AI Model Configuration

Premail classifies your email using a large language model. It sends the sender, subject line, and message body to the model and asks it to categorize the message. You pick the provider.

Anthropic (Claude)

The default. Premail uses Claude Haiku, which is fast and very cheap. Unless you receive thousands of emails per day, the cost will be negligible. Get an access key from console.anthropic.com and paste it into the AI Model tab.

OpenAI

Works the same way. Paste in your OpenAI access key, pick a model. GPT-4o Mini is a reasonable choice if you're already in the OpenAI ecosystem and don't feel like creating another account somewhere.

Ollama (local, no data leaves your machine)

Ollama runs AI models locally. Nothing gets sent to any external server, which may matter to you a great deal or not at all, depending on your personal threat model.

1Download and install Ollama from ollama.com. A small icon will appear in your menu bar after installation.
2Open Terminal and pull a model. We recommend ollama pull qwen3 for the best classification quality on local hardware.
3In Premail's AI Model tab, select Ollama and enter the model name you pulled (e.g.qwen3).

Performance depends on your hardware. Classification will be slower than cloud providers, and quality varies by model. Larger models are more accurate but slower. qwen3 strikes the best balance we've tested for Premail's filtering tasks.

Your access keys are stored locally on your computer and are never sent to any Premail server. They go directly from your machine to whichever AI provider you've configured.

←What Happens When Your Computer Sleeps Built-in Rules→

Still have questions?

Contact Support (for Pro members)