Comment by cmrdporcupine
3 days ago
Congrats def in order but as usual the proof will be in the pudding of actually running the thing.
GLM 5.2 has token efficiency problems. It's not a stupid model, but it takes a lot of "thinking" to produce not-stupid results. ("But wait...").
Which makes its pricing deceptive.
I tried to get by through the month of June on just GLM 5.2 and it was ... fine-ish for about two weeks. But the provider situation wasn't ideal.
Have you counted your thinking tokens for say Opus or Fable? It wouldn’t surprise me if frontier closed models “over-reason” just as much, but you don’t see it thanks to the summariser.
(We do know GPT5.6 have adopted the caveman shorthand, which explains its token efficiency).
I have a $200 monthly Codex plan. I never run out of budget and it's... disturbingly smart. It's very hard for anything to compete with that right now.
I do occasional experiments where I cancel or downgrade that and try to live on open models only and it just never works out financially or skills wise. There's nobody offering K3 etc at rates that end up being significantly cheaper.
Yet.