Models and Auth¶

The reviewer runs on a separate AI model that you choose. Zwischen supports models from Anthropic, Google, OpenAI, and DeepSeek.

Choosing a model¶

Set the reviewer model in your defaults or in a profile:

defaults:
  model: gpt-5.4
  api_key: your-openai-key

Different models behave differently as reviewers. Zwischen Labs runs continuous test suites across providers and models to understand these differences, and applies provider-specific and model-specific prompt adjustments automatically. You can disable these adjustments with model_tuning: false if you want the base reviewer prompt only.

See Supported Models for the full list.

API key authentication¶

The default authentication method is API key. Provide the key in one of two ways:

In settings.yaml:

defaults:
  api_key: your-provider-key

Via environment variable:

Set the provider's standard environment variable: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, or DEEPSEEK_API_KEY. You can also set these in the env block of your settings file:

env:
  ZWISCHEN_API_KEY: "your-zwischen-key"
  OPENAI_API_KEY: "your-openai-key"

Values in the env block are defaults — real environment variables take precedence.

The API key is never sent to the Zwischen server. It is held in process memory on your machine only and passed directly to the model provider.

OAuth authentication¶

OpenAI also supports OAuth authentication, which authenticates via your ChatGPT account instead of an API key.

To set up OAuth:

zwischen oauth

Then set auth_mode in your settings:

defaults:
  model: gpt-5.4
  auth_mode: oauth

OAuth is currently supported for OpenAI only. Other providers require API key authentication.

You can also re-authenticate or check OAuth status mid-session:

/z oauth

Model tuning¶

When model_tuning is true (the default), Zwischen applies provider-specific and model-specific prompt adjustments tuned by Zwischen Labs. These adjustments account for behavioral differences between models — an OpenAI model reviewing code may react very differently to the same event stream than a Gemini model.

Set model_tuning: false to disable these adjustments and use the base reviewer prompt only.

Configuration reference¶

Key	Type	Default	Description
`model`	string	—	Model ID for the reviewer
`api_key`	string	—	Provider API key
`auth_mode`	string	`"api_key"`	`"api_key"` or `"oauth"` (OpenAI only)
`model_tuning`	boolean	`true`	Apply provider-specific prompt adjustments