alt Hacker NewsI really wish there was just an easy guide on when to use Sol vs Terra vs Luna, and it just moves further into confusing territory when it comes to naming.
The naming convention is especially difficult to decipher depending on what your native language is. Of course a latin language speaker might be able to easily determine oh yeah each one is slightly bigger than the other but I still think it borderlines too confusing.
That aside all the numbers look amazing, and I'll be happy to probably main this alongside grok-4.5 for a while comparing the two on price and efficiency.
I vastly prefer the direction that OpenAI seems to be going with token efficiency and performance compared to Anthropic who seems to be moving towards a world where you just token-max as much as possible ignoring any and all costs.
Replies
My guess is that it's the same for Haiku/Sonnet/Opus: Biggest model for architecture and high level planning and technically challenging problems, medium model for simple implementation tasks, small model is for nothing
Use Luna. It's more performant than 5.5 and it's cheap. Hopefully it's cheap because it's more environmentally friendly than the bigger models. So you're doing a good thing. If it's a smaller model it may even be faster, but I haven't looked into it yet.
I love how all the replies to this comment recommend completely different strategies for deciding which model to use.
it's simple: unless trivial TOIL, always use the highest at ultra max settings.
In my tests, in almost all cases, using Sol on (low) reasoning is the best option intelligence/price-wise.
Luna is good too, for classification tasks or any pre-processing task that is not critical
Why would you need a guide for that now? We long had to pick different models (and thinking levels) by task and feel.
You don’t know what sol means? You don’t understand the difference in sizes between Terra and sol? I’m genuinely asking.
I use the strongest model (5.5 now 5.6 sol) on the highest reasoning effort with /fast for everything. With a $200 pro sub I can't even use my weekly limit. And it's faster than using a weaker model that makes more mistakes which I have to waste time fixing.