Configuration

Configuration File

The main configuration file is ~/.llms/llms.json. It's automatically created on first run with sensible defaults.

Initialize Configuration

If you need to reset the configuration, you can initialize it again:

llms --init

This creates ~/.llms/llms.json with the latest default configuration.

Configuration Structure

{
  "defaults": {
    "headers": { ... },
    "text": { ... },
    "image": { ... },
    "audio": { ... },
    "file": { ... }
  },
  "providers": {
    "groq": { ... },
    "openai": { ... },
    ...
  }
}

Defaults Section

Headers

Common HTTP headers for all requests:

{
  "defaults": {
    "headers": {
      "Content-Type": "application/json"
    }
  }
}

Chat Templates

Default request templates for different modalities:

{
  "defaults": {
    "text": {
      "model": "grok-4-fast",
      "messages": [
        {"role": "user", "content": ""}
      ],
      "temperature": 0.7
    },
    "image": {
      "model": "gemini-2.5-flash",
      "messages": [ ... ]
    },
    "audio": {
      "model": "gpt-4o-audio-preview",
      "messages": [ ... ]
    },
    "file": {
      "model": "gpt-5",
      "messages": [ ... ]
    }
  }
}

Conversion Settings

Image conversion and limits:

{
  "convert": {
    "max_image_size": 2048,
    "max_image_length": 20971520,
    "webp_quality": 90
  }
}

Providers Section

Each provider requires specific configuration. See the Providers page for details.

Basic Provider

{
  "providers": {
    "groq": {
      "enabled": true,
      "type": "OpenAiProvider",
      "base_url": "https://api.groq.com/openai",
      "api_key": "$GROQ_API_KEY",
      "models": {
        "llama3.3:70b": "llama-3.3-70b-versatile"
      },
      "pricing": {
        "llama3.3:70b": {
          "input": 0.40,
          "output": 1.20
        }
      }
    }
  }
}

UI Configuration

The UI configuration is stored in ~/.llms/ui.json:

{
  "prompts": [
    {
      "id": "it-expert",
      "name": "Act as an IT Expert",
      "value": "I want you to act as an IT Expert..."
    }
  ],
  "defaultModel": "grok-4-fast",
  "theme": "auto"
}

Environment Variables

API Keys

Reference environment variables in config with $ prefix:

{
  "api_key": "$GROQ_API_KEY"
}

Set in your shell:

export GROQ_API_KEY="gsk_..."

Other Settings

# Enable verbose logging
export VERBOSE=1

Custom Configuration Path

Use a custom configuration file:

llms --config /path/to/custom-config.json "Hello"

Configuration Management

View Configuration

# List providers and models
llms --list

# List specific providers
llms ls groq anthropic

Enable/Disable Providers

# Enable providers
llms --enable groq openai

# Disable providers
llms --disable ollama

Set Default Model

llms --default grok-4-fast

This updates defaults.text.model in the config file.