🧠
DeepSeek
Model AI Models & RoutingInstall Command
npx clawhub@latest install deepseek-claw
Installation Guide
1
Check Environment
Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.
2
Run Installation
Run the install command above in your terminal. ClawHub will automatically download and install DeepSeek to the ~/.openclaw/skills/ directory.
3
Verify Installation
Run openclaw skills list to check your installed skills and confirm DeepSeek appears in the list.
4
Configure (Optional)
Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.
Manual Installation: Copy the Skill folder to
~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
DeepSeek-V3
Deep Reasoning
High Cost-Efficiency
Detailed Description
The DeepSeek skill connects OpenClaw to the DeepSeek series of large language models, providing powerful conversation and reasoning capabilities at exceptional cost-efficiency.
Core Features
- Model Access: Supports DeepSeek-V3, DeepSeek-R1, and other models in the series
- Deep Reasoning: DeepSeek-R1 provides chain-of-thought reasoning capabilities, ideal for complex logical problems
- Coding Ability: Excellent performance on programming tasks, supporting multiple programming languages
- Long Context: Supports 128K context window
- High Cost-Efficiency: API pricing far lower than comparable models
Configuration
{
skills: {
"deepseek-claw": {
apiKey: "sk-xxx",
model: "deepseek-chat", // deepseek-chat or deepseek-reasoner
baseUrl: "https://api.deepseek.com"
}
}
}
Use Cases
- Scenarios requiring cost-effective AI models
- Complex logical reasoning and mathematical problems (using the R1 model)
- Code generation and debugging tasks
- As a fallback model paired with ClawRouter