Complete list of all available model variants across providers
This page lists all available model variants for each AI provider supported by GitWhisper. Use these exact names when specifying variants with the --model-variant flag.
# List all variants for all modelsgitwhisper list-variants# List variants for a specific modelgitwhisper list-variants --model openaigitwhisper list-variants --model claude
# Use GPT-5gitwhisper commit --model openai --model-variant gpt-5# Use o3-mini for reasoninggitwhisper commit --model openai --model-variant o3-mini# Set as defaultgitwhisper set-defaults --model openai --model-variant gpt-4o
claude-sonnet-4-5-20250929 # Default - best balanceclaude-sonnet-4-20250514 # Stable Sonnet 4claude-opus-4-1-20250805 # Enhanced Opus with extended contextclaude-opus-4-20250514 # Most powerful Claude
claude-3-opus-20240307 # Most powerful Claude 3claude-3-sonnet-20240307 # Balanced Claude 3claude-3-haiku-20240307 # Fast and efficient
Usage Example
Recommendations
# Use latest Sonnet 4.5gitwhisper commit --model claude --model-variant claude-sonnet-4-5-20250929# Use Opus 4 for maximum qualitygitwhisper commit --model claude --model-variant claude-opus-4-20250514# Use Haiku for speedgitwhisper commit --model claude --model-variant claude-3-haiku-20240307
gemini-1.5-pro-002 # Up to 2M tokens contextgemini-1.5-flash-002 # Up to 1M tokens contextgemini-1.5-flash-8b # Most cost-effective
Usage Example
Recommendations
# Use default 2.0 Flashgitwhisper commit --model gemini# Use 2.5 Pro with thinking modegitwhisper commit --model gemini --model-variant gemini-2.5-pro# Use 1.5 Pro for massive contextgitwhisper commit --model gemini --model-variant gemini-1.5-pro-002
llama-3.3-70b-instruct # Latest 70B modelllama-3.2-3b-instruct # Small efficient modelllama-3.2-1b-instruct # Tiny efficient modelllama-3.1-405b-instruct # Largest Llama modelllama-3.1-70b-instruct # Large balanced modelllama-3.1-8b-instruct # Small fast model
llama-3-70b-instruct # Default - proven qualityllama-3-8b-instruct # Fast and efficient
Usage Example
Recommendations
# Use Llama 3.3 70Bgitwhisper commit --model llama --model-variant llama-3.3-70b-instruct# Use small model for speedgitwhisper commit --model llama --model-variant llama-3.1-8b-instruct
gpt-4o # Default - OpenAI's flagshipDeepSeek-R1 # DeepSeek reasoningLlama-3.3-70B-Instruct # Meta LlamaDeepseek-V3 # DeepSeek V3Phi-4-mini-instruct # Microsoft Phi"Codestral 25.01" # Mistral code model (quote the name)"Mistral Large 24.11" # Mistral large (quote the name)
Some model names contain spaces and must be quoted when used on the command line.
Usage Example
More Models
# Use GPT-4o (default)gitwhisper commit --model github# Use DeepSeek for reasoninggitwhisper commit --model github --model-variant DeepSeek-R1# Use Codestral (note the quotes)gitwhisper commit --model github --model-variant "Codestral 25.01"
Ollama supports hundreds of models. You can use any model from ollama.com/library.Popular choices:
llama3.2:latest # Default - balanced choicecodellama # Code-optimizeddeepseek-coder # Excellent for codeqwen2.5-coder # Qwen code modelphi3 # Fast and efficientgemma2 # Google's modelmixtral # High qualityllama3:70b # Large powerful model
Usage Example
Find Models
# First, pull the model locallyollama pull codellama# Then use with GitWhispergitwhisper commit --model ollama --model-variant codellama# Use specific versiongitwhisper commit --model ollama --model-variant llama3.2:3b
You can set a default model and variant to avoid specifying them each time:
# Set default model only (uses default variant)gitwhisper set-defaults --model openai# Set default model with specific variantgitwhisper set-defaults --model claude --model-variant claude-opus-4-20250514# Set for Ollama with custom base URLgitwhisper set-defaults --model ollama --model-variant codellama --base-url http://localhost:11434# View current defaultsgitwhisper show-defaults# Clear defaultsgitwhisper clear-defaults
# Check current variantsgitwhisper list-variants# Check for specific modelgitwhisper list-variants --model claude# Update GitWhisper to get latest modelsgitwhisper update
New models are added regularly. Check the GitHub repository for announcements.