Quick Start

1. Set API Keys

Set environment variables for the providers you want to use:

export OPENROUTER_API_KEY="sk-or-..."
export GROQ_API_KEY="gsk_..."
export GOOGLE_FREE_API_KEY="AIza..."

See the API Keys page for a complete list of supported providers.

2. Initialize Configuration

llms --init

This creates a default configuration file at ~/.llms/llms.json.

3. Enable Providers

Enable the providers you want to use:

llms --enable openrouter_free google_free groq

You can also enable premium providers:

llms --enable openai anthropic grok

4. List Available Models

See which models are available:

llms ls

Or list models for specific providers:

llms ls groq openrouter_free

5. Start Chatting

CLI Usage

# Simple question
llms "Explain quantum computing in simple terms"

# With specific model
llms -m grok-4-fast "jq command to sort openai models by created"

# With system prompt
llms -s "You are a quantum computing expert" "Explain quantum computing"

Start the Server

Run an OpenAI-compatible server with web UI:

llms --serve 8000

This launches:

• Web UI at http://localhost:8000
• OpenAI-compatible API at http://localhost:8000/v1/chat/completions

Use the API

curl -X POST http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Next Steps

• Configuration Guide - Customize your setup
• CLI Usage - Learn all CLI commands
• Web UI Features - Explore the web interface
• Image Support - Use images with vision models
• Audio Support - Process audio files
• File Support - Work with PDFs and documents