Hacker News Reader

Comment by quirino | Hacker News Reader

I generally just check the Price/Performance graph on Openrouter: https://openrouter.ai/rankings#performance#benchmarks. Activate the "Show Pareto" toggle on the right.

I was still using GLM-5.2 in my personal projects, but this just made Luna a very easy choice.

View on HN

Hasn't OpenRouter had Luna and Terra on 50% off sale since they launched? I wonder what will happen to that.

It's still 50% off apparently. Listed as $0.10 for input (original price was $1.0 without this reduction or sale)

You're right, they've continued the 50% off on the new 80% off price. So it's now 90% off yesterday's OpenAI price.

The official doc says, Luna = Previous Nano models, kind of. Is it really good at coding?

Depends on the reasoning effort, see https://deepswe.datacurve.ai (add Luna via model selection drop down, if it's not shown by default)

Thanks for the link!

According to the link I mentioned above it's roughly as good as GPT-5.4. Haven't tried it in practice yet.

I bet it must be better in some contexts and worse in others.

Smaller models are great if you are doing targeted changes in existing codebases. Don’t expect to use it for creating complex architecture from scratch or do major refactors. The larger the context, the greater the drop off will be.

Smaller models are also excellent executors/operators. When given a solid plan, including e.g. what files/functions to change and how, what to test, even a recent 27-30B open weight model will usually do an excellent job.

Reply on news.ycombinator.com