### Initialize and Run AstrBot

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/astrbot

Initialize AstrBot environment for the first time and then start the AstrBot service. The run command checks for existing installations.

```bash
astrbot init # 仅首次使用时执行，用于初始化环境。这个指令会将 AstrBot 安装到当前终端所在的目录。  
```

```bash
astrbot run  # 启动 AstrBot。这个指令会检测当前目录是否安装了 AstrBot，如果未安装会提示使用 `astrbot init` 初始化。  
```

--------------------------------

### Get User Balance Example

Source: https://api-docs.deepseek.com/zh-cn/api/get-user-balance

This example shows the structure of a successful response when querying user balance details.

```json
{
  "is_available": true,
  "balance_infos": [
    {
      "currency": "CNY",
      "total_balance": "110.00",
      "granted_balance": "10.00",
      "topped_up_balance": "100.00"
    }
  ]
}
```

--------------------------------

### Start Reasonix Agent

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/reasonix

Navigate to your project directory and execute the Reasonix agent using npx. This command initiates the agent without requiring global installation.

```bash
cd /path/to/my-project
npx reasonix code
```

--------------------------------

### Clone AstrBot Repository

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/astrbot

Clone the AstrBot repository to start the Docker installation process.

```bash
git clone https://github.com/AstrBotDevs/AstrBot --depth 1  
```

```bash
cd AstrBot  
```

--------------------------------

### Migrate to DeepSeek Provider in OpenClaw

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/openclaw

Run this command to re-enter the configuration phase and switch to the DeepSeek provider if you have an existing OpenClaw installation. Follow the on-screen prompts to complete the setup.

```bash
openclaw onboard --install-daemon  

```

--------------------------------

### Install Crush

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/crush

Install the Crush agent globally using npm. Verify the installation by checking the version.

```bash
npm install -g @charmland/crush
```

```bash
crush --version
```

--------------------------------

### Python FIM Completion Example

Source: https://api-docs.deepseek.com/zh-cn/guides/fim_completion

This example demonstrates how to use the FIM completion API in Python. It provides the beginning and end of a Fibonacci function and asks the model to complete the middle part. Ensure you have the `openai` library installed and replace `<your api key>` with your actual API key.

```python
from openai import OpenAI

client = OpenAI(
    api_key="<your api key>",
    base_url="https://api.deepseek.com/beta",
)

response = client.completions.create(
    model="deepseek-v4-pro",
    prompt="def fib(a):",
    suffix="    return fib(a-1) + fib(a-2)",
    max_tokens=128
)
print(response.choices[0].text)

```

--------------------------------

### Start OpenCode

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/opencode

Execute this command to launch the OpenCode application.

```bash
opencode
```

--------------------------------

### Install Pi Coding Agent

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/pi_mono

Install the Pi coding agent globally using npm. Verify the installation by checking the version.

```bash
npm install -g @mariozechner/pi-coding-agent
```

```bash
pi --version
```

--------------------------------

### Install Pi using Official Script (Linux/macOS)

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/pi_mono

Alternative installation method for Linux and macOS users using a curl script.

```bash
curl -fsSL https://pi.dev/install.sh | sh
```

--------------------------------

### Install OpenClaw on Linux/Mac

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/openclaw

Execute this command to install OpenClaw using the installation script on Linux or macOS systems.

```bash
curl -fsSL https://openclaw.ai/install.sh | bash  

```

--------------------------------

### Install OpenClaw (Windows)

Source: https://api-docs.deepseek.com/zh-cn/guides/coding_agents

Install OpenClaw on Windows using the provided installation script via PowerShell.

```powershell
iwr -useb https://openclaw.ai/install.ps1 | iex
```

--------------------------------

### Install Anthropic SDK

Source: https://api-docs.deepseek.com/zh-cn/guides/anthropic_api

Install the official Anthropic SDK using pip. This is the first step to interact with the Anthropic API.

```bash
pip install anthropic  
```

--------------------------------

### Install OpenClaw on Windows

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/openclaw

Execute this command to install OpenClaw using the installation script on Windows systems.

```powershell
iwr -useb https://openclaw.ai/install.ps1 | iex  

```

--------------------------------

### Start Langcli Session

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/langcli

Launch Langcli from your terminal. After starting, you can interact with it by typing commands like 'hi'.

```bash
# 启动Langcli
langcli  

# 之后在回话中输入:  
hi  
```

--------------------------------

### Start Deep Code in Project Directory

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/deepcode

Navigate to your project directory and launch the Deep Code CLI to start an AI coding session.

```bash
cd /path/to/my-project
deepcode
```

--------------------------------

### Install OpenClaw (Linux/Mac)

Source: https://api-docs.deepseek.com/zh-cn/guides/coding_agents

Install OpenClaw on Linux or Mac using the provided installation script via curl.

```bash
curl -fsSL https://openclaw.ai/install.sh | bash
```

--------------------------------

### Install GitHub Copilot CLI

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/copilot_cli

Install the GitHub Copilot CLI globally using npm. Requires Node.js 22 or higher.

```bash
npm install -g @github/copilot
```

--------------------------------

### Install Claude Code using npm

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/claude_code

Install Claude Code globally using npm. Ensure you have Node.js 18+ installed. Windows users should also install Git for Windows.

```bash
npm install -g @anthropic-ai/claude-code

```

--------------------------------

### Start OpenClaw Dashboard

Source: https://api-docs.deepseek.com/zh-cn/guides/coding_agents

Launch the OpenClaw Web UI to interact with the AI assistant.

```bash
openclaw dashboard
```

--------------------------------

### Install Langcli (macOS/Linux/WSL)

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/langcli

Use this command for a quick installation of Langcli on macOS, Linux, and WSL environments. A terminal restart is recommended after installation.

```bash
bash -c "$(curl -fsSL https://assets.langcli.com/installation/install-langcli.sh)"
```

--------------------------------

### Manual Langcli Installation

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/langcli

Install Langcli globally using npm. Ensure Node.js version 20 or higher is installed before running this command.

```bash
npm i -g langcli-com
```

--------------------------------

### Install AstrBot on Windows

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/astrbot

Use this command to install AstrBot on Windows systems.

```powershell
iwr -useb https://docs.astrbot.app/install.ps1 | iex  
```

--------------------------------

### Install AstrBot on macOS/Linux

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/astrbot

Use this command to install AstrBot on macOS and Linux systems.

```bash
curl -LsSf https://docs.astrbot.app/install.sh | bash  
```

--------------------------------

### Start Claude Code in Project Directory

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/claude_code

After configuring environment variables, navigate to your project directory and run the 'claude' command to start the AI programming assistant.

```bash
cd /path/to/my-project
claude

```

--------------------------------

### Start OpenClaw Web UI

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/openclaw

Open the Web UI to interact with OpenClaw in the Chat page.

```bash
openclaw dashboard  

```

--------------------------------

### Access V3.1-Terminus using OpenAI-compatible API (Python)

Source: https://api-docs.deepseek.com/zh-cn/guides/comparison_testing

This Python script demonstrates how to use the OpenAI SDK to interact with the V3.1-Terminus model. Install the SDK using `pip3 install openai` and set your `DEEPSEEK_API_KEY` environment variable.

```python
# Please install OpenAI SDK first: `pip3 install openai`
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get('DEEPSEEK_API_KEY'),
    base_url="https://api.deepseek.com/v3.1_terminus_expires_on_20251015")

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "Hello"},
    ],
    stream=False
)

print(f"Model is: {response.model}")
print(f"Output is: {response.choices[0].message.content}")
```

--------------------------------

### Install Langcli (Windows)

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/langcli

For Windows users, run this command in an Administrator PowerShell to install Langcli. It downloads and executes a batch script.

```powershell
cmd /c "curl -fsSL -o %TEMP%\install-langcli.bat https://assets.langcli.com/installation/install-langcli.bat && %TEMP%\install-langcli.bat"
```

