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.
Btw, they had 3D pelican-on-the-bicycle easter egg in one of the promo videos: https://youtu.be/bOC3DisEOfg?t=117 so I'm pretty sure that they spent some small amount of resources to train the model to produce good svg version as well. :D
kyorochan 2 hours ago [-]
The 3D version is interesting, because it's more detailed which means more things to get wrong. The mudguards are symmetrical for some reason which you would never see in real life, and there are three brake cables but no brakes!
I also think there's an extra level that I would hope an AI would nail which maybe an amateur artist would also fail at, such as thinking about what position a pelican would actually ride a bike in (maybe angling the beak down for aerodynamics etc.), but we are far away from this.
theturtletalks 6 hours ago [-]
This is one of those benchmarks I don’t mind if they benchmax because it would mean models are actually good at creating svg graphics.
theturtletalks 6 hours ago [-]
Look at how well it made this Xbox controller SVG:
Do you know what reasoning level this was generated at?
sejje 2 hours ago [-]
It's immaculate, wow
stymaar 8 hours ago [-]
When you see how good the output of the Luna model without reasoning is compared to SotA just a year and a half ago, it's pretty clear that it's been trained on explicitly.
maleldil 7 hours ago [-]
I don't see how this is proof, and not just that the model got the better. You're comparing models a year and a half apart; this is a lifetime in LLM development.
stymaar 37 minutes ago [-]
It's a lifetime on things that are explicitly being trained on! But small models like Luna didn't magically become more powerful than SotA models on stuff that they weren't explicitly trained on with a dedicated RL-pipeline.
brookst 5 hours ago [-]
Yeah, suggestive but hardly proof
WarmWash 3 hours ago [-]
Many people still believe that LLMs can only reproduce what is in their training set.
stymaar 34 minutes ago [-]
That'd be too restrictive, but to get improvement in a particular domain you definitely need to train specifically for it. Just cramming more random internet text in a bigger model has stopped being a effective way of scaling since at least mid 2023.
threatripper 14 hours ago [-]
It seems to start understanding how bicycles work. Look at the front fork. There are reasons why it's shaped the way it is in real bicycles. If you do physical simulations in 3D with reinforcement learning you will start understanding that most of the arrangements that the other agents use just won't work.
epihelix 13 hours ago [-]
Yes, the curve of the front fork on the max pelican was what I noticed also. It's impressive (if not an accident), and a remarkably accurate bike overall. The pelican just needs to raise their seat a little.
steve-atx-7600 16 hours ago [-]
You would not expect the developers of the model to optimize for a well known benchmark?
Did even better from the front. What's surprising is that it used the exact same colors as the simonw example, despite my prompt only being
> Generate an SVG of a ring-tailed lemur riding an electric scooter. Front view
GPT-6 Astra Extra High
pilaf 11 hours ago [-]
Interesting how the background is almost identical to two of the Astra pelicans'.
8 hours ago [-]
benatkin 12 hours ago [-]
Hmm, the face makes it not work as a one shot artifact.
CamperBob2 13 hours ago [-]
If you want to see something brutal, ask for a zebra riding a scooter. I have yet to see any models do a credible job at that.
ulrikrasmussen 9 hours ago [-]
I remember that early image models couldn't generate a cyclops no matter how you prompted it, it would at best put a third eye in the forehead.
pointitkememe 9 hours ago [-]
[flagged]
boxed 6 hours ago [-]
The lemur is worse though. The hands don't follow physics for example. You claim this would be easier, but then the model is worse.
y1n0 16 hours ago [-]
I would expect it happens more organically where people’s discussion of the benchmark and posted results find their way into the training data, like anything else on the internet.
Kranar 15 hours ago [-]
What is this supposed to mean exactly? Do you think there are developers at OpenAI or Anthropic whose job is to train these state of the art models to draw pelicans riding bicycles? Like how exactly do you expect them to be doing that anyways? Hiring graphic artists to create SVGs of bike riding pelicans and feeding thousands of them into the model's training set?
mudkipdev 15 hours ago [-]
Generate two images, get a vision model to judge, then RL reward the better one. And yes, OpenAI employees on twitter bragged about the model's SVG capabilities. So there are clearly people working there who care about it.
awakeasleep 15 hours ago [-]
You gotta look up how RLHF works before you ask a demanding question like this.
