GitWhisper supports multiple AI providers and models. Use these commands to discover available options.
list-models Display all supported AI model providers.
Usage gitwhisper list-models # or use the shorthand gw list-models
Terminal Output $ gw list-models Available models: - claude (Anthropic Claude ) - openai (OpenAI GPT models ) - gemini (Google Gemini ) - grok (xAI Grok ) - llama (Meta Llama ) - deepseek (DeepSeek, Inc. ) - github (GitHub) - ollama (Ollama) - free (LLM7.io - No API key required )
Model Descriptions Anthropic Claude - Advanced reasoning and long-context capabilities.API Key: Sign up at console.anthropic.com OpenAI GPT - Industry-leading language models including GPT-4 and GPT-5.API Key: Sign up at platform.openai.com Google Gemini - Multimodal AI with strong reasoning and long context windows.API Key: Get one at ai.google.dev xAI Grok - Powerful models with real-time information access.API Key: Sign up at x.ai Meta Llama - Open-source models via API providers.API Key: Available through various providers
DeepSeek - Cost-effective models with strong coding capabilities.API Key: Sign up at platform.deepseek.com GitHub Models - Access to multiple models through GitHub’s marketplace.API Key: GitHub personal access token with model permissions
Ollama - Run models locally on your machine.Setup: Install from ollama.com Note: No API key required for local usageLLM7.io - Free tier access without API keys.Limitations:
8k characters per request
60 requests/hour
10 requests/minute
1 request/second
Note: No API key requiredlist-variants Display available variants for AI models.
Usage List all variants for all models.
gw list-variants --model < model-nam e >
List variants for a specific model.
Options Filter variants by model. Allowed values: claude, openai, gemini, grok, llama, deepseek, github, ollama, freeShorthand: -m
Examples All variants
OpenAI variants
Claude variants
Terminal Output Examples OpenAI Variants $ gw list-variants --model openai Available variants for openai: - gpt-4o (default) - gpt-5 - gpt-5-mini - gpt-5-nano - gpt-5-pro - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-4.5-preview - gpt-4o - gpt-4o-mini - gpt-realtime - gpt-realtime-mini - o1-preview - o1-mini - o3-mini
Claude Variants $ gw list-variants --model claude Available variants for claude: - claude-sonnet-4-20250514 (default) - claude-sonnet-4-5-20250929 - claude-opus-4-1-20250805 - claude-opus-4-20250514 - claude-3-7-sonnet-20250219 - claude-3-7-sonnet-latest - claude-3-5-sonnet-latest - claude-3-5-sonnet-20241022 - claude-3-5-sonnet-20240620 - claude-3-opus-20240307 - claude-3-sonnet-20240307 - claude-3-haiku-20240307
Gemini Variants $ gw list-variants --model gemini Available variants for gemini: - gemini-2.0-flash (default) - gemini-2.5-pro (advanced reasoning with thinking ) - gemini-2.5-flash (updated Sep 2025 ) - gemini-2.5-flash-lite (most cost-efficient ) - gemini-2.5-flash-image (image generation ) - gemini-2.5-computer-use (agent interaction ) - gemini-1.5-pro-002 (2M tokens ) - gemini-1.5-flash-002 (1M tokens ) - gemini-1.5-flash-8b (cost effective )
Grok Variants $ gw list-variants --model grok Available variants for grok: - grok-2-latest (default) - grok-4 (most intelligent ) - grok-4-heavy (most powerful ) - grok-4-fast (efficient reasoning ) - grok-code-fast-1 (agentic coding ) - grok-3 (reasoning capabilities ) - grok-3-mini (faster responses )
DeepSeek Variants $ gw list-variants --model deepseek Available variants for deepseek: - deepseek-chat (default) - deepseek-v3.2-exp (latest experimental ) - deepseek-v3.1 (hybrid reasoning ) - deepseek-v3.1-terminus - deepseek-r1-0528 (upgraded reasoning ) - deepseek-v3-0324 (improved post-training ) - deepseek-reasoner
Llama Variants $ gw list-variants --model llama Available variants for llama: - llama-3-70b-instruct (default) - llama-3-8b-instruct - llama-3.1-8b-instruct - llama-3.1-70b-instruct - llama-3.1-405b-instruct - llama-3.2-1b-instruct - llama-3.2-3b-instruct - llama-3.3-70b-instruct
GitHub Variants $ gw list-variants --model github Available variants for github: - gpt-4o (default) - DeepSeek-R1 - Llama-3.3-70B-Instruct - Deepseek-V3 - Phi-4-mini-instruct - Codestral 25.01 - Mistral Large 24.11 - etc. Check more on https://github.com/marketplace?type=models
Ollama Variants $ gw list-variants --model ollama Check Ollama models here: https://ollama.com/search
Free Tier $ gw list-variants --model free No variant selection - uses LLM7.io default model Anonymous tier limits: • 8k chars per request • 60 requests/hour, 10 requests/min, 1 request/sec Powered by LLM7.io - No API key required!
Using Models and Variants In Commands # Use specific model gw commit --model claude # Use specific variant gw commit --model openai --model-variant gpt-4o # Analyze with Gemini Pro gw analyze --model gemini --model-variant gemini-2.5-pro
Set as Defaults # Set default model gw set-defaults --model claude # Set default model and variant gw set-defaults --model openai --model-variant gpt-4o
Model Selection Guide For best quality:
claude with claude-opus-4-1-20250805openai with gpt-5 or o1-previewgemini with gemini-2.5-pro
For best speed:
openai with gpt-4o-miniclaude with claude-3-haiku-20240307gemini with gemini-2.5-flash-lite
For cost efficiency:
deepseek with deepseek-chatgemini with gemini-2.5-flash-litefree (no API key required)
For local/offline:
ollama with any local model
For coding tasks:
grok with grok-code-fast-1deepseek with deepseek-reasonergithub with Codestral 25.01