GPT-6 Astra on OpenRouter

104

TTopfi about 3 hours ago 48 commentsRead Article on openrouter.ai

ZH version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

79% Positive

Analyzed from 866 words in the discussion.

Discussion (48 Comments)Read Original on HackerNews

simonw•about 2 hours ago

I posted this in the other Astra thread but it's just fallen off the homepage, so...

Pelicans from Astra, plus 5.6 Sol, Terra, Luna for comparison: https://static.simonwillison.net/static/2026/gpt-6-and-5.6-p...

I think this is a genuinely interesting comparison grid. Astra may be more expensive, but if you have a budget of 10 cents for a Pelican Astra low gives you something SO much better than the other models.

Astra uses less tokens overall too, for better results.

Astra transcript here: https://tools.simonwillison.net/markdown-svg-renderer?url=ht...

jsdalton•12 minutes ago

Simon do you have a page somewhere that shows _all_ of the penguins created by various models across time?

You’ve been doing this public service for so long (well, for so long in “AI hype” years anyway) that it’d be fascinating to see the evolution of this artifact across time.

vb-8448•29 minutes ago

I find curios that Astra's pelicans are basically the same (yellow sun top right corner, green bike, same bike shape, same legs style, very similar background) while in other there is more randomness.

pizza234•10 minutes ago

Astra is the only model that correctly depicts occlusion of crank and leg, although interestingly, at max and medium levels (not in between).

thimabi•24 minutes ago

This tracks with what OpenAI has been saying about Astra: that it tends to do things in a certain way and it’s up to you to prompt it to change its style.

BrokenCogs•about 1 hour ago

Interesting that all of the bikes are turquoise colored, except for the medium effort

andai•36 minutes ago

Oh my goodness. I was not prepared for Luna on "none".

Reminded me of https://clocks.brianmoore.com/

tyre•16 minutes ago

Haiku the GOAT

Xunjin•about 1 hour ago

Do you have other ideas of "combinations" for this kind of benchmark?

I'm wondering if this is being trained on by the models today.

r_lee•29 minutes ago

I have a feeling they've been doing that for a while now, even if unintentional, as it's such a well known benchmark

lspears•about 1 hour ago

Luna's price seems off

XCSme•about 2 hours ago

That's some crazy SVG generation:

https://aibenchy.com/compare/openai-gpt-6-astra-high/google-...

It took a while to test it, initially OpenRouter was giving Not Found errors for this model ID.

readams•5 minutes ago

The Astra one looks pretty good except it's standing on the wrong side of the table

satvikpendem•about 1 hour ago

That's quite shocking, at a sufficiently advanced level we can make all non-realistic graphics purely out of SVGs, as they'd have good scaling for things like logos and app icons. I know it was technically and theoretically possible before AI but most people weren't spending hours tweaking SVG HTML. I remember making an SVG dark mode toggle icon and it took days to get it right, I assume it's one shottable now.

kulahan•about 1 hour ago

That photo looks pretty hilariously stupid, so this appears to be more of a first toe dip rather than some indication we can one-shot a previously difficult process.

appplication•29 minutes ago

Sure, it is a bit cartoonish but it’s relatively impressive. I do wonder what you would get if you asked for photorealism

embedding-shape•about 2 hours ago

At the bottom it says "Score 98.58", what measure is used for this score? It's kind of horrible, the perspective is all off (legs of the table makes that very obvious), the mouse/hamster has two mouths, a stub for a right paw, looks like left hand holds a melon on a stick or something, and there are pluses in the background for some reason. Not sure it'd call it "close to perfect" which the score seems to want to indicate.

XCSme•about 1 hour ago

Do you prefer the fable one?

It's more "correct" but looks a lot worse in my opinion:

https://aibenchy.com/compare/openai-gpt-6-astra-high/google-...

kulahan•about 1 hour ago

No, both of them look awful. I genuinely am unsure if this is a meme you're making that's going over my head...?

XCSme•about 1 hour ago

Yeah, that's confusing, the score is for the entire benchmark, not for SVG generation only.

Good point about the mouths, I just noticed, lol

Imo, it's still better than most models, I personally like the stylized perspective.

You can view here all generations for all models: https://aibenchy.com/showcase/

XCSme•about 1 hour ago

I've replaced "Score" there with model ranking, to reduce confusion, thanks for the feedback!

jaesonaras•22 minutes ago

Anyone had success using Astra as a Foundry model via Github Copilot? The error I get is that tooling is not available if reasoning has a value.

kingstnap•about 3 hours ago

Its also available finally to Pro users! Just took 24 hours.

InsideOutSanta•about 3 hours ago

They gave out bankable resets for every day people on pro plans didn't get Astra. Given that, I wish they'd waited a few more days before activating it on my account :-D

paxys•about 2 hours ago

That's a pretty genius internal incentive to move fast.

wincy•about 2 hours ago

They haven’t activated Astra for me yet, I have two resets now. I’ve been using the opportunity to test out how good 5.6 Sol is at computer use asking it to generate stuff in Blender which has been… interesting

Edit: nevermind it JUST gave me a notification to use it!

embedding-shape•about 2 hours ago

> They gave out bankable resets for every day people on pro plans didn't get Astra.

Yeah, when I saw that Tweet I knew the person was saying it because they knew it'll be available within 24h.

vb-8448•33 minutes ago

Played in codex app a couple of hours today: it feels much faster than SOL, even if the TPS is half of it.

algoth1•about 2 hours ago

Just got it. European plus user here. Only codex, no chatgpt

gavinray•about 3 hours ago

I have GPT-6 access in Codex and OpenAI API now

I'm a Business plan user with Cyber verification enabled, FWIW.

embedding-shape•about 2 hours ago

Same just got access literally this minute, Pro user here, no Cyber verification but have passed my ID over to them back in 2024 or something, maybe at the ChatGPT 3 API launch or something?

Has there been anything published about if Astra uses different amount of usage from your subscription plan compared to Sol? Don't recall coming across that in the press releases.

r_lee•about 3 hours ago

is Azure for this actually ZDR?

starik36•about 2 hours ago

What is the actual utility of using this model on Azure? It's twice as expensive, according to the link.

Do Azure offer something that simply hitting the OpenAI endpoint doesn't provide?

hhh•21 minutes ago

It's the same price as regular processing. You get guarantees microsoft give you, which are ones OpenAI won't (or require dedicated spend,) and you can use azure identities for access.

claiir•about 1 hour ago

They’re ZDR and the OAI ones aren’t

paxys•14 minutes ago

OpenAI also has ZDR for enterprise accounts.

itsjustkev•about 1 hour ago

Compared to OpenAI flex? I'm pretty sure that is their batch processing endpoint, which is naturally cheaper.

cute_boi•about 2 hours ago

I got it, but sadly no resets...

vatsachak•about 3 hours ago

Damn I am so hyped

6thbit•about 2 hours ago

Invoking simonw for pelicans pretty please.

drivers99•about 2 hours ago

That's over here: https://news.ycombinator.com/item?id=49570643

Osama0456•about 3 hours ago

is it finally available on openrouter and what about fable 5.1

r_lee•about 3 hours ago

that's literally what the link is for...