Post #3541440
2026-07-02 19:00 UTC
@osteel@phpc.social Which models are you trying?
My work accounts are OpenAI/Cursor/Claude but personally I have Ollama Cloud and OpenCode Go accounts, both of which are pretty reliable at this point now that they've scaled up to handle the GLM 5.2 rush.
Another option, if you're paying API rates anyway (OpenCode Go and Ollama Cloud are subsidized), would be GitHub Copilot. Smaller cheap model selection, but at this point inference on them is pretty reliable.
Replies (1)
-
@osteel@phpc.social 2026-07-02 20:01
@ian@phpc.social so this isn’t for coding work, but as part of some application logic. I’m basically doing image comparisons, and I’m struggling to find reliable providers to try out Chinese models (I’ve exhausted most "western" models by now). But it seems to be related to image size more than anything (although the models I’m testing aren’t supposed to have any size limits)