by TurdF3rguson 4 hours ago
It also means giving up vision which I don't know how I would deal with. I think I would prefer a weaker model with vision than a stronger without.
Openrouter definitely supports vision models. Why would you have to give up vision?
For example if I want to paste a screenshot of what I mean, I can't.
vision runs just fine locally for most usecases, so it's really just a skill to call that Ollama instance
If you using opencode or similar you can just temporarily switch models -- in the same session -- to something that has vision and have it look at your image. And then switch back.
[dead]
Why's that?