#Would "MedGemma Text only model" be ever added to Openrouter?

31 messages · Page 1 of 1 (latest)

kind crown
#

I am trying to develop a school project and I cannot afford hosting a Virtual Machine all by myself, could it be added soon? Thanks for your time.

flint palm
kind crown
flint palm
kind crown
#

since I saw a Dutch tool called Autoscriber, it uses GPT 3.5 and GPT 4

#

based on their peer reviewed academic research paper.

nova orchid
#

its multimodality?

kind crown
#

I saw that it out performs many models on the out put.

#

For analyzing documents and images and getting medical reports.

nova orchid
#

so multimodality

kind crown
#

GPT is general, not specilised.

nova orchid
#

as soon as you drop the image requirement, there are dozens of models that are better despite being general

#

some are western, some are chinese

#

some are open, some are closed

#

some are big, some are small

#

but (med)gemma is outcompeted outside of multimodal

kind crown
#

So it'd be better to use GPT 5 Thinking model

nova orchid
#

yeah gpt-5 (thinking) is a much better model

kind crown
nova orchid
#

fine tuning can be expensive and openrouter doesn't expose it yet

kind crown
nova orchid
#

prompt engineering is worth looking into yes

#

models can learn in context

#

there are even frameworks like dspy for that kind of thing (although i've never used them)

kind crown
#

Alright, thank you so much ❤️

nova orchid
#

gl