[Oras]

Also pricing, I wanted to give a try, but when pricing is only 30% cheaper than Opus, I wouldn't go for it with these issues.

[chpatrick]

It's pricing is a lot cheaper if you can run it yourself.

[jeremyjh]

What?

It is less than 20% of the cost of Opus at API rates. 1.40/4.40 vs 5/25.

[cmrdporcupine]

Not when you factory in token efficiency. It burns a lot more tokens to do the same job, so when I compared to GPT5.5 I was frankly not really much ahead, and with weaker thinking.

Maybe makes sense if you have z.AI's (not greatly priced) subscription plan, but it's not competitive against an OpenAI or Anthropic monthly coding subscription plan. I burned through almost $10 worth of tokens just doing an hour of work.