Merge pull request #241 from samzong/en/models

docs(models): add english version

docs/zh/docs/en/models/api-call.md

@@ -0,0 +1,91 @@
+---
+status: new
+translated: true
+---
+
+# Model Invocation
+
+The `d.run` platform offers two deployment options for large language models, allowing you to choose based on your specific needs:
+
+- **MaaS by Token**: Utilizes token-based billing, sharing resources, and enables model invocation without requiring instance deployment
+- **Model Service**: Provides dedicated instances with per-instance billing, offering unlimited API call access
+
+## Supported Models and Deployment Options
+
+| Model Name                    | MaaS by Token | Model Service |
+| ----------------------------- | ------------- | ------------- |
+| 🔥 DeepSeek-R1                | ✅            |               |
+| 🔥 DeepSeek-V3                | ✅            |               |
+| Phi-4                         |               | ✅            |
+| Phi-3.5-mini-instruct         |               | ✅            |
+| Qwen2-0.5B-Instruct           |               | ✅            |
+| Qwen2.5-7B-Instruct           | ✅            | ✅            |
+| Qwen2.5-14B-Instruct          |               | ✅            |
+| Qwen2.5-Coder-32B-Instruct    |               | ✅            |
+| Qwen2.5-72B-Instruct-AWQ      | ✅            | ✅            |
+| baichuan2-13b-Chat            |               | ✅            |
+| Llama-3.2-11B-Vision-Instruct | ✅            | ✅            |
+| glm-4-9b-chat                 | ✅            | ✅            |
+
+## Model Endpoints
+
+A model endpoint is a URL or API address that allows users to access and send requests for model inference.
+
+| Invocation Method | Endpoint            |
+| ----------------- | ------------------- |
+| MaaS by Token     | `chat.d.run`        |
+| Model Service     | `<region>-02.d.run` |
+
+## API Invocation Examples
+
+### Invoking via MaaS by Token
+
+To invoke models using the MaaS by Token method, follow these steps:
+
+1. **Obtain API Key**: Log in to your user console and create a new API Key
+2. **Set Endpoint**: Replace the SDK endpoint with `chat.d.run`
+3. **Invoke Model**: Use the official model name along with the new API Key for invocation
+
+**Example Code (Python)**:
+
+```python
+import openai
+
+openai.api_key = "your-api-key"  # Replace with your API Key
+openai.api_base = "https://chat.d.run"
+
+response = openai.Completion.create(
+  model="public/deepseek-r1",
+  prompt="What is your name?"
+)
+
+print(response.choices[0].text)
+```
+
+### Invoking via Model Service
+
+To invoke models using the Model Service method, follow these steps:
+
+1. **Obtain API Key**: Log in to your user console and create a new API Key
+2. **Set Endpoint**: Replace the SDK endpoint with `<region>-02.d.run`
+3. **Invoke Model**: Use the official model name along with the new API Key for invocation
+
+**Example Code (Python)**:
+
+```python
+import openai
+
+openai.api_key = "your-api-key"  # Replace with your API Key
+openai.api_base = "<region>-02.d.run"
+
+response = openai.Completion.create(
+  model="u-1100a15812cc/qwen2",
+  prompt="What is your name?"
+)
+
+print(response.choices[0].text)
+```
+
+## Support and Feedback
+
+For any questions or feedback, please contact our [Technical Support Team](../contact/index.md).

