Running the same website-build prompt through twelve model-and-effort combinations shows a model's top effort tier rarely produces the best result, and that price, effort level, and quality move mostly independently of each other.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You build with Claude or a similar model regularly and want real cost numbers instead of a marketing claim about a new release.
You're deciding whether to default to a model's highest effort setting or save money on a lower tier.
You want to see actual dollar costs for a non-trivial multi-step AI build, not a token-count estimate.
SKIP IF…
You already have a fixed model/effort workflow and don't switch based on pricing.
You want implementation-level detail on how prompt caching works under the hood; this stays at the concept level.
TL;DR
The full version, fast.
Testing four AI models (Fable 5.1, Fable 5, Opus 5, and Codex Sol) at Low, High, and Max effort against one identical prompt, an animated SpaceX landing page, produces twelve blind-scored builds. The highest-scoring output, Fable 5.1 at High effort, was also one of the cheapest at $8.78, while the priciest run, Fable 5 at Max effort, cost $24.01 for a middling 6/10 result. Effort level correlates loosely with both price and quality: several Low-tier builds outscored Max-tier ones, and the newest model's own Low tier landed near the bottom. The takeaway is that defaulting to a model's maximum effort setting is rarely worth the extra spend for everyday generation work.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Cold open: Brock states the test, the same prompt across every model to see whether Fable 5.1's cheaper caching actually lowers real build cost.
00:31 – 01:12
02 · The scorecard: 4 models, 3 effort levels
Introduces the blank scorecard: four models (Fable 5.1, Fable 5, Opus 5, Codex Sol) each run at Low, High, and Max effort, to be scored on look, time, and cost.
01:12 – 02:28
03 · Why people say it's 75% cheaper (caching explained)
Explains prompt caching with a bookmark analogy: cached tokens cost $0.25/M on Fable 5.1 versus $1/M on Fable 5, a 75% cut in the cached rate specifically, not the sticker price of every token.
02:28 – 04:09
04 · Connecting the Higgsfield MCP to Claude
Walks through adding Higgsfield as a custom MCP connector inside Claude's Customize > Connectors panel so Claude can call it directly.
04:09 – 05:53
05 · Generating the Falcon 9 video clips
Uses Opus 5, cheaper for a non-coding asset call, with the Higgsfield MCP and its Seedance 2.5 model to generate five Falcon 9 video clips for the site's footage.
05:53 – 07:00
06 · The one prompt every model gets
Locks in the single test prompt: build an animated SpaceX landing page from the five clips, explicitly skipping his own animated-website skill so every model builds from scratch.
07:00 – 08:58
07 · Blind test begins: rating the websites
First two blind reveals: Opus 5 Max scores 6/10 and costs $10.70; Opus 5 High scores 5/10 and costs about $11.
08:58 – 12:55
08 · How to check your real cost with /usage
Shows the Claude /usage command for real per-session cost, then reveals Fable 5 Max (6/10, $24.01) and Codex Sol Low (7/10, cost untracked).
12:55 – 14:59
09 · My favorite design so far
Fable 5.1 High reveals as the best-looking build yet, 8/10, at one of the lowest costs seen, $8.78; a 4/10 build (later identified as Codex Sol Max) and Codex Sol High (6/10) follow.
14:59 – 18:12
10 · The most creative animation
Fable 5.1 Max's landing-shake effect scores 7/10 for $10.67; Opus 5 Low bottoms out at 2/10 for $6.58; Fable 5 High, Fable 5.1 Low, and the closing Fable 5 Low build round out all twelve reveals.
18:12 – 19:39
11 · Final scorecard: looks
Full 12-build ranking by look: Fable 5.1 High tops it at 8/10, Fable 5 Low and Fable 5.1 Max tie for second at 7/10, Opus 5 Low sits last at 2/10.
19:39 – 20:28
12 · Final scorecard: cost
Full 12-build ranking by cost: Fable 5 High is cheapest at $5.78, Fable 5 Max is priciest at $24.01, with little correlation to the look ranking.
20:28 – 21:43
13 · Is Fable 5.1 max worth it?
Closing take: running a model's Max effort tier by default is overkill for most everyday tasks, and Brock admits to genuine fatigue with the pace of new model releases.
Atomic Insights
Lines worth screenshotting.
Prompt caching on the newest Claude tier costs $0.25 per million tokens, down from $1 per million on the prior model and $10 per million for anything not cached.
