Claude Code Multi-Model Launcher - Help
=======================================

Usage:
  claude-all <provider> [options] [message]
  claude-all --help

Provider Options (1-10):
  1) MiniMax (Direct Anthropic API)
  2) Google Gemini (API Key - AI Studio)
  3) Google Gemini (OAuth - Vertex AI)
  4) OpenAI (API Key)
  5) OpenAI (OAuth - Experimental)
  6) xAI / Grok (API Key)
  7) ZhipuAI / GLM (API Key)
  8) Groq (API Key)
  9) Ollama (Local Models)
  10) Custom / Other

Options:
  -m, --model <model_name>  Specify exact model to use
  -h, --help               Show this help message

Examples:
  # Use default model (auto-selects first model)
  claude-all 7
  echo "Hello" | claude-all 7

  # Use specific model
  claude-all 7 --model glm-4.5-air
  claude-all 4 -m o1-preview
  claude-all 8 -m llama-3.3-70b-versatile

  # Direct message (no need for /model prefix)
  echo "Write a function" | claude-all 7 --model glm-4.7

Available Models by Provider:
-----------------------------

GLM (7):
  - glm-4.7 (default)
  - glm-4.6
  - glm-4.6-flash
  - glm-4.6-plus
  - glm-4.5-air
  - glm-4.5-pro
  - glm-4-plus
  - glm-4-air
  - glm-4-airx
  - glm-4

OpenAI (8):
  - o1-preview
  - o1-mini
  - gpt-4o (default)
  - gpt-4o-mini
  - gpt-4-turbo
  - gpt-4o-2024-08-06
  - gpt-4
  - gpt-3.5-turbo

Groq (7):
  - llama-3.3-70b-versatile (default)
  - llama-3.1-70b-versatile
  - llama-3.1-8b-instant
  - llama3-70b-8192
  - llama3-8b-8192
  - mixtral-8x7b-32768
  - gemma2-9b-it

Gemini (7):
  - gemini-2.0-flash-exp
  - gemini-1.5-pro
  - gemini-1.5-pro-latest
  - gemini-1.5-flash
  - gemini-1.5-flash-8b
  - gemini-1.5-flash-latest
  - gemini-1.0-pro

Tips:
- Use --model to avoid auto-selection
- You can also set API key via environment variable
- No need to type /model prefix when piping messages