Skip to main content

Documentation Index

Fetch the complete documentation index at: https://sambanova-systems.mintlify.dev/docs/llms.txt

Use this file to discover all available pages before exploring further.

Claude Code is a command-line tool that lets you delegate coding tasks directly to Claude from your terminal. It understands your project’s codebase and can help you analyze, plan, write, and edit code.

​
Prerequisites

Before getting started, ensure you have:

​
Setup

  1. Install the official Claude Code package 
    npm install -g @anthropic-ai/claude-code
  2. Install the router package 
    npm install -g @musistudio/claude-code-router
  3. Create and configure your ~/.claude-code-router/config.json file with the following settings: 
    {
   "LOG": true,
   "LOG_LEVEL": "trace",
   "CLAUDE_PATH": "",
   "HOST": "127.0.0.1",
   "PORT": 3456,
   "APIKEY": "",
   "API_TIMEOUT_MS": "600000",
   "PROXY_URL": "",
   "transformers": [],
   "Providers": [
     {
       "name": "SambaNova",
       "api_base_url": "https://api.sambanova.ai/v1/chat/completions",
       "api_key": *****************************",
       "models": [
         "Llama-4-Maverick-17B-128E-Instruct"
       ]
     }
   ],
   "StatusLine": {
     "enabled": false,
     "currentStyle": "default",
     "default": {
       "modules": []
     },
     "powerline": {
       "modules": []
     }
   },
   "Router": {
     "default": "SambaNova,Llama-4-Maverick-17B-128E-Instruct",
     "background": "SambaNova,Llama-4-Maverick-17B-128E-Instruct",
     "think": "SambaNova,Llama-4-Maverick-17B-128E-Instruct",
     "longContext": "SambaNova,Llama-4-Maverick-17B-128E-Instruct",
     "longContextThreshold": 60000,
     "webSearch": "SambaNova,Llama-4-Maverick-17B-128E-Instruct"
   }
 }
  4. Start Claude Code using the router: 
    ccr code
    Configuration changes require a service restart to take effect.
    ccr restart
  5. Use UI Mode (optional) for easier configuration management. 
    ccr ui
You’re now set up to use Claude Code with SambaCloud models, delivering inference speeds up to 5x faster than typical GPU providers. If you encounter any issues or need assistance, contact your SambaNova support team.