouter,google/gemini-2.5-pro-preview"
}
}
```
```
- `background`
This model will be used to handle some background tasks([background-token-usage](https://docs.anthropic.com/en/docs/claude-code/costs#background-token-usage)). Based on my tests, it doesn’t require high intelligence. I’m using the qwen-coder-2.5:7b model running locally on my MacBook Pro M1 (32GB) via Ollama.
If your computer can’t run Ollama, you can also use some free models, such as qwen-coder-2.5:3b.
**Available Built-in Transformers:**
- `think`
This model will be used when enabling Claude Code to perform reasoning. However, reasoning budget control has not yet been implemented (since the DeepSeek-R1 model does not support it), so there is currently no difference between using UltraThink and Think modes.
It is worth noting that Plan Mode also use this model to achieve better planning results.
Note: The reasoning process via the official DeepSeek API may be very slow, so you may need to wait for an extended period of time.
- `deepseek`: Adapts requests/responses for DeepSeek API.
- `gemini`: Adapts requests/responses for Gemini API.
- `maxtoken`: Sets a specific `max_tokens` value.
- `openrouter`: Adapts requests/responses for OpenRouter API.
- `tooluse`: Optimizes tool usage for certain models.
- `gemini-cli` (experimental): Unofficial support for Gemini via Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd).
- `longContext`
This model will be used when the context length exceeds 32K (this value may be modified in the future). You can route the request to a model that performs well with long contexts (I’ve chosen google/gemini-2.5-pro-preview). This scenario has not been thoroughly tested yet, so if you encounter any issues, please submit an issue.
**Custom Transformers:**
- model command
You can also switch models within Claude Code by using the `/model` command. The format is: `provider,model`, like this:
`/model openrouter,anthropic/claude-3.5-sonnet`
This will use the anthropic/claude-3.5-sonnet model provided by OpenRouter to handle all subsequent tasks.
You can also create your own transformers and load them via the `transformers` field in `config.json`.
5. About transformer
`transformer` is used to convert requests and responses for different vendors. For different vendors, we can configure different transformers.
For example, in the following case, we use the `openrouter` transformer for the OpenRouter vendor. This transformer removes the `cache_control` parameter (mainly used to adapt Claude's prompt cache) from the request for models other than Claude. In the response, it adapts the reasoning field.
```json
{
"name": "openrouter",
"api_base_url": "https://openrouter.ai/api/v1/chat/completions",
"api_key": "",
"models": [
"google/gemini-2.5-pro-preview",
"anthropic/claude-sonnet-4",
"anthropic/claude-3.5-sonnet",
"anthropic/claude-3.7-sonnet:thinking",
"deepseek/deepseek-chat-v3-0324"
],
"transformer": {
"use": [
"openrouter"
]
}
}
```
You can also configure transformers for different models of the same vendor. For instance, in the following example, we use the `deepseek` transformer for the DeepSeek vendor. This transformer sets the maximum value of `max_tokens` to `8192` in the request, and in the response, it adapts the `reasoning_content` field. Additionally, for the `deepseek-chat` model, we use the `tooluse` transformer, which optimizes the tool call for the `deepseek-v3` model using the `tool_choice` parameter (mainly because deepseek-r1 does not support the tool_choice parameter).
```json
{
"name": "deepseek",
"api_base_url": "https://api.deepseek.com/chat/completions",
"api_key": "",
"models": [
"deepseek-chat",
"deepseek-reasoner"
],
"transformer": {
"use": [
"deepseek"
],
"deepseek-chat": {
"use": [
"tooluse"
]
}
}
}
```
Currently, the following transformers are available:
- deepseek
- gemini
- maxtoken
- openrouter
- tooluse
- gemini-cli (experimental, unofficial support: https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd)
You can configure custom transformers in the `config.json` file using the `transformers` field, for example:
```json
{
"transformers": [
@@ -203,17 +182,23 @@ You can configure custom transformers in the `config.json` file using the `trans
}
```
## Features
#### Router
- [x] Support change models
- [x] Github Actions
- [ ] More detailed logs
- [ ] Support image
- [ ] Support web search
The `Router` object defines which model to use for different scenarios:
## Github Actions
- `default`: The default model for general tasks.
- `background`: A model for background tasks. This can be a smaller, local model to save costs.
