Show HN: Lunon – Instant model switching across LLMs • Hacker News Board

Show HN: Lunon – Instant model switching across LLMs

#1

Post by johnmcelhone » Fri, Apr 11, 2025, 6:16 PM UTC

Hey HN! We built Lunon to make LLM development way less of a headache. Ever wanted to see how different models handle the same prompt without all the setup hassle? That's what we fixed.

Our API lets you compare Claude, GPT, Mistral and others in real-time with just a few lines of code. No more complex infrastructure or managing multiple API connections - we handle all that boring stuff behind the scenes.

Plus, you can cut costs by intelligently routing requests to the right model for each task. Use the powerful (expensive) models only when you really need them.

If you're building with LLMs and tired of the integration headaches, would love to hear feedback!

Show HN: Lunon – Instant model switching across LLMs
lunon.com

Re: Show HN: Lunon – Instant model switching across LLMs

#2

Post by dinobones » Fri, Apr 11, 2025, 7:18 PM UTC

Nice webpage/design, but what is the advantage over Openrouter that already has ~trillions tokens/month in traffic?

Re: Show HN: Lunon – Instant model switching across LLMs

#3

Post by cchance » Fri, Apr 11, 2025, 7:41 PM UTC

Nice websites but seriously,

A. a pricing link that takes you to NOT pricing B. listing Grok and Groq in the same block as if they have anything to do one another is a bad choice

Re: Show HN: Lunon – Instant model switching across LLMs

#4

Post by chipgap98 » Fri, Apr 11, 2025, 7:56 PM UTC

You have early access to the o4 models?

Re: Show HN: Lunon – Instant model switching across LLMs

#5

Post by turnsout » Fri, Apr 11, 2025, 7:57 PM UTC

Gotta fix the typo on Anthropic's name

Re: Show HN: Lunon – Instant model switching across LLMs

#6

Post by rgbrgb » Fri, Apr 11, 2025, 8:03 PM UTC

neat idea. random tiny piece of site feedback: make the hero backgrounds dark so that the text is legible as the image loads in.

more constructively, this is the kind of code ai is great at writing in my codebase and once it’s there locally as a library, it’s free. it’s not clear to me why I’d want it behind an api instead, at least as a solo-ish dev. I’d recommend looking at the similar openrouter that seems to have some traction and think about why users are using them. You might also think about deeper agent or eval stuff you could add that are beyond the scope of the little backend switching lib I could have Claude write. Anyway, good luck and thanks for sharing!

Re: Show HN: Lunon – Instant model switching across LLMs

#7

Post by _bin_ » Fri, Apr 11, 2025, 8:11 PM UTC

Front page says "Antrophic" rather than "Anthropic" :)

Some people may also find the grok/groq section confusing

Re: Show HN: Lunon – Instant model switching across LLMs

#8

Post by johnmcelhone » Fri, Apr 11, 2025, 8:25 PM UTC

_bin_ wrote: post #7

Front page says "Antrophic" rather than "Anthropic" :) Some people may also find the grok/groq section confusing

That was my bad - just fixed that mistake. Thanks for catching it!

Will explore some more ideas for the Groq & Grok part too.

Re: Show HN: Lunon – Instant model switching across LLMs

#9

Post by johnmcelhone » Fri, Apr 11, 2025, 8:28 PM UTC

cchance wrote: post #3

Nice websites but seriously, A. a pricing link that takes you to NOT pricing B. listing Grok and Groq in the same block as if they have anything to do one another is a bad choice

Didn't catch the pricing bug, will update right now.

A few others have also mentioned about the Grok & Groq confusion. Will think through some ideas here and update.

Appreciate the feedback!

Re: Show HN: Lunon – Instant model switching across LLMs

#10

Post by johnmcelhone » Fri, Apr 11, 2025, 8:29 PM UTC

turnsout wrote: post #5

Gotta fix the typo on Anthropic's name

Fixed, thank you!