Indium tin oxide is a byproduct of the zinc oxide refinement process so it's doesn't see sustainable/enough to go around which seems like graphene is a better choice. Right now, they're primarily made of perovskite which is hybrid inorganic/organic and a lil toxic. MIT has a few studies on using graphene for OPV.
To me it's never seemed like "inexpensive" and "indium" belong in the same sentence.
So off the top of my head I would say graphene which is just fancy carbon rather than a rare element like indium.
I would want to try them both in the lab but if you scale up there's probably not enough indium to go around no matter how thin you spread it.