Configuration¶

GPTChangelog can be configured at both the global and project levels. This page explains all available configuration options and how to manage them.

Configuration Locations¶

GPTChangelog looks for configuration in the following locations, in order of precedence:

If a setting is defined in both places, the project-specific setting takes precedence.

To create a new configuration file:

gptchangelog config init

You'll be prompted to choose between global or project-specific configuration and enter your OpenAI API key and preferred model.

To see your current configuration:

gptchangelog config show

This will display both global and project-specific configurations if they exist.

The configuration file uses the INI format:

[openai]
api_key = your-api-key-here
model = gpt-5-mini

Option	Description	Default
`api_key`	Your OpenAI API key	(Required)
`model`	The OpenAI model to use	`gpt-5-mini`

You can also use environment variables to override configuration settings:

Variable	Corresponding Config Option
`OPENAI_API_KEY`	`[openai] api_key`
`GPTCHANGELOG_MODEL`	`[openai] model`

Environment variables take precedence over configuration file settings.

GPTChangelog works best with GPT-5 family models, but you can use other options:

[openai]
model = gpt-3.5-turbo

Smaller models may produce less comprehensive results but can be more cost-efficient.

You can maintain different configurations for different projects:

[openai]
api_key = your-api-key-here

[openai]
api_key = your-api-key-here
model = gpt-5-mini

[openai]
api_key = your-api-key-here
model = gpt-5-mini

[openai]
api_key = your-api-key-here
model = gpt-3.5-turbo