- `think`: A model for reasoning-heavy tasks, like Plan Mode.
- `longContext`: A model for handling long contexts (e.g., > 60K tokens).
You just need to install `Claude Code Actions` in your repository according to the [official documentation](https://docs.anthropic.com/en/docs/claude-code/github-actions). For `ANTHROPIC_API_KEY`, you can use any string. Then, modify your `.github/workflows/claude.yaml` file to include claude-code-router, like this:
You can also switch models dynamically in Claude Code with the `/model` command:
`/model provider_name,model_name`
Example: `/model openrouter,anthropic/claude-3.5-sonnet`
## 🤖 GitHub Actions
Integrate Claude Code Router into your CI/CD pipeline. After setting up [Claude Code Actions](https://docs.anthropic.com/en/docs/claude-code/github-actions), modify your `.github/workflows/claude.yaml` to use the router:
```yaml
name: Claude Code
@@ -221,20 +206,13 @@ name: Claude Code
on:
issue_comment:
types: [created]
pull_request_review_comment:
types: [created]
issues:
types: [opened, assigned]
pull_request_review:
types: [submitted]
# ... other triggers
jobs:
claude:
if: |
(github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
(github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
(github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
(github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
# ... other conditions
runs-on: ubuntu-latest
permissions:
contents: read
@@ -272,75 +250,58 @@ jobs:
env:
ANTHROPIC_BASE_URL: http://localhost:3456
with:
anthropic_api_key: "test"
anthropic_api_key: "any-string-is-ok"
```
You can modify the contents of `$HOME/.claude-code-router/config.json` as needed.
GitHub Actions support allows you to trigger Claude Code at specific times, which opens up some interesting possibilities.
This setup allows for interesting automations, like running tasks during off-peak hours to reduce API costs.
For example, between 00:30 and 08:30 Beijing Time, using the official DeepSeek API:
## 📝 Further Reading
- The cost of the `deepseek-v3` model is only 50% of the normal time.
- [Project Motivation and How It Works](blog/en/project-motivation-and-how-it-works.md)
- [Maybe We Can Do More with the Router](blog/en/maybe-we-can-do-more-with-the-route.md)
- The `deepseek-r1` model is just 25% of the normal time.
## ❤️ Support & Sponsoring
So maybe in the future, I’ll describe detailed tasks for Claude Code ahead of time and let it run during these discounted hours to reduce costs?
## Some tips:
Now you can use deepseek-v3 models directly without using any plugins.
If you’re using the DeepSeek API provided by the official website, you might encounter an “exceeding context” error after several rounds of conversation (since the official API only supports a 64K context window). In this case, you’ll need to discard the previous context and start fresh. Alternatively, you can use ByteDance’s DeepSeek API, which offers a 128K context window and supports KV cache.
![](screenshoots/contexterror.jpg)
Note: claude code consumes a huge amount of tokens, but thanks to DeepSeek’s low cost, you can use claude code at a fraction of Claude’s price, and you don’t need to subscribe to the Claude Max plan.
Some interesting points: Based on my testing, including a lot of context information can help narrow the performance gap between these LLM models. For instance, when I used Claude-4 in VSCode Copilot to handle a Flutter issue, it messed up the files in three rounds of conversation, and I had to roll everything back. However, when I used claude code with DeepSeek, after three or four rounds of conversation, I finally managed to complete my task—and the cost was less than 1 RMB!
## Some articles:
1. [Project Motivation and Principles](blog/en/project-motivation-and-how-it-works.md) ([项目初衷及原理](blog/zh/项目初衷及原理.md))
2. [Maybe We Can Do More with the Router](blog/en/maybe-we-can-do-more-with-the-route.md) ([或许我们能在 Router 中做更多事情](blog/zh/或许我们能在Router中做更多事情.md))
## Buy me a coffee
If you find this project helpful, you can choose to sponsor the author with a cup of coffee. Please provide your GitHub information so I can add you to the sponsor list below.
If you find this project helpful, please consider sponsoring its development. Your support is greatly appreciated!
[![ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/F1F31GN2GM)
<table>
<tr>
<td><img src="/blog/images/alipay.jpg" width="200" /></td>
<td><img src="/blog/images/wechat.jpg" width="200" /></td>
<td><img src="/blog/images/alipay.jpg" width="200" alt="Alipay" /></td>
<td><img src="/blog/images/wechat.jpg" width="200" alt="WeChat Pay" /></td>
</tr>
</table>
## Sponsors
### Our Sponsors
Thanks to the following sponsors for supporting the continued development of this project:
A huge thank you to all our sponsors for their generous support!
@Simon Leischnig (If you see this, feel free to contact me and I can update it with your GitHub information)
[@duanshuaimin](https://github.com/duanshuaimin)
[@vrgitadmin](https://github.com/vrgitadmin)
@\*o (可通过主页邮箱联系我修改 github 用户名)
[@ceilwoo](https://github.com/ceilwoo)
@\*说 (可通过主页邮箱联系我修改 github 用户名)
@\*更 (可通过主页邮箱联系我修改 github 用户名)
@K\*g (可通过主页邮箱联系我修改 github 用户名)
@R\*R (可通过主页邮箱联系我修改 github 用户名)
[@bobleer](https://github.com/bobleer)
@\*苗 (可通过主页邮箱联系我修改 github 用户名)
@\*划 (可通过主页邮箱联系我修改 github 用户名)
[@Clarence-pan](https://github.com/Clarence-pan)
[@carter003](https://github.com/carter003)
@S\*r (可通过主页邮箱联系我修改 github 用户名)
@\*晖 (可通过主页邮箱联系我修改 github 用户名)
@\*敏 (可通过主页邮箱联系我修改 github 用户名)
@Z\*z (可通过主页邮箱联系我修改 github 用户名)
@\*然 (可通过主页邮箱联系我修改 github 用户名)
[@cluic](https://github.com/cluic)
@\*苗 (可通过主页邮箱联系我修改 github 用户名)
[@PromptExpert](https://github.com/PromptExpert)
@\*应 (可通过主页邮箱联系我修改 github 用户名)
[@yusnake](https://github.com/yusnake)
- @Simon Leischnig
- [@duanshuaimin](https://github.com/duanshuaimin)
- [@vrgitadmin](https://github.com/vrgitadmin)
- @*o
- [@ceilwoo](https://github.com/ceilwoo)
- @*说
- @*更
- @K*g
- @R*R
- [@bobleer](https://github.com/bobleer)
- @*苗
- @*划
- [@Clarence-pan](https://github.com/Clarence-pan)
- [@carter003](https://github.com/carter003)
- @S*r
- @*晖
- @*敏
- @Z*z
- @*然
- [@cluic](https://github.com/cluic)
- @*苗
- [@PromptExpert](https://github.com/PromptExpert)
- @*应
- [@yusnake](https://github.com/yusnake)
- @*飞
- @董*
(If your name is masked, please contact me via my homepage email to update it with your GitHub username.)

305
README_zh.md Normal file
View File

@@ -0,0 +1,305 @@
# Claude Code Router
> 一款强大的工具，可将 Claude Code 请求路由到不同的模型，并自定义任何请求。
![](screenshoots/claude-code.png)
## ✨ 功能
- **模型路由**: 根据您的需求将请求路由到不同的模型（例如，后台任务、思考、长上下文）。
- **多提供商支持**: 支持 OpenRouter、DeepSeek、Ollama、Gemini、Volcengine 和 SiliconFlow 等各种模型提供商。
- **请求/响应转换**: 使用转换器为不同的提供商自定义请求和响应。
- **动态模型切换**: 在 Claude Code 中使用 `/model` 命令动态切换模型。
- **GitHub Actions 集成**: 在您的 GitHub 工作流程中触发 Claude Code 任务。
- **插件系统**: 使用自定义转换器扩展功能。
## 🚀 快速入门
### 1. 安装
首先，请确保您已安装 [Claude Code](https://docs.anthropic.com/en/docs/claude-code/quickstart)：
```shell
npm install -g @anthropic-ai/claude-code
```
然后，安装 Claude Code Router：
```shell
npm install -g @musistudio/claude-code-router
```
### 2. 配置
创建并配置您的 `~/.claude-code-router/config.json` 文件。有关更多详细信息，您可以参考 `config.example.json`。
`config.json` 文件有几个关键部分：
- **`PROXY_URL`** (可选): 您可以为 API 请求设置代理，例如：`"PROXY_URL": "http://127.0.0.1:7890"`。
- **`LOG`** (可选): 您可以通过将其设置为 `true` 来启用日志记录。日志文件将位于 `$HOME/.claude-code-router.log`。
- **`Providers`**: 用于配置不同的模型提供商。
- **`Router`**: 用于设置路由规则。`default` 指定默认模型，如果未配置其他路由，则该模型将用于所有请求。
这是一个综合示例：
```json
{
"PROXY_URL": "http://127.0.0.1:7890",
"LOG": true,
"Providers": [
{
"name": "openrouter",
"api_base_url": "https://openrouter.ai/api/v1/chat/completions",
"api_key": "sk-xxx",
"models": [
"google/gemini-2.5-pro-preview",
"anthropic/claude-sonnet-4",
"anthropic/claude-3.5-sonnet"
],
"transformer": { "use": ["openrouter"] }
},
{
"name": "deepseek",
"api_base_url": "https://api.deepseek.com/chat/completions",
"api_key": "sk-xxx",
"models": ["deepseek-chat", "deepseek-reasoner"],
"transformer": {
"use": ["deepseek"],
"deepseek-chat": { "use": ["tooluse"] }
}
},
{
"name": "ollama",
"api_base_url": "http://localhost:11434/v1/chat/completions",
"api_key": "ollama",
"models": ["qwen2.5-coder:latest"]
}
],
"Router": {
"default": "deepseek,deepseek-chat",
"background": "ollama,qwen2.5-coder:latest",
"think": "deepseek,deepseek-reasoner",
"longContext": "openrouter,google/gemini-2.5-pro-preview"
}
}
```
### 3. 使用 Router 运行 Claude Code
使用 router 启动 Claude Code：
```shell
ccr code
```
#### Providers
`Providers` 数组是您定义要使用的不同模型提供商的地方。每个提供商对象都需要：
- `name`: 提供商的唯一名称。
- `api_base_url`: 聊天补全的完整 API 端点。
- `api_key`: 您提供商的 API 密钥。
- `models`: 此提供商可用的模型名称列表。
- `transformer` (可选): 指定用于处理请求和响应的转换器。
#### Transformers
Transformers 允许您修改请求和响应负载，以确保与不同提供商 API 的兼容性。
- **全局 Transformer**: 将转换器应用于提供商的所有模型。在此示例中，`openrouter` 转换器将应用于 `openrouter` 提供商下的所有模型。
```json
{
"name": "openrouter",
"api_base_url": "https://openrouter.ai/api/v1/chat/completions",
"api_key": "sk-xxx",
"models": [
"google/gemini-2.5-pro-preview",
"anthropic/claude-sonnet-4",
"anthropic/claude-3.5-sonnet"
],
"transformer": { "use": ["openrouter"] }
}
```
- **特定于模型的 Transformer**: 将转换器应用于特定模型。在此示例中，`deepseek` 转换器应用于所有模型，而额外的 `tooluse` 转换器仅应用于 `deepseek-chat` 模型。
```json
{
"name": "deepseek",
"api_base_url": "https://api.deepseek.com/chat/completions",
"api_key": "sk-xxx",
"models": ["deepseek-chat", "deepseek-reasoner"],
"transformer": {
"use": ["deepseek"],
"deepseek-chat": { "use": ["tooluse"] }
}
}
```
- **向 Transformer 传递选项**: 某些转换器（如 `maxtoken`）接受选项。要传递选项，请使用嵌套数组，其中第一个元素是转换器名称，第二个元素是选项对象。
```json
{
"name": "siliconflow",
"api_base_url": "https://api.siliconflow.cn/v1/chat/completions",
"api_key": "sk-xxx",
"models": ["moonshotai/Kimi-K2-Instruct"],
"transformer": {
"use": [
[
"maxtoken",
{
"max_tokens": 16384
}
]
]
}
}
```
**可用的内置 Transformer：**
- `deepseek`: 适配 DeepSeek API 的请求/响应。
- `gemini`: 适配 Gemini API 的请求/响应。
- `maxtoken`: 设置特定的 `max_tokens` 值。
- `openrouter`: 适配 OpenRouter API 的请求/响应。
- `tooluse`: 优化某些模型的工具使用。
- `gemini-cli` (实验性): 通过 Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd) 对 Gemini 的非官方支持。
**自定义 Transformer:**
您还可以创建自己的转换器，并通过 `config.json` 中的 `transformers` 字段加载它们。
```json
{
"transformers": [
{
"path": "$HOME/.claude-code-router/plugins/gemini-cli.js",
"options": {
"project": "xxx"
}
}
]
}
```
#### Router
`Router` 对象定义了在不同场景下使用哪个模型：
- `default`: 用于常规任务的默认模型。
- `background`: 用于后台任务的模型。这可以是一个较小的本地模型以节省成本。
- `think`: 用于推理密集型任务（如计划模式）的模型。
- `longContext`: 用于处理长上下文（例如，> 60K 令牌）的模型。
您还可以使用 `/model` 命令在 Claude Code 中动态切换模型：
`/model provider_name,model_name`
示例: `/model openrouter,anthropic/claude-3.5-sonnet`
## 🤖 GitHub Actions
将 Claude Code Router 集成到您的 CI/CD 管道中。在设置 [Claude Code Actions](https://docs.anthropic.com/en/docs/claude-code/github-actions) 后，修改您的 `.github/workflows/claude.yaml` 以使用路由器：
```yaml
name: Claude Code
on:
issue_comment:
types: [created]
# ... other triggers
jobs:
claude:
if: |
(github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
# ... other conditions
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: read
issues: read
id-token: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Prepare Environment
run: |
curl -fsSL https://bun.sh/install | bash
mkdir -p $HOME/.claude-code-router
cat << 'EOF' > $HOME/.claude-code-router/config.json
{
"log": true,
"OPENAI_API_KEY": "${{ secrets.OPENAI_API_KEY }}",
"OPENAI_BASE_URL": "https://api.deepseek.com",
"OPENAI_MODEL": "deepseek-chat"
}
EOF
shell: bash
- name: Start Claude Code Router
run: |
nohup ~/.bun/bin/bunx @musistudio/claude-code-router@1.0.8 start &
shell: bash
- name: Run Claude Code
id: claude
uses: anthropics/claude-code-action@beta
env:
ANTHROPIC_BASE_URL: http://localhost:3456
with:
anthropic_api_key: "any-string-is-ok"
```
这种设置可以实现有趣的自动化，例如在非高峰时段运行任务以降低 API 成本。
## 📝 深入阅读
- [项目动机和工作原理](blog/zh/项目初衷及原理.md)
- [也许我们可以用路由器做更多事情](blog/zh/或许我们能在Router中做更多事情.md)
## ❤️ 支持与赞助
如果您觉得这个项目有帮助，请考虑赞助它的开发。非常感谢您的支持！
[![ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/F1F31GN2GM)
<table>
<tr>
<td><img src="/blog/images/alipay.jpg" width="200" alt="Alipay" /></td>
<td><img src="/blog/images/wechat.jpg" width="200" alt="WeChat Pay" /></td>
</tr>
</table>
### 我们的赞助商
非常感谢所有赞助商的慷慨支持！
- @Simon Leischnig
- [@duanshuaimin](https://github.com/duanshuaimin)
- [@vrgitadmin](https://github.com/vrgitadmin)
- @*o
- [@ceilwoo](https://github.com/ceilwoo)
- @*说
- @*更
- @K*g
- @R*R
- [@bobleer](https://github.com/bobleer)
- @*苗
- @*划
- [@Clarence-pan](https://github.com/Clarence-pan)
- [@carter003](https://github.com/carter003)
- @S*r
- @*晖
- @*敏
- @Z*z
- @*然
- [@cluic](https://github.com/cluic)
- @*苗
- [@PromptExpert](https://github.com/PromptExpert)
- @*应
- [@yusnake](https://github.com/yusnake)
- @*飞
- @董*
（如果您的名字被屏蔽，请通过我的主页电子邮件与我联系，以便使用您的 GitHub 用户名进行更新。）

8
config.json
View File

@@ -1,8 +0,0 @@
{
"usePlugin": "",
"LOG": true,
"OPENAI_API_KEY": "",
"OPENAI_BASE_URL": "",
"OPENAI_MODEL": "",
"modelProviders": {}
}