--------------------------------

### Access V3.1-Terminus using OpenAI-compatible API (Node.js)

Source: https://api-docs.deepseek.com/zh-cn/guides/comparison_testing

This Node.js script shows how to use the OpenAI SDK to communicate with the V3.1-Terminus model. Install the SDK using `npm install openai` and ensure the `DEEPSEEK_API_KEY` environment variable is set.

```javascript
// Please install OpenAI SDK first: `npm install openai`

import OpenAI from "openai";

const openai = new OpenAI({
        baseURL: 'https://api.deepseek.com/v3.1_terminus_expires_on_20251015',
        apiKey: process.env.DEEPSEEK_API_KEY,
});

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Hello!."}
    ],
    model: "deepseek-chat",
  });

  console.log("Model is:", completion.model)
  console.log("Output is:", completion.choices[0].message.content);
}

main();
```

--------------------------------

### Using OpenAI Compatible API to Access V3.1-Terminus

Source: https://api-docs.deepseek.com/zh-cn/guides/comparison_testing

This section provides examples of how to access the V3.1-Terminus model using an OpenAI-compatible API by setting a specific base URL. It includes cURL, Python, and Node.js examples.

```APIDOC
## Using OpenAI Compatible API to Access V3.1-Terminus

To access the `DeepSeek-V3.1-Terminus` model using an OpenAI-compatible API, modify your `base_url` to `https://api.deepseek.com/v3.1_terminus_expires_on_20251015`.

### cURL Example

```bash
curl https://api.deepseek.com/v3.1_terminus_expires_on_20251015/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${DEEPSEEK_API_KEY}" \
  -d '{
        "model": "deepseek-chat",
        "messages": [
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Hello!"}
        ],
        "stream": false
      }'
```

**Output Example:**

```json
{
    "model": "deepseek-v3.1-terminus",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello! How can I help you today?"
            },
            "logprobs": null,
            "finish_reason": "stop"
        }
    ]
}
```

### Python Example

```python
# Please install OpenAI SDK first: `pip3 install openai`
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get('DEEPSEEK_API_KEY'),
    base_url="https://api.deepseek.com/v3.1_terminus_expires_on_20251015")

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "Hello"},
    ],
    stream=False
)

print(f"Model is: {response.model}")
print(f"Output is: {response.choices[0].message.content}")
```

**Sample Output:**

```
Model is: deepseek-v3.1-terminus
Output is: Hello! How can I help you today?
```

### Node.js Example

```javascript
// Please install OpenAI SDK first: `npm install openai`

import OpenAI from "openai";

const openai = new OpenAI({
        baseURL: 'https://api.deepseek.com/v3.1_terminus_expires_on_20251015',
        apiKey: process.env.DEEPSEEK_API_KEY,
});

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Hello!."}
    ],
    model: "deepseek-chat",
  });

  console.log("Model is:", completion.model)
  console.log("Output is:", completion.choices[0].message.content);
}

main();
```

**Output Example:**

```
Model is: deepseek-v3.1-terminus
Output is: Hello! How can I help you today?
```

**Verification:**

You can verify that you are using the V3.1-Terminus model by checking the `model` field in the API response.
```

--------------------------------

### Upgrade OpenCode

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/opencode

Run this command to upgrade your OpenCode installation to the latest version, which is required for compatibility.

```bash
opencode upgrade
```

--------------------------------

### 初始化 nanobot 配置文件

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/nanobot

运行 `nanobot onboard` 命令来初始化 nanobot 的配置文件。配置文件路径因操作系统而异。

```bash
nanobot onboard
```

--------------------------------

### Run Pi and Select Model

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/pi_mono

Navigate to your project directory and run the `pi` command. Use `/model` to switch to DeepSeek models.

```bash
cd /path/to/my-project
pi
```

--------------------------------

### Verify Claude Code Installation

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/claude_code

After installation, run this command to verify that Claude Code is installed correctly. It should display the version number if the installation was successful.

```bash
claude --version

