YHK - yet another hacker news clone

Best LLM for every budget, updated daily

60 points terryds 1 hour ago 34 comments

radial_symmetry 39 minutes ago | parent

The coding and math tabs seem to be missing the latest models...

SkyBelow 25 minutes ago | parent

Math in particular is quite far behind. GPT 5.2 is recommended as the best for highest cost. Really?

pelagicAustral 37 minutes ago | parent

Is there a cheaper model than Gemini 3.8 Flash (High) that maybe/kind-of is on-par with it? For me it works really good but hit the limit in two hours tops... last week was the first time I hit the weekly limit and had to wait 4 days... Claude patches OK, but that is also getting drained really fast these days...

TomGarden 36 minutes ago | parent

is this on the $20-ish sub? I hear ultra lasts for a very long time

pelagicAustral 34 minutes ago | parent

Yeah, 20... I was going to try Deepseek later on, just chuck 20 in there and see how good it does, and how far I can go as well...

TomGarden 32 minutes ago | parent

yeah I enjoy the speed of Gemini, but I also just have the low tier one (I use the 20x Claude and Codex subs for most of my work). For iteration, Gemini is so much fun, but Opus 5.5 is quite fast, as is sol. If you're on a budget, deepseek does look great

pelagicAustral 27 minutes ago | parent

Yeah, I mean, I think in theory I could push it to the next tier on Gemini, but at the same time I wouldn't mind trying something else, since maybe my workloads are not really that smart and I am wasting a lot of computational power on something a cheaper model with similar capabilities can do.

montroser 35 minutes ago | parent

DeepSeek 4.1 Flash is your answer.

pelagicAustral 33 minutes ago | parent

Ah OK, yeah, I was actually going to go for that earlier, I'll check it out once I get home, thanks!

Tepix 37 minutes ago | parent

1. In real life, most of us use token packages like OpenCode Go etc.

It would be handy to have a site like this one that takes into account the various deals and attempts to calculate the number of tokens per monthly fee for a chosen model. I realize this makes the task a lot more difficult.

2. It would be handy to have a chart like that for the AI hardware that people own. It helps you decide which model to run (resulting in different levels of intelligence and speed). Also difficult to please everyone (preprocessing vs token generation for example) and to keep updated!

I found https://llm-list.com/ yesterday and when I had a detailed look, I quickly found outdated entries, for example looking at GLM 5.3 flash it listed several providers as "free" that weren't free any longer.

TomGarden 36 minutes ago | parent

If you maintain this over time, maybe include other sources than just AA and update the design to look less like zero-shot claude styling (I know that font! I know that color! Lol) it's genuinely useful :)

jwolfe 36 minutes ago | parent

This definition of cost is not particularly useful. You want cost per task, not cost per 1m tokens. Artificial Analysis does a good job of this.

hsnewman 35 minutes ago | parent

I'm sure that local LLM will be far cheaper

mrngld 14 minutes ago | parent

Depends on what level of intelligence you're wanting to use. A vanishingly small number of people can or would want to go to the hardware expense of running something like GLM 5.3 Flash, much less something like K3.

And if you want Astra/Fable/Opus frontier level, then there's no option at all.

But if you don't need that, or you don't need speed... That opens up the discussion. I've been impressed even with how Siri's been doing with the Apple Foundation Models in MacOS/iOS 27 given how small they are.

Edit: I can't even fully spec the M5 Ultra Mac Studio you'd need for GLM5.3 Flash since 512GB isn't available yet, but it's already at $9500 for 256GB RAM.

aslkalska 32 minutes ago | parent

all I ever wanted is an updated website where I can see the best models I can run on my different devices locally, I don't get why people are throwing money at these companies

jeremysalwen 31 minutes ago | parent

It's missing Opus 5.5 which was released over a day ago (and also is clearly on the pareto frontier).

shakow 28 minutes ago | parent

Don't know if they updated it since your comment, but for me it's on the graph – and on the Pareto frontier indeed.

