I 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.
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.
Same, I am actually able to reach my weekly limit, but when I start going below 30%, I switch to normal speed, and that usually gets me through the week.
I absolutely save money and time by constantly using everything at the highest reasoning. I guess my use case and needs are different from others, but I really don’t understand how it can be true when people say they don’t need the highest reasoning and best model. Every time I drop down, things are missed, code gets unnecessarily bloated, more mistakes, and more iterations to solve the same problem. I think it might be because I’m spending a lot of time in a legacy system that I’m trying to clean up, and given the messiness, one needs all the reasoning available to decode what the hell is going on in there.
I have found that higher reasoning doesn't always produce better results. Models often tend to overthink and get themselves in a bind. And tasks just take longer for no reason.
I used to have the same experience until 5.6 sol xhigh. I have instructions in my code review skill and agents.md to encourage parallelism including multiple agents as long as quality isn’t impacted. I additionally instruct codex to not use less capable agents because at least with 5.5 this would seriously increase slop. Maybe sol is smarter about delegation. Hopefully because I’ll have to slow down or hopefully get approval for extra use credits. Now’s a great time for a limit reset if anyone from open ai is reading :).
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
> I really wish there was just an easy guide on when to use Sol vs Terra vs Luna
Their dev guide has the following:
> Use gpt-5.6-sol for frontier capability, gpt-5.6-terra for a balance of intelligence and cost, or gpt-5.6-luna for efficient, high-volume workloads. The gpt-5.6 alias routes requests to gpt-5.6-sol
It's just how LLMs work - these are three completely separate models trained in parallel, with different numbers of parameters and using different amounts of compute.
They could hide this behind a harness that picks the correct model for you, but devs don't seem to like that.
There's also the 'effort' slider, which I guess how many experts in the MoE are evaluated and how long reasoning chains are allowed to go on, which is the 'smooth' scaling you are thinking of.
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.
Previously it was much more obvious which model to reach for depending on your use case because they had the mini and nano naming conventions.
Getting rid of that seems like a step back. Just a personal nit though.
I've seen buzz about this elsewhere as well but to me effort levels seem more like spend limits disguised with another word. I don't think they should even exist.
The naming convention is bizarre and doesn't really mean anything to normies. Trying to pick between "Sol" and "Terra" is like asking the average person if they want the Max or the Ultra chip.
"i really wish this thing in my non native language was easier to decipher"
huh? if you dont know the words then read them in your native language. Sol/Terra/Luna are immediately unambiguous to an english speaker with any sense.
That isn't what "genuinely asking" looks like, you're criticizing using "questions" as cover. It isn't subtle, nor is it constructive.
I agree with them, Sol, Terra, and Luna are confusing names. They mean the same thing as GPT-5.6-Max, GPT-5.6-Plus, and GPT-5.6-Fast but require base knowledge for an analogy.
It feels like it was adding by the marketing department.
I'd agree it is similar to Anthropic's naming scheme, which I'd argue shares the same problems as this. It improves marketability/googlability, but decreases actual comprehension.
You don't actually explain why or how these names are "easy to understand" just state that they simply are. That's great; to me, they aren't obvious or intuitive at all. May have well just start randomly pointing at dictionary words.
I collect roman coins, with latin legends, so the sun/earth/moon references jumped out at me, and partly based on the opus/sonnet/haiku precedent I assumed that these names were referring to different model sizes/prices in a way that mapped to the names (Sun > Earth > Moon).
I'll admit though that until recently I never really thought about Anthropic's naming scheme as having meaning (an Opus being longer than a Sonnet, being longer than a Haiku).
This demonstrates the problem with an education that has no emphasis on the liberal arts, such as critical thinking. No justification is needed for why and how these names are easy to understand.
>They mean the same thing as GPT-5.6-Max, GPT-5.6-Plus, and GPT-5.6-Fast but require base knowledge for an analogy.
But do they though? When do you use GPT-5.6-Max-Low vs. GPT-5.6-Plus High? Or GPT-5.6-Fast-Xhigh? What's the Pareto optimal choice (outcome and price)? According to the benches it seems to bop around and the even if the benches are accurate the best choice isn't always consistent.
> When do you use GPT-5.6-Max-Low vs. GPT-5.6-Plus High?
You don't, because that isn't something I proposed using for model naming.
I called them GPT-5.6-Max, GPT-5.6-Plus, and GPT-5.6-Fast. Reasoning levels are distinct from the model design itself, and the UI makes that clear.
Plus, using that same flawed argument this would be called GPT-5.6-Sol-Low or GPT-5.6-Luna-High which also makes no sense/is confusing. So that argument applies (or more accurately doesn't), no matter the model names.
Your names are not good because “Fast” is not a descriptor of model size and overlaps with fast/ultrafast inference. And “Plus” collides with the ChatGPT subscription plan. Point being, naming is hard.
I do know what Sol/Terra/Luna mean, but was also confused for a second on the hierarchy. After doing a bit or research it dawned on me that they are arranged in the order of the sizes of the celestial objects but it somehow wasn't immediately obvious to me from the start.
Anthropic ships models with a helpful one-liner tag that makes the model hierarchy obvious. I think it wouldn't hurt if OpenAI did the same.
Did you not read the second sentence? Obviously I know what sol is given my first language being Spanish. I'm just speaking in a general sense that it can be confusing for others.
I already know plenty who had no clue what the difference between Terra and Luna would be.
My first instinct was Sol > Luna > Terra, since Sol is the farthest away, then Luna, and Terra is the closest. Size was not my first instinct. Or should Terra be the best model because its closest to people, then Luna because there have been people on it, then Sol be the worst because no human has been there?
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.