HN Explorer

17 comments

[ 2.6 ms ] story [ 113 ms ] thread
pecord
Little miss leading as it is sorted by number of output tokens, and I’ve heard Grok is rather verbose.
behnamoh
Misleading because much of Grok's traffic is through their free endpoint. Title should be:

    Grok is the most popular free cloud model on OpenRouter
And even then this wouldn't matter because most devs don't use OpenRouter (commissions!, incompatible API in edge cases, etc.), and most LLM enthusiasts who want to run free models do it on their own machine.

---

Edit: Most → Much

tripplyons
The Grok 4 Fast and Grok Code Fast models have really impressed me. The only issue I've had is reaching a rate limit on the Grok 4 Fast model. Amazing pricing for highly capable models with good tool calling support.
TeeWEE
Is open router used a lot? I just use claude code, so this is a misrepresentation of what is actually the most popular model right?
blackhaj7
I was hesitant to use Grok but have actually found it to be excellent and it has totally replaced ChatGPT for me now.

The biggest difference is that it isn’t sycophantic and will often tell me I am wrong when I am. This makes way more of a difference than I thought it would as I feel I can trust the results more (perhaps naively)

rcarmo
FYI, GPT-5 in GitHub Copilot has (almost) completely gotten rid of the “you’re absolutely right” and faux Californian enthusiasm those of us with a British English bias find so condescendingly irritating. ;)

I should try Grok for comparison then.

dghlsakjg
50% of their tokens on grok code fast were consumed by kilocode users.

Kilocode has been giving away free grok code fast usage.

When the price comes up for 0 I will be curious to see if this trend holds.

lvl155
I stopped using openrouter because it’s getting pretty shady. I rather spend my money and traffic on someone like Vercel.
strangescript
Grok 4 fast is a legit model. Their code models, including supernova still aren't smart enough. Claude and Codex are ahead. Its definitely fast, but who cares if you have to re-prompt it or it hits issues it can't fix.
spoaceman7777
It's free on OpenRouter, but paid on the official xAI API, for the moment.

So, I'd imagine that is inflating the numbers just a bit lol.

xnx
Those stacked bar charts are data visualization malpractice. They would tell a much clearer story (who's #1, what are the trends, when did one overtake another) as regular line charts.
arresin
I am using it more than the disaster that is gpt5
rcarmo
I’m curious as to why, since inside GitHub Copilot GPT-5 has been stellar lately. Are you using it directly? (I assume that the prompting strategy inside Copilot is the reason why it’s so good right now).
arresin
It’s very slow. Extremely marginal improvement over o3. Sometimes falls short (after taking a lot longer). Lower the thinking amount and all marginal improvement evaporates.