The single best-scoring website in a 12-way blind test also came in as one of the three cheapest builds, at $8.78.
The most expensive build in the test, at $24.01, scored a middling 6 out of 10, tying with three cheaper alternatives.
A model's Low effort tier and another model's High effort tier can land within one point of each other on quality, despite a large price gap.
One Max-effort build took 27 minutes to generate, nearly 13 times longer than the fastest build in the same test at just over 2 minutes.
The newest model's own Low effort tier ranked near the bottom of the field, below three different High and Max tier runs from other models.
An MCP connector lets a chat interface call outside tools, like a video generation service, directly inside the conversation instead of requiring a separate app.
Using a cheaper model for asset generation, and saving the expensive model for the actual build, is one way to control spend without touching final output quality.
Only one vendor's chat interface exposed a built-in per-session cost command in this test, which made an apples-to-apples price comparison across providers impossible.
Blind-scoring outputs before revealing which model made them removes the bias of judging a result by brand reputation instead of what's actually on screen.
Takeaway
The max-effort setting rarely buys you what you think it does.
WHAT TO LEARN
Across twelve identical builds, price, effort level, and output quality moved almost independently of each other, so defaulting to a model's most expensive tier is usually not worth the extra spend.
03Why people say it's 75% cheaper (caching explained)
Prompt caching charges $0.25 per million tokens on the newest tier versus $1 per million on the prior model and $10 per million for anything not cached, so a 'cheaper model' claim usually refers to that cached rate, not every token.
05Generating the Falcon 9 video clips
An MCP connector lets a chat interface call outside tools, like a video generator, directly inside the conversation instead of requiring a separate app.
Using a cheaper model for asset generation, and saving the expensive model for the actual build, is a way to control spend without touching output quality.
08How to check your real cost with /usage
A built-in cost command surfaces real per-session spend without leaving the chat, but only one vendor in this test had one, which blocked a true cross-provider price comparison.
Scoring outputs blind, before revealing which model made them, removes the bias of judging a result by brand reputation instead of what's on screen.
09My favorite design so far
The single best-scoring output in the whole test was also one of the cheapest, arguing against always defaulting to the highest effort setting.
The cheapest effort tier of a flagship model can land mid-pack on quality rather than automatically at the bottom.
10The most creative animation
Maximum effort settings don't reliably buy either the best result or the most expensive one; cost and effort level correlate loosely at best.
11Final scorecard: looks
A brand-new model's low-effort tier can score below an older model's higher-effort tier, meaning the model name alone predicts quality worse than the effort setting chosen.
12Final scorecard: cost
The most expensive run in a twelve-way comparison cost more than four times the cheapest one, despite both testing the same kind of build.
The model with the priciest max-effort pricing on paper was not the most expensive result in this specific real-world test, so published pricing tiers don't map cleanly to real session cost.
13Is Fable 5.1 max worth it?
Running the highest effort tier by default is overkill for most everyday tasks; it exists for genuinely hard problems, not routine generation work.
The gap in perceived output quality between a model's cheapest and priciest tier is often smaller than the hype around a new release implies.
Glossary
Terms worth knowing.
Prompt caching
A pricing mechanism where an AI model charges a steep discount for tokens it has already processed earlier in the same conversation, since it doesn't have to reprocess that context from scratch.
Effort level
A setting, commonly Low, High, or Max, that controls how much computation a model spends reasoning through a request, trading speed and cost against output quality.
MCP connector
A plug-in style integration that lets a chat-based AI interface call an outside tool or service, such as an image or video generator, without the user leaving the conversation.
“So think of caching like a bookmark that we are able to give an AI.”
self-contained analogy that explains prompt caching pricing in one sentence→ TikTok hook↗ Tweet quote
20:40
“it's not necessarily the outputs that we're getting from these models that is very interesting, it's how much does it actually cost to get a decent output”
the thesis of the whole 21-minute test in one line→ newsletter pull-quote↗ Tweet quote
21:33
“I'm getting really tired of new models dropping and feeling like I'm missing out by not using them.”
candid, relatable close with no setup needed→ IG reel cold open↗ Tweet quote
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphor
Anthropic just dropped Cloud Fable 5 .1 and everybody is losing their minds about it. So instead of just hyping it up, I decided to test it with all the other models and compare the outputs and more importantly, the cost. For this specific use case, I tested it by using the exact same prompt for all of the models in order to generate an animated website.