```

--------------------------------

### Complete Python Example for Tool Calls

Source: https://api-docs.deepseek.com/zh-cn/guides/tool_calls

Demonstrates a full Python implementation for fetching user's current weather information using Tool Calls. Requires user-defined function implementations for tools.

```python
from openai import OpenAI

def send_messages(messages):
    response = client.chat.completions.create(
        model="deepseek-v4-pro",
        messages=messages,
        tools=tools
    )
    return response.choices[0].message

client = OpenAI(
    api_key="<your api key>",
    base_url="https://api.deepseek.com",
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather of a location, the user should supply a location first.",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA",
                    }
                },
                "required": ["location"]
            },
        }
    },
]

messages = [{"role": "user", "content": "How's the weather in Hangzhou, Zhejiang?"}]
message = send_messages(messages)
print(f"User>\t {messages[0]['content']}")

tool = message.tool_calls[0]
messages.append(message)

messages.append({"role": "tool", "tool_call_id": tool.id, "content": "24℃"})
message = send_messages(messages)
print(f"Model>\t {message.content}")

```

--------------------------------

### Initializing Deepseek API Client

Source: https://api-docs.deepseek.com/zh-cn/guides/thinking_mode

Sets up the Deepseek API client using environment variables for the API key and base URL.

```python
client = OpenAI(
    api_key=os.environ.get('DEEPSEEK_API_KEY'),
    base_url=os.environ.get('DEEPSEEK_BASE_URL'),
)
```

--------------------------------

### Run Crush and Select Model

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/crush

Navigate to your project directory and run the 'crush' command. Use Ctrl+L or '/model' to open the model switcher and select a DeepSeek model.

```bash
cd /path/to/my-project
crush
```

--------------------------------

### Install Deep Code CLI

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/deepcode

Install the Deep Code command-line interface globally using npm. Ensure Node.js version 18 or higher is installed.

```bash
npm install -g @vegamo/deepcode-cli
```

--------------------------------

### 安装 nanobot

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/nanobot

使用 `uv tool install` 命令安装 nanobot。在 Windows 上，请确保将 `.local\bin` 添加到 PATH 环境变量，或使用 `uv tool update-shell` 更新终端。

```bash
uv tool install nanobot-ai
```

```powershell
$env:PATH = "$env:USERPROFILE\.local\bin;$env:PATH"
```

```bash
uv tool update-shell
```

```bash
nanobot --version
```

--------------------------------

### Start AstrBot with Docker Compose

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/astrbot

Start the AstrBot services in detached mode using Docker Compose.

```bash
sudo docker compose up -d  
```

--------------------------------

### Verify Deep Code Installation

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/deepcode

Check if the Deep Code CLI was installed successfully by running the version command.

```bash
deepcode --version
```

--------------------------------

### Connect to DeepSeek in OpenCode

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/opencode

Within OpenCode, use the /connect command followed by 'deepseek' to initiate the connection to the DeepSeek provider. You will then be prompted to enter your DeepSeek API Key and select the DeepSeek-V4-Pro model.

```bash
/connect
```

--------------------------------

### Start Copilot CLI

Source: https://api-docs.deepseek.com/zh-cn/quick_start/agent_integrations/copilot_cli

Launch the Copilot CLI after configuring the environment variables. This enables Agent mode, tool calls, and MCP powered by DeepSeek.

```bash
copilot
```

--------------------------------

### Strict Mode Tool Definition Example

Source: https://api-docs.deepseek.com/zh-cn/guides/tool_calls

An example of defining a tool with the 'strict' attribute set to true for strict adherence to JSON Schema format in Beta.

```json
{
    "type": "function",
    "function": {
        "name": "get_weather",
        "strict": true,
        "description": "Get weather of a location, the user should supply a location first.",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                }
            },
            "required": ["location"],
            "additionalProperties": false
        }
    }
}

```

--------------------------------

### Call DeepSeek API with Python SDK

Source: https://api-docs.deepseek.com/zh-cn

This Python script demonstrates how to use the OpenAI SDK to interact with the DeepSeek API. Install the SDK using 'pip3 install openai'.

```python
# Please install OpenAI SDK first: `pip3 install openai`
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get('DEEPSEEK_API_KEY'),
    base_url="https://api.deepseek.com")

response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "Hello"},
    ],
    stream=False,
    reasoning_effort="high",
    extra_body={"thinking": {"type": "enabled"}}
)

print(response.choices[0].message.content)

```