WarmWash 3 hours ago [-]
Right, but that's not the crazy part. The crazy part is thinking they do it all specifically for pelicans on bikes.
If that was the case, the models would have been producing near perfect outputs for it a year ago.
Instead they are just training on general SVG generation, which in no way should be viewed as "benchmaxxing".
dgellow 10 hours ago [-]
> Do you think there are developers at OpenAI or Anthropic whose job is to train these state of the art models to draw pelicans riding bicycles?
Yes
jenniferhooley 4 hours ago [-]
Do you really think there aren't data annotator services specifically training for SVG drawing? And that those annotators don't have a rich set of frequently requested icons/graphics/etc. that they review and train on?
I don't think it's a great rebuttal, quite the opposite actually: it's the same prompt with the most obvioy tweak you can imagine and the results are all the same. That definitely looks like it's been something the models have been trained on, and not some emergent capability (and if you take into account how nonthinking Luna compares to the SotA models from a year an half ago: https://simonwillison.net/tags/pelican-riding-a-bicycle/?pag... it becomes even more obvious)
boxed 6 hours ago [-]
How about you come up with something yourself instead of just moving the goalpost?
stymaar 33 minutes ago [-]
No goalpost was harmed in the above comment.
mi_lk 15 hours ago [-]
It stopped being a valuable benchmark proxy quite a few model versions ago. Simon knows it, so is everyone who’s serious about it
Treat it like a bit as is
benatkin 14 hours ago [-]
It's actually not just valuable, but infinitely valuable. Because it's imaginary, there is no way to do it perfectly, and thus the possibilities are endless, and it tests out both the formulation and execution of ideas.
epiccoleman 5 hours ago [-]
Starting my SVG of a pelican on a bicycle as a service startup today, invest now for infinite returns!
justinbaker84 8 hours ago [-]
Your comparison grid is one of the most useful comparison grids I have ever seen in terms of measuring AI.
It feels silly to say that about making a pelican image but it really shows the difference in output and cost in an easy to understand way.
jsdalton 17 hours 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.
I used Light mode and it used up all my limits for the day and had to continue the following day.
bahmboo 14 hours ago [-]
Would be great to spend some money (other people's money) on paying some illustrators and artists to do the same for comparison. It could be straight images converted to SVG or direct vector graphics.
WarmWash 3 hours ago [-]
Technically you would pay programmers to write SVG code with no visual feedback if you want a straight 1:1 comparison.
Gander5739 11 hours ago [-]
Doesn't that somewhat miss the point? The models can't see and check their work, for instance.
bahmboo 10 hours ago [-]
I'm not clear what you are saying. I am curious about what humans can do in the same context. It's becoming a standard I think for some tasks. E.g. how does a Gen AI stack up against a human in quality and "cost". Perhaps I'm missing what you are asking.
spockz 7 hours ago [-]
They can. Ask them to generate SVG , call a renderer and let them inspect the bitmap/png. They can learn about it.
Gander5739 4 hours ago [-]
They can, but for this specifc test, they don't. It's a oneshot with no feedback.
vb-8448 17 hours 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.
thimabi 17 hours 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.
pizza234 17 hours ago [-]
Astra is the only model that correctly depicts occlusion of crank and leg, although interestingly, at max and medium levels (not in between).
vessenes 16 hours ago [-]
Looked to me like it missed the chain though.
TiredOfLife 6 hours ago [-]
Kimi k3 and Fable max also
petilon 16 hours ago [-]
Astra pelican looks amazing: it looks like it was made by a professional artist. All the others look like they were made by kindergartners.
andai 18 hours ago [-]
Oh my goodness. I was not prepared for Luna on "none".
It's so meme-worthy next to the astra-max for any situation of "What you were promised" vs "What you received".
tyre 17 hours ago [-]
Haiku the GOAT
jeffybefffy519 11 hours ago [-]
Shouldnt you give the AI a different task each time? otherwise the model companies just optimise for this benchmark because its in their best interest to...
mkagenius 12 hours ago [-]
Do you ever randomize on a particular model - like try and get 3 outputs and pick one at random?
Coz who knows if astra low will produce max like output if tried once more.
mkl 4 hours ago [-]
Why do Sol and Terra use 26 input tokens when the others use 16?
simonw 3 hours ago [-]
I don't know and I'm really
Interested in the answer.
I heard a rumor that Luna is a slightly different architecture from Sol and Terra, which makes me wonder if Luna and Astra might be more related to each other than to Sol and Terra.
Bit of a big leap to make from a token count though!
Interesting that all of the bikes are turquoise colored, except for the medium effort
alastairr 12 hours ago [-]
It's mildly interesting that the bikes always seem to be front wheel facing the right.
simonw 4 hours ago [-]
Most images of bicycles on the web are arranged that way because the drivetrain is always on the right of the bicycle and you want that displayed prominently.
alastairr 4 hours ago [-]
I don't know how I didn't think of that! Makes sense.
18 hours ago [-]
18 hours ago [-]
Xunjin 18 hours 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 17 hours 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 18 hours ago [-]
Luna's price seems off
droidjj 17 hours ago [-]
The price is probably coming from when Luna was first released. OpenAI slashed the price by 80% at the end of July.
simonw 16 hours ago [-]
Yes! Good catch, thanks - I'll fix that.
simonw 16 hours ago [-]
I had the prices wrong on Sol and Terra as well - they've all had price drops:
The improved front fork design mentioned by Threatripper is about the only thing Astra is doing better, IMO.
scotty79 7 hours ago [-]
They really can't decide which way pelican's knees should bend, do they?
EugeneOZ 7 hours ago [-]
I love Astra pelicans! Awesome results!
fHr 17 hours ago [-]
Luna is my go to daily model it's great value
tuo-lei 16 hours ago [-]
Me toooo, for all my personal projects I need to pay for the tokens~
At workplace I use sol because I don't need to pay
ghthor 17 hours ago [-]
Mine as well, it’s fast and keeps me in flow; and cheap!
poopiokaka 12 hours ago [-]
[dead]
man4 16 hours ago [-]
[dead]
jedjjfjf 15 hours ago [-]
[dead]
leoqa 19 hours ago [-]
[flagged]
samuelknight 19 hours ago [-]
How are we supposed to know if Astra is frontier without the pelican?
satvikpendem 18 hours ago [-]
It's simonw. It's interesting to see their pelican benchmark, another comment by a different author elsewhere here shows some very good SVG generation too.
ComplexSystems 19 hours ago [-]
It's absolutely related.
StopTheCringe 18 hours ago [-]
[flagged]
bnorton 16 hours ago [-]
You’re closer to this than I am but do you find it odd that helmets are almost never included? Biking is almost always accompanied by helmets
maxlapdev 16 hours ago [-]
But pelicans are almost never accompanied by helmets, so it cancels out.
sumedh 16 hours ago [-]
> Biking is almost always accompanied by helmets
Isnt Netherlands the leader in bike riders and they dont wear helmets.
neutronicus 16 hours ago [-]
At least one reasoning trace I saw considered a helmet and discarded the idea because it was worried about obscuring some detail
kzrdude 3 minutes ago [-]
The names, I thought they were going to keep Sol, Terra, Luna for a while (while increasing versions). Are names like Sol and Astra really burned as one-offs? I think that's a waste of a good model name. Hope they keep them going with updates, as nicknames for the various model sizes on offer.
frenchtoast8 3 hours ago [-]
I signed up for OpenRouter, loaded it up with $25, and after running a test prompt immediately had my account suspended. There’s no way to talk to support, emails go nowhere, and their Discord is swarmed with people who also are getting no responses to anything.
I would recommend staying away from OpenRouter. No matter how good the service is, if anything does go wrong, you have no recourse and you lose every credit in your account. Ironically some of the few responses I actually saw in the Discord were doubling down on their “no refunds no matter what” policy.
dominick-cc 27 minutes ago [-]
That's crazy. Thanks for the heads up.
tocariimaa 42 minutes ago [-]
Are there alternatives that don't slurp in the remaining unused credits every new month? OpenRouter credits carry to the next month up to a year so that's why I use it.
43 minutes ago [-]
predkambrij 1 hours ago [-]
I did get a response when sending to support@openrouter.ai about a year ago (complaining about some information claims), not about my account.
enraged_camel 27 minutes ago [-]
Yeah their support is non-existent. It's actually mind-blowing that so many people use it.
43 minutes ago [-]
miyuru 3 hours ago [-]
take screenshots of the responses and do a chargeback.
Gecko4072 1 hours ago [-]
They were just bought for $7B and rely on Discord?
bellowsgulch 17 minutes ago [-]
God, that's a step up from AI support, which is so sad to type out loud.
bellowsgulch 16 minutes ago [-]
Thanks, might move our corporate accounts over to proxy billing now.
jjcm 14 hours ago [-]
It's ability to handle non-90 degree cutouts and shapes for web dev is one of the best I've seen. The vision model on this is VERY capable.
Note the flowing svg lines, and how accurately it recreated them. Here's Opus 5 for comparison - you can really see how while Astra really recreated the flow that was in the original design, opus only got the general vibe: https://image.non.io/dfe13de0-4487-431f-8b69-544ff3030dac.we...
One thing I will say is you are paying for quality. That site build cost $24 - extremely non-trivial for a simple frontend.
copperx 12 hours ago [-]
> That site build cost $24 - extremely non-trivial for a simple frontend.
I would say that $24 is trivial IF that's the final design. The truth is that the cost doesn't leave much room for error or experimentation.
jermaustin1 45 minutes ago [-]
A bespoke design like that a year ago would have cost $200-2000+ between design and development. Hell, it probably still does unless the person wanting the design is already a developer who knows how to prompt.
Everything costs more now than it did a year ago... except for THIS, and we are still complaining that a 90-99% reduction in cost is STILL too expensive. And a 50-75% reduction in time is STILL too long.
We used to have to wait for weeks for a design like that when I worked at a consultancy, and that is a week of salary. For the design, then it got handed off to a front end developer to slice it and get built so the back end developer can hook it up to a CRM. We are talking a month turn around with design, revisions, development, testing, and bug fixing.
It can now be done in a couple of hours for less than a single hour's cost. If it were 10x slower and 10x more expensive, it would STILL be "good deal".
kolinko 7 hours ago [-]
Wdym no room for error or experimation? Changes are even cheaper, and in my experience they are faster and way cheaper with models than with designers.
paxys 2 hours ago [-]
Plus you can offload a lot of work to a cheaper model
JumpCrisscross 9 hours ago [-]
> truth is that the cost doesn't leave much room for error or experimentation
Compared to what?
risyachka 3 hours ago [-]
>> The truth is that the cost doesn't leave much room for error or experimentation
Yeah if you are solo developer without budget.
For any business this is nothing, the ROI is massive.
mydreamof 11 hours ago [-]
I don't get it. For me it seems Opus was more accurate in terms of for example this small building in the right down corner
CapsAdmin 10 hours ago [-]
I would say opus was in some ways more accurate, but missed the higher level curvature feel of the site that astra picked up on.
It sounds completely trivial and likely I'm wrong here, but could it be that opus saw the reference image squished? That might explain the sharper horizontal curvature
esikich 11 hours ago [-]
They look pretty similar to me, I'm not sure what you're seeing that is so much better.
w4yai 11 hours ago [-]
Also the curves and background lines that separate the right image from the left content
It took a while to test it, initially OpenRouter was giving Not Found errors for this model ID.
satvikpendem 18 hours 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.
dprkh 16 hours ago [-]
I thought all the designers have been using vector graphics for a long time now.
embedding-shape 8 hours ago [-]
"Designer" is a very broad term and can mean very different things to different people, not everyone is doing stuff that can be represented nicely by vectors.
mceachen 15 hours ago [-]
Aldus Freehand 1.0 was released in 1988. Adobe Illustrator was first released in 1987.
kulahan 18 hours 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 17 hours ago [-]
Sure, it is a bit cartoonish but it’s relatively impressive. I do wonder what you would get if you asked for photorealism
redox99 14 hours ago [-]
The problem is not photorealism. The SVG is outright dumb, its on the wrong side of the table, the table has fucked up geometry (its tilted) and many more minor flaws.
XCSme 10 hours ago [-]
That's true, if it really "knows" stuff, a bit weird to have basic flaws like 2 mouths, and sitting on the side...
embedding-shape 19 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 18 hours ago [-]
Do you prefer the fable one?
It's more "correct" but looks a lot worse in my opinion:
And not to mention, the hamster is standing at the wrong end of the table.
sehugg 8 hours ago [-]
And also the hamster has two mouths
embedding-shape 5 hours ago [-]
I think it might be standing at the wrong edge of the table too, worth adding.
embedding-shape 8 hours ago [-]
Incredible, I've played table-tennis since I was like 14, and I didn't notice that egregious error yet I noticed all the other small ones! Thanks for pointing that out, should have been very obvious.
XCSme 18 hours 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.
I've replaced "Score" there with model ranking, to reduce confusion, thanks for the feedback!
embedding-shape 8 hours ago [-]
Now I'm wondering why it's ranked #4 instead, not sure this reduced confusion :P
What panel of judges are you using for scoring/ranking this? Seems subjective enough to not be able to be ranked/scored at all
XCSme 8 hours ago [-]
Yeah, ranking is for entire model, not only SVG generation. Maybe I remove it entirely and add generation date instead.
I was thinking to manually grade/rank the SVGs, but I decided against it, as it is indeed subjective.
I was thinking it could have at least a simple objective check (hamster doesn't have extra or missing parts, table has 2 sides, and net is in the middle, etc.).
readams 17 hours ago [-]
The Astra one looks pretty good except it's standing on the wrong side of the table
viccis 11 hours ago [-]
>AGI
>Playing ping pong from the side of the table
I think marketing might be getting a bit absurd at this point
mawadev 9 hours ago [-]
I must live in a different world or it feels like I'm reading LLM generated comments, but who exactly is falling for this marketing?
I even keep seeing obvious stealth marketing like this: "<topic> and how do I use it with <product> in <product>"
jubilanti 3 hours ago [-]
> who exactly is falling for this marketing?
The entire mainstream media and political establishment, and every normie I meet is convinced Skynet is already upon us
ryanschaefer 1 hours ago [-]
For me it’s the two mouths
18 hours ago [-]
5 hours ago [-]
MisterMunchkin 12 hours ago [-]
$10/$50 is incredibly expensive compared to Chinese models which are cents.
I think they’re really going to struggle selling these models long-term. My company is already massively cutting down on access because they’ve realised most people don’t actually produce any value using it. All the tokenmaxers have ruined it for the rest of us now that accounting have seen the costs.
kolinko 6 hours ago [-]
It's like saying you're not paying for senior level engineers because you can get juniors for quarter the price per hour.
bigyabai 6 minutes ago [-]
If the assignment isn't a 600,000 SLOC greenfield superproject, that's a perfectly acceptable alternative.
sschueller 5 hours ago [-]
Not like companies to fire senior engineers and then hiring two juniors to replace them to optimize expenses... /s
kolinko 4 hours ago [-]
An official motto of a president of one of the biggest software companies in Poland (Comarch) was "you can replace any experienced engineer with a finite amount of sutdents... for half of the cost".
It must be super interesting working there rn :D
wookmaster 1 hours ago [-]
My company literally mandated tokenmaxxing while all the engineers told them this was a bad idea.
gentlewater 10 hours ago [-]
Not really comparable IMO. Astra and Fable are not the every day workhorse you reach for to do basic tasks (unless your company has fuck you-money), they’re the tool you break out when you need the absolute strongest performance. There are plenty of tasks where finding and fixing one or two extra edge cases saves the business a lot of money, even if the cost is high. The best example would be scanning for vulnerabilities, if these models weren’t kneecapped in that area.
ghosty141 9 hours ago [-]
We have ChatGPT Pro at work and I usually use Terra medium/high and only bring out Sol High when the big or feature actually requires "thinking"/complex behavior. This has worked pretty well for me and it's very token efficient
KptMarchewa 11 hours ago [-]
the only thing that matters is cost per task. Astra seems to be massively efficient.
simianwords 11 hours ago [-]
No it doesn't. Any source?
saidnooneever 5 hours ago [-]
in the middel of a coding session with 5.6 sol. astra popped up, swapped, asked review, it fixed a few really critical bugs immediately. pretty nice. one around some resource lifetimes in a rendering pipeline which would have been a nightmare to find manually.
almost had the feelin it was watching its little brother fail and had to 'step in' for a moment :').
time to go play outside...
kingstnap 20 hours ago [-]
Its also available finally to Pro users! Just took 24 hours.
InsideOutSanta 19 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
embedding-shape 19 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.
wincy 3 hours ago [-]
I must have been one of the last ones to get it because I managed to snag two bankable resets. Already reset once after having it clear up geometry in Blender, but it did a fantastic job!
wincy 19 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!
paxys 19 hours ago [-]
That's a pretty genius internal incentive to move fast.
killerstorm 4 hours ago [-]
I tried it with some humanities questions and with the default OR system prompt (no prompt?) it seems to be rather mild - lacking usual AI mannerisms. Kinda cool.
sumedh 16 hours ago [-]
Just got access to it on Plus plan in Australia. 2 Banked resets as well.
ebiester 5 hours ago [-]
For those on plus, are you seeing astra limited to medium? Considering the rate limits that probably makes sense, but I'm wondering what different groups have access to.
vb-8448 17 hours ago [-]
Played in codex app a couple of hours today: it feels much faster than SOL, even if the TPS is half of it.
WASDx 3 hours ago [-]
Likely because it uses fewer thinking tokens (that you don't see anyways).
friendlypenguin 12 hours ago [-]
I was really hoping for Astra to be less expensive then Opus...
redox99 11 hours ago [-]
It is (uses way less tokens)
simianwords 11 hours ago [-]
No it isn't cheaper, any source for task vs price comparison to Sol?
This is the second comment I see where you write "no it isn't", without providing a source for your statement. Then you follow it by asking for a source. So is there a source you can provide to back up your statement?
dgellow 10 hours ago [-]
It’s supposed to work the other way, if you make a positive claim that it is cheaper, where is your proof?
d2p 9 hours ago [-]
Odd that the tool call failure rate is so high (5%) for the OpenAI provider than Azure (0.2-0.5%).
algoth1 19 hours ago [-]
Just got it. European plus user here. Only codex, no chatgpt
christophilus 3 hours ago [-]
Tangentially related, but Astra generated some of the worst Odin code I’ve ever seen. Turns out AGI is indistinguishable from an Oracle subcontractor who hates tech and hates his job.
1saadcodes 10 hours ago [-]
The higher price seems less important if it actually gets the job done with fewer tokens. I'm still very worried that this will end up coming back to bite us, by becoming more expensive once they inevitably nerf it. Every major model provider does that now after all
NSUserDefaults 5 hours ago [-]
I misread the title as GPTA-6, wondering what sort of crazy crossover was happening.
azinman2 2 hours ago [-]
I’m confused. I thought it was being only rolled out to select partners for now?
swe_dima 5 hours ago [-]
According to the metrics the "fast" mode is not any faster...
upcoming-sesame 10 hours ago [-]
Any tips on using Astra as orchestrator with Luna workers efficiently in codex?
logged4upvoting 9 hours ago [-]
(This applies to Sol but probably works for Astra too)
I've created with Sol a skill called Low Quota Mode that intends to reduce the use of tokens usages by the frontier (intelligent model) and delegate the use of bulk reading of docs/code and implementation to a sub-agent running Luna Max. Sol is asked to supervise, read the diffs and approves the commit/pr.
The skill might need some iterations while you use it, for example at the end of a rough session you can ask Sol how did it went, which were the points of conflict with Luna and try to iron them little by little by editing the skill.
Also in difficult tasks, ask to babysit the sub-agent model, I've seen it makes more effort into communication between frontier and sub-agent to guide the task with more care.
So far it has reduced my tokens usage a lot (have not quantified but the quota lasts more).
DrProtic 6 hours ago [-]
Could you shoot us the github gist?
jaesonaras 17 hours 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.
r_lee 20 hours ago [-]
is Azure for this actually ZDR?
jiggawatts 11 hours ago [-]
It cracks me up that you have to ask in a public forum because the vendors purposefully obscure this critical information.
The only reason most of my customers would use Azure Foundry instead of OpenAI directly is the ZDR assurance but it is so incredibly difficult to extract out of their model menu.
There is no trivial way to block non-ZDR models either so every customer has to “vet” and individually approve models.
If anyone from Microsoft is reading this: get your act together! You’re failing at the one thing people might want to pay you to do!
r_lee 8 hours ago [-]
from my understanding, ZDR for this is for vetted customers only + their whole "privacy preserving abuse monitoring" or whatever is active
but again, seems like there's no word from Azure if this applies to them.
very confusing.
19 hours ago [-]
gavinray 19 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 19 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.
forrestthewoods 10 hours ago [-]
Threw $10 at this to help me prepare for my league’s fantasy auction this weekend. It spend $3.50 and then said “this action would cause you to go above your spending limit”.
Then I threw $100 for a Codex Max sub and it included Astra and it did it for me.
Sure seems like Astra is expensive AF.
starik36 19 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 17 hours 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 18 hours ago [-]
They’re ZDR and the OAI ones aren’t
nibbleyou 13 hours ago [-]
Does anyone know if it is not ZDR on the codex app usage too. I am assuming it isn't
17 hours ago [-]
olalonde 17 hours ago [-]
WTHIT?
spdustin 16 hours ago [-]
ZDR = Zero Data Retention — they don't store your inputs/outputs.
viccis 11 hours ago [-]
AKA extortion
DaSHacka 1 hours ago [-]
More like the business tax
Peanuts99 10 hours ago [-]
If you've got access to an Azure subscription and you don't pay the bill personally.
itsjustkev 18 hours ago [-]
Compared to OpenAI flex? I'm pretty sure that is their batch processing endpoint, which is naturally cheaper.
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...
I also think there's an extra level that I would hope an AI would nail which maybe an amateur artist would also fail at, such as thinking about what position a pelican would actually ride a bike in (maybe angling the beak down for aerodynamics etc.), but we are far away from this.
https://www.svgviewer.dev/s/i8t1VXzQ
Quote from the thinking trace:
> I’m thinking about how a helmet would obscure lemur ears, but using an electric scooter helmet seems responsible.
It's pretty solid - face is a little wonky but excellent tail and scooter.
Did even better from the front. What's surprising is that it used the exact same colors as the simonw example, despite my prompt only being
> Generate an SVG of a ring-tailed lemur riding an electric scooter. Front view
GPT-6 Astra Extra High
If that was the case, the models would have been producing near perfect outputs for it a year ago.
Instead they are just training on general SVG generation, which in no way should be viewed as "benchmaxxing".
Yes
I'd be shocked if they didn't myself.
Treat it like a bit as is
It feels silly to say that about making a pelican image but it really shows the difference in output and cost in an easy to understand way.
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.
I'm running out of excuses not to build a proper comparison site though. Maybe I'll have Astra do rhat.
I used Light mode and it used up all my limits for the day and had to continue the following day.
Reminded me of https://clocks.brianmoore.com/
Coz who knows if astra low will produce max like output if tried once more.
I heard a rumor that Luna is a slightly different architecture from Sol and Terra, which makes me wonder if Luna and Astra might be more related to each other than to Sol and Terra.
Bit of a big leap to make from a token count though!
I just checked the tiktoken library and couldn't see any changes relating to Luna: https://github.com/openai/tiktoken
I'm wondering if this is being trained on by the models today.
https://openai.com/index/advancing-the-price-performance-fro...
Sol discount is until November 21, 2026 according to https://developers.openai.com/api/docs/changelog
Apparently the crowd agrees because they keep upvoting these.
The improved front fork design mentioned by Threatripper is about the only thing Astra is doing better, IMO.
Isnt Netherlands the leader in bike riders and they dont wear helmets.
I would recommend staying away from OpenRouter. No matter how good the service is, if anything does go wrong, you have no recourse and you lose every credit in your account. Ironically some of the few responses I actually saw in the Discord were doubling down on their “no refunds no matter what” policy.
Here's an image design source of truth: https://image.non.io/78f4cd8b-2560-4643-9a51-96a89171f994.we...
And here's the page it build from it: https://image.non.io/e7d3a9e5-f9df-4fd8-b79f-1f90280f978f.we...
Note the flowing svg lines, and how accurately it recreated them. Here's Opus 5 for comparison - you can really see how while Astra really recreated the flow that was in the original design, opus only got the general vibe: https://image.non.io/dfe13de0-4487-431f-8b69-544ff3030dac.we...
One thing I will say is you are paying for quality. That site build cost $24 - extremely non-trivial for a simple frontend.
I would say that $24 is trivial IF that's the final design. The truth is that the cost doesn't leave much room for error or experimentation.
Everything costs more now than it did a year ago... except for THIS, and we are still complaining that a 90-99% reduction in cost is STILL too expensive. And a 50-75% reduction in time is STILL too long.
We used to have to wait for weeks for a design like that when I worked at a consultancy, and that is a week of salary. For the design, then it got handed off to a front end developer to slice it and get built so the back end developer can hook it up to a CRM. We are talking a month turn around with design, revisions, development, testing, and bug fixing.
It can now be done in a couple of hours for less than a single hour's cost. If it were 10x slower and 10x more expensive, it would STILL be "good deal".
Compared to what?
Yeah if you are solo developer without budget.
For any business this is nothing, the ROI is massive.
It sounds completely trivial and likely I'm wrong here, but could it be that opus saw the reference image squished? That might explain the sharper horizontal curvature
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.
It's more "correct" but looks a lot worse in my opinion:
https://aibenchy.com/compare/openai-gpt-6-astra-high/google-...
https://aibenchy.com/showcase/?page=2#showcase=67fc6d6c8e4c3...
https://aibenchy.com/showcase/?page=3#showcase=c215b5c915da6...
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/
What panel of judges are you using for scoring/ranking this? Seems subjective enough to not be able to be ranked/scored at all
I was thinking to manually grade/rank the SVGs, but I decided against it, as it is indeed subjective.
I was thinking it could have at least a simple objective check (hamster doesn't have extra or missing parts, table has 2 sides, and net is in the middle, etc.).
>Playing ping pong from the side of the table
I think marketing might be getting a bit absurd at this point
I even keep seeing obvious stealth marketing like this: "<topic> and how do I use it with <product> in <product>"
The entire mainstream media and political establishment, and every normie I meet is convinced Skynet is already upon us
I think they’re really going to struggle selling these models long-term. My company is already massively cutting down on access because they’ve realised most people don’t actually produce any value using it. All the tokenmaxers have ruined it for the rest of us now that accounting have seen the costs.
It must be super interesting working there rn :D
almost had the feelin it was watching its little brother fail and had to 'step in' for a moment :').
time to go play outside...
Yeah, when I saw that Tweet I knew the person was saying it because they knew it'll be available within 24h.
Edit: nevermind it JUST gave me a notification to use it!
Edit:
GPT-6 Astra (low): 57 Intelligence Index, $7.70/M tokens
GPT-5.6 Sol (high): 57 Intelligence Index, $3.08/M tokens
So for the same measured intelligence, Sol costs only 40% as much — i.e. ~60% cheaper, while Astra is ~2.5× more expensive.
Why is the burden of proof on me tho!?
astra high is also 3x cheaper than opus max at basically the same intelligence.
astra high is also about as expensive as sol max while being more intelligent.
astra medium is cheaper than sol max while also being cheaper and roughly same intelligence.
im going to replace my sol usage with astra high/medium i think
caveat: benchmarks are really fuzzy with llms
https://artificialanalysis.ai/models/releases/gpt-6-astra
I've created with Sol a skill called Low Quota Mode that intends to reduce the use of tokens usages by the frontier (intelligent model) and delegate the use of bulk reading of docs/code and implementation to a sub-agent running Luna Max. Sol is asked to supervise, read the diffs and approves the commit/pr.
The skill might need some iterations while you use it, for example at the end of a rough session you can ask Sol how did it went, which were the points of conflict with Luna and try to iron them little by little by editing the skill.
Also in difficult tasks, ask to babysit the sub-agent model, I've seen it makes more effort into communication between frontier and sub-agent to guide the task with more care.
So far it has reduced my tokens usage a lot (have not quantified but the quota lasts more).
The only reason most of my customers would use Azure Foundry instead of OpenAI directly is the ZDR assurance but it is so incredibly difficult to extract out of their model menu.
There is no trivial way to block non-ZDR models either so every customer has to “vet” and individually approve models.
If anyone from Microsoft is reading this: get your act together! You’re failing at the one thing people might want to pay you to do!
but again, seems like there's no word from Azure if this applies to them.
very confusing.
I'm a Business plan user with Cyber verification enabled, FWIW.
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.
Then I threw $100 for a Codex Max sub and it included Astra and it did it for me.
Sure seems like Astra is expensive AF.
Do Azure offer something that simply hitting the OpenAI endpoint doesn't provide?