So by the end of this video, you can see the capabilities of each model and a rough estimate of the cost. And most of all, whether or not it is worth it to use Fable 5 .1 for your everyday tasks. So without further ado, let's dive right in.
All right, so here is the scorecard that we're going to go by. So by the end of this video, I'm going to fill out this entire chart here so we can have a sense of which is the fastest model when it comes to generating this, which one looks the best, which is kind of up to my personal opinion, how long it takes, and then the most important part, probably the cost.
How much do each of these different models cost at each of these different effort levels? So to give you more of a breakdown, not only am I going to test each of the models, Fable 5 .1, Fable 5, Opus 5, and Codex Soul, but we're also going to be testing the effort level as well.
We're going to be testing three effort levels per model. So we're going to test the low effort level, the high, and the max in order to see how expensive it is, how long it takes, and how good it looks. Now before we dive into this, we need to quickly talk about why people are saying that this is 75 % cheaper than other models like CloudFable 5.
And that has to do with something called caching. If you don't know what caching is, let me explain it very simply right now with an analogy so that way anybody can probably understand. understand this.
So think of caching like a bookmark that we are able to give an AI. So this all has to do with the amount of input tokens that we are consuming when using Fable 5 .1 compared to the other previous models. So originally, input tokens are $10 per million output tokens with both Fable 5 .1 and Fable 5.
Well, when we use caching, it is 25 cents per million tokens. So basically, when Claude remembers something that you previously talked about earlier on in a specific conversation or a thread inside of Code, for example, it's not going to charge you $10 per million input tokens.
It's going to then charge you the 25 cents rather. Now, the key point that we need to understand right now and why people are saying this is 75 % cheaper than Fable 5 is because Fable 5, when it comes to caching, was $1 per million tokens. Now, Fable 5 .1 is 25 cents.
So this is essentially a 75 % discount from the previous model. Now, this all sounds great in theory, but the question is, does this really save us money when we go and build a website, for example? And that's exactly what we're going to test in this video now first things first i'm inside of the cloud desktop app and as you can see on the very bottom of my screen we now have fable 5 .1 selected we could also select between fable 5 in the more models section right here so we're going to be testing both fable 5 .1 fable 5 and opus 5 here in this video but before we do this we need to actually generate the visual assets that we're going to be using for our websites so i'm going to be using a mcp server and i'm going to be using a specific connector called higgs field in order to do this now if you don't know what Higgs field is it's basically an all -in -one creative AI studio that allows you to use all of the top AI image and video models all inside of one platform and the best part is is when we plug it directly into Claude with a connector basically we don't even have to go inside of Higgs field to generate these image and video assets we could just have Claude do it directly for us and add this to our website without us needing to go into this platform.
Now I'm going to show you real quickly how to set this up it's going to take maybe 30 seconds so first of all there's going to be a link in the description to access the Higgsfield MCP. So make sure to click on that link.
And from there, you're gonna then see this right here. Once you have an account, all you're gonna do is come to the Higgsfield MCP section and we're gonna copy this right here where it says MCP URL. Then we're gonna come back to Cloud, simply come over to the left -hand side where it says Customize.
Then we're gonna go down to Connectors. This is basically how we're able to connect different applications to Cloud without us needing to leave the Cloud interface. What I'm gonna do is I'm gonna come over and click Add and I'm gonna go to the bottom.
it says add custom connector right here personally i'm just going to call this higgs field and then i'm going to paste in that remote mcp server that i just copied right here next you're going to see this checklist right here i'm just going to move forward with this and click on add and just like that you can now see that higgs field is connected into clock now for the fun part this is when we're going to start generating these videos that we're going to use in this animated website so what i'm going to do is i'm just going to paste in this very simple prompt right here it's essentially saying use the higgs field mcp to generate five photo reel videos of the falcon 9 from spacex it breaks down the aspect ratio the resolution and how long that these videos should be and it kind of breaks down these three scenes that we want to generate right here so this is a pretty basic prompt i could get more specific with it if i wanted to but higgs field is going to actually optimize this prompt in order to generate these videos now what i'm going to do is at the bottom right here you could see i have fable 5 .1 enabled i'm just going to toggle this onto opus 5 because for generating these video and image assets with higgs field using fable 5
0 .1 isn't necessