Skip to content

Which model should I use for the cheapest demo? #42

Description

@bornajerk

tried gpt-4o and it burned like $3 just opening settings. the readme mentions qwen somewhere but doesn't say if it actually works for screen reading or just text stuff. anyone got a working cheap setup? just need the lowest cost that can reliably read a screen and click a button, don't care about speed.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions