Choose Your AI Model

Supported Providers

Provider	Models	Key Command	Best For
Anthropic	Claude Sonnet 4.6, Opus 4.6	vault set anthropic_api_key	Best reasoning, tool use
OpenAI	GPT-4o, GPT-5.3	vault set openai_api_key	Fast, widely available
Google	Gemini 2.0 Flash, Pro	vault set gemini_api_key	Large context window
xAI	Grok 3, Grok 3 Mini	vault set xai_api_key	Web search built-in
Ollama	Llama 3, Mistral, Phi-3	(no key needed)	Free, private, offline
Any OpenAI-compatible	LM Studio, vLLM, Groq, Together, Fireworks, DeepSeek	vault set openai_compat_api_key	Custom endpoints

Quick Setup

# Cloud providers (pick one)
aibutler vault set anthropic_api_key sk-ant-...
aibutler vault set openai_api_key sk-...
aibutler vault set gemini_api_key AIza...

# Local (no key needed — just install Ollama)
# https://ollama.com
ollama pull llama3
aibutler run  # auto-detects Ollama

Switching Models

Change model at any time in ~/.aibutler/config.yaml:

settings:
  model: claude-sonnet-4-6    # or: gpt-4o, gemini-2.0-flash, llama3

Or switch in the REPL:

/model gpt-4o

Cost Management

AI Butler tracks every token and dollar spent:

aibutler cost status      # Current spend
aibutler cost breakdown   # Per-model breakdown
aibutler cost budget 50   # Set $50/month budget

Strategies: frugal (minimize cost), balanced (default), quality (maximize quality).

Offline Mode

Run completely offline with local models:

settings:
  offline_mode: true
  model: llama3

No data leaves your machine. Zero cloud API calls.