SJMG 20 minutes ago | parent

For intelligence only as of 8:51 MT

noumenon1111 10 minutes ago | parent

It was expert timing on the commenter's and the developer's part. Opus 5.5 still doesn't show under coding though.

npongratz 10 minutes ago | parent

Opus 5.5 is indeed on the Intelligence tab, but I don't see it on the Coding or Math tabs.

floppyd 27 minutes ago | parent

As the time goes on it only becomes harder to differentiate between model capabilities with just one or two numbers. I would love to see some kind of multi-axis placement of all the models on less objective attributes, like wordiness, willingness to give up, an ability to "think ahead" and pre-solve possible problems in code, for example, that I didn't think of or didn't think of talking about, etc etc etc.

For example I've been really enjoying Deepseek v4.1 Flash, it's very "straightforward" to the point of being almost dumb sometimes, but it's absolutely relentless and would solve almost any problem no matter how inefficient the solution is.

No idea how to measure all that, just average CoT length per task is probably a good approximation for some things, but not others.

jrflo 24 minutes ago | parent

Does anyone actually pay API costs out of their own pocket? It's about 10x cheaper to just get a codex or chat gpt subscription, it's so heavily subsidized compared to the API that I'm sure it would be cheaper to use frontier models on a subscription plan rather than paying API prices for deepseek flash.

h46u5jytyhtg 21 minutes ago | parent

Large enterprises pay per token even through a ChatGPT “membership”, for example.

jrflo 18 minutes ago | parent

Which is why I said "out of their own pocket"

lowercased 21 minutes ago | parent

I do. For local dev work, I'm mostly using jetbrains' Junie, I can swap between a collection of models from google, openai, anthrophic.

I've had more than a few people tell me "oh, it's so much cheaper to use a $20 claude account" or "i've never hit a limit ever using my openai". Inevitably.. I end up reading/hearing "oh, I need to give it another couple hours to start using it again"... I've never hit that with my approach, even if it's costing me a bit more. Being able to work when I want when I have time has some value.

I also have openai and anthropic direct API billing set up for hosted and client projects that need to call out to an LLM service.

the__alchemist 18 minutes ago | parent

I thought Air was JB's multi-model interface? What is Junie? (I see the buttons, but am very confused by JB's AI offerings in general)

Is it worth the ~10x extra cost over the subscriptions? (This is obviously a leading question). Also, I think you can use OpenAI's subcription login with Air, but not Claude's.

jrflo 17 minutes ago | parent

Why not use a codex or claude subscription? If you use the entire usage allotment on the $200 plan it's about $2,000 in equivalent API costs. Switching providers may be valuable but it's quite literally an order of magnitude cheaper.

mmmattt 14 minutes ago | parent

I do, 3-4$ a month of deep seek is enough for my usage

LeBit 12 minutes ago | parent

I use local LLMs on my Mac Mini.

Otherwise DeepSeek Flash 4.1 is dirt cheap (other "Flash" models are not that expensive either). I pay (very few dollars) out of my own pocket.

There are many things where having an API Key is necessary.

Maybe I’ve missed the boat though: is there now a method to use an api key to access a subscription?

jrflo 5 minutes ago | parent

You can't use an API key on subscriptions, but I've gotten around it using the `codex exec` command to run requests outside the CLI or GUI if you're already authenticated on that machine. Won't work for all cases, but I've never ran into a limitation in my use case of not having an API key.

ford 18 minutes ago | parent

You're better off going directly to artificial analysis, this is a feature-poor/misleading/outdated repackaging

Ex. this type of price estimation is quite naive - some models can require 2-3x the number of tokens to achieve the same level of intelligence. Artificial Analysis' own cost per task is a more fair estimation of cost.

Xeoncross 13 minutes ago | parent

If you have a 24-64GB mac, consider running Qwen3.8 27B locally at night. It's a bit slower to run locally, but if you're sleeping it's less of a problem.

Depending on your memory, you'll need to use the weaker Q4 versions but they still perform well.

It ranks higher than GPT-5.3 Codex (xhigh) or Claude Opus 4.6 (max) so is great for pairing with https://github.com/kunchenguid/gnhf for nightly experimentation, cleanup, or recommendation lists for in the morning.

newsy-combi 12 minutes ago | parent

Coding and math graphs are very interesting. Extremely cheap models make it into the upper echelon, delivering 90% of the performance for 1% of the price compared to the #1.

verytrivial 12 minutes ago | parent

I find it interesting that with the given metric comparison, for coding at min 50 strength, every frontier model brand is from a distinct vendor: Ling, Qwen, Gemini, Muse, Grok, GPT, and Claude in increasing value.