Skip to main content
GitWhisper supports multiple AI model providers, giving you flexibility to choose the model that best fits your needs, budget, and infrastructure.

​
Supported Providers

GitWhisper integrates with leading AI providers and offers both cloud-based and self-hosted options:

OpenAI

Industry-leading models including GPT-4o, GPT-5, and o-series reasoning models

Claude

Anthropic’s powerful Claude models, including Opus 4 and Sonnet 4.5

Gemini

Google’s advanced Gemini 2.5 with thinking modes and large context windows

Grok

xAI’s powerful Grok models with advanced reasoning capabilities

Llama

Meta’s open-source Llama models for flexible deployment

DeepSeek

Advanced reasoning models from DeepSeek with hybrid capabilities

GitHub Models

Free access to premium models with your GitHub account

Ollama

Self-hosted open-source models for complete privacy and control

Free Model

No API key required - powered by LLM7.io

​
Choosing a Model

​
For Best Quality

If you want the highest quality commit messages and code analysis:
  • OpenAI GPT-4o or GPT-5 - Best overall performance and reasoning
  • Claude Opus 4 - Excellent for understanding complex code changes
  • Gemini 2.5 Pro - Advanced reasoning with thinking mode

​
For Speed and Cost

If you prioritize fast responses and lower costs:
  • OpenAI GPT-4o-mini - Fast and cost-effective
  • Claude Sonnet - Good balance of speed and quality
  • Gemini 2.5 Flash - Efficient with low latency

​
For Privacy

If you need to keep your code completely private:
  • Ollama - Run models locally on your own hardware
  • No data leaves your machine
  • Supports llama3, codellama, mistral, and more

​
For Free Usage

If you want to try GitWhisper without API keys:
  • Free Model - Powered by LLM7.io, no signup required
  • GitHub Models - Free tier with GitHub PAT (rate limited)
Rate limits apply: Free and GitHub models have usage limits. For production use, consider a paid API provider.

​
Setting Your Default Model

Set a default model to avoid specifying it with each command: 
# Set default model
gitwhisper set-defaults --model openai

# Set default model with specific variant
gitwhisper set-defaults --model claude --model-variant claude-opus-4-20250514

# View current defaults
gitwhisper show-defaults

​
Using Different Models

You can switch models for any commit: 
# Use OpenAI
gitwhisper commit --model openai

# Use Claude with specific variant
gitwhisper commit --model claude --model-variant claude-opus-4-20250514

# Use free model
gitwhisper commit --model free

​
Model Variants

Each provider offers multiple model variants with different capabilities:
  • Default variants are used when no variant is specified
  • Latest models offer the newest features and improvements
  • Mini/Fast variants provide faster, more economical options
  • Specialized variants like reasoning models for complex analysis
See the Model Variants page for a complete list.

​
API Key Management

Most models require an API key. GitWhisper provides multiple ways to configure keys:
Store your API key permanently:
gitwhisper save-key --model openai --key "your-api-key"
Learn more about API key configuration in the Configuration Guide.

​
Custom Endpoints

For Ollama and other self-hosted solutions, you can configure custom base URLs: 
gitwhisper set-defaults --model ollama --model-variant llama3 --base-url http://localhost:11434
See Custom Endpoints for more details.

​
Next Steps

View All Variants

Complete list of available model variants

API Keys Setup

Configure your API keys securely

OpenAI Models

Learn about OpenAI model options

Claude Models

Explore Claude model capabilities

Build docs developers (and LLMs) love

Get started for freeTalk to us