docs/zh/docs/en/models/user-guides/bob-translate.md

@@ -0,0 +1,35 @@
+---
+translated: true
+---
+
+# Using d.run in Bob Translate
+
+This guide explains how to call model services from d.run within Bob Translate.
+
+[Bob](https://bobtranslate.com/) is a macOS platform translation and OCR software that allows you to translate and perform OCR directly within any application. It's quick, efficient, and easy to use!
+
+![Bob Translate](../images/bobtranslate.png)
+
+## Installing Bob Translate
+
+You can download and install Bob Translate from the [Mac App Store](https://apps.apple.com/cn/app/bob-%E7%BF%BB%E8%AF%91%E5%92%8C-ocr-%E5%B7%A5%E5%85%B7/id1630034110).
+
+## Configuring Bob Translate
+
+Open the settings page in Bob Translate, add a translation service, and select the service type as `OpenAI`.
+
+![Bob Translate](../images/bobtranslate-2.png)
+
+Add your API Key and API Host obtained from d.run:
+
+- **API Key**: Enter your API Key
+- **API Host**:
+  - For MaaS: Use `https://chat.d.run`
+  - For independently deployed model services, refer to the model instance details, typically `https://<region>.d.run`
+- **Custom Model**: Specify as `public/deepseek-r1`
+
+![Bob Translate](../images/bobtranslate-3.png)
+
+## Demo of Bob Translate Usage
+
+![Bob Translate](../images/bobtranslate-4.png)

docs/zh/docs/en/models/user-guides/cherry-studio.md

@@ -0,0 +1,38 @@
+---
+translated: true
+---
+
+# Using d.run in Cherry Studio
+
+[🍒 Cherry Studio](https://cherry-ai.com/) is a desktop client for LLMs, supporting integration with multiple LLM providers including OpenAI, GPT-3, and d.run.
+
+![Cherry Studio](../images/cherry-studio.jpg)
+
+## Installing Cherry Studio
+
+You can download the installation package from the [Cherry Studio official website](https://cherry-ai.com/).
+
+Versions are available for MacOS, Windows, and Linux.
+
+## Configuring Cherry Studio
+
+Open the Cherry Studio configuration page and add a model provider, such as naming it `d.run` with the provider type set to `OpenAI`.
+
+![Cherry Studio](../images/cherry-studio-2.png)
+
+Enter your API Key and API Host obtained from d.run:
+
+- API Key: Enter your API Key
+- API Host:
+    - For MaaS, use `https://chat.d.run`
+    - For independently deployed models, refer to the model instance details, typically `https://<region>.d.run`
+
+### Managing Available Models
+
+Cherry Studio automatically detects available models. You can enable the models you need from the model list.
+
+![Cherry Studio](../images/cherry-studio-4.png)
+
+## Cherry Studio Usage Demo
+
+![Cherry Studio](../images/cherry-studio-5.png)

docs/zh/docs/en/models/user-guides/cline-in-vscode.md

@@ -0,0 +1,41 @@
+---
+translated: true
+---
+
+# Using d.run in VSCode and Cline
+
+[Cline](https://cline.bot/) is a VSCode plugin that enables you to use d.run model services within VSCode.
+
+## Installing Cline
+
+Search for and install the Cline plugin in VSCode.
+
+![Cline](../images/cline-in-vscode.png)
+
+You can also download and use RooCode, which is a branch of Cline.
+
+> Note: Cline was originally known as Claude Dev. RooCode (RooCline) is based on this branch.
+
+If you're unable to directly download the plugin due to network restrictions, consider downloading the `.vsix` file from the VSCode Extension Marketplace and installing it via `Install from VSIX`.
+
+- [Cline](https://marketplace.visualstudio.com/items?itemName=saoudrizwan.claude-dev)
+- [RooCode](https://marketplace.visualstudio.com/items?itemName=RooVeterinaryInc.roo-cline): A branch of Cline
+
+## Configuring Cline
+
+Open the Cline configuration page:
+
+![Cline](../images/cline-in-vscode-2.png)
+
+- **API Provider**: Select "OpenAI Compatible"
+- **Base URL**: Enter `https://chat.d.run`
+- **API Key**: Input your API key
+- **Model ID**: Enter your model ID
+    - Obtainable from d.run's Model Square, with MaaS models prefixed as public/deeepseek-r1
+    - For independently deployed models, retrieve it from the model service list
+
+![Cline](../images/cline-in-vscode-3.png)
+
+## Cline Usage Demo
+
+![Cline](../images/cline-in-vscode-4.png)

docs/zh/docs/en/models/user-guides/index.md

@@ -0,0 +1,27 @@
+---
+translated: true
+---
+
+# Example Scenarios for Usage
+
+You can refer to the following example scenarios to configure and use model services provided by d.run in your development work.
+
+## Model Invocation Examples
+
+- Refer to [Model Invocation Examples](../api-call.md) to choose the method of invoking the model.
+- Refer to [Get API Key](../apikey.md) to obtain the key.
+
+## Scenario List
+
+The following scenarios are described:
+
+| Application Scene | Operation Instructions |
+| --- | ---- |
+| [Cline in VSCode](https://github.com/cline/cline) | [Using d.run's model services in VSCode via Cline/RooCode](./cline-in-vscode.md) |
+| [Cherry Studio](https://cherry-ai.com) | [Using d.run's model services in Cherry Studio](./cherry-studio.md) |
+| [Bob Translate](https://bobtranslate.com) | [Using d.run's model services in Bob Translate](./bob-translate.md) |
+| [Lobe Chat](https://github.com/lobehub/lobe-chat) | [Using d.run's model services in Lobe Chat](./lobe-chat.md) |
+
+## Contribution Notes
+
+If you have more usage scenarios, we welcome you to share them with us through [Github PR](https://github.com/d-run/drun-docs).

docs/zh/docs/en/models/user-guides/lobe-chat.md

@@ -0,0 +1,49 @@
+---
+translated: true
+---
+
+# Using Lobe Chat Translator
+
+[Lobe Chat](https://lobehub.com/en) is an open-source modern AI chat framework.
+It supports multiple AI providers (OpenAI/Claude 3/Gemini/Ollama/Qwen/DeepSeek), knowledge bases (file uploads/knowledge management/RAG), and multi-modality (visual/TTS/plugins/art). Deploy your private ChatGPT/Claude application for free with one click.
+
+![Lobe Chat](../images/lobe-chat.png)
+
+## Install Lobe Chat
+
+For detailed installation instructions, please refer to the
+[official documentation of Lobe Chat](https://lobehub.com/en/docs/self-hosting/start).
+Lobe Chat offers various deployment and installation methods.
+
+This guide uses Docker as an example, primarily introducing how to use d.run's model service.
+
+```bash
+
+# LobeChat supports configuring API Key and API Host directly during deployment
+
+$ docker run -d -p 3210:3210 \
+    -e OPENAI_API_KEY=sk-xxxx \  # Enter your API Key
+    -e OPENAI_PROXY_URL=https://chat.d.run/v1 \  # Enter your API Host
+    -e ENABLED_OLLAMA=0 \
+    -e ACCESS_CODE=drun \
+    --name lobe-chat \
+    lobehub/lobe-chat:latest
+```
+
+## Configure Lobe Chat
+
+Lobe Chat also allows users to add model service provider configurations after deployment.
+
+![Lobe Chat](../images/lobe-chat-2.png)
+
+Enter the API Key and API Host obtained from d.run.
+
+- API Key: Enter your API Key
+- API Host:
+    - For MaaS, use `https://chat.d.run`
+    - For independently deployed models, check the model instance details, typically `https://<region>.d.run`
+- Configure custom models: e.g., `public/deepseek-r1`
+
+## Lobe Chat Usage Demo
+
+![Lobe Chat](../images/lobe-chat-3.png)

docs/zh/docs/models/user-guides/index.md

@@ -1,3 +1,7 @@
+---
+status: new
+---
+
 # d.run 使用示例场景
 
 您可以参考以下示例场景，在开发工作中配置并使用 d.run 提供的模型服务。

docs/zh/navigation.yml

@@ -202,3 +202,10 @@ plugins:
                 字节跳动: ByteDance
                 联系我们: Contact Us
                 2025 年人工智能趋势展望: AI Trend in 2025
+                模型调用: Model Invocation
+                在 Bob 翻译中使用: Using in Bob Translate
+                在 LobeChat 中使用: Using in LobeChat
+                在 Cherry Studio 中使用: Using in Cherry Studio
+                在 VSCode 和 Cline 中使用: Using in VSCode
+                使用示例场景: Use Cases
+                示例场景介绍: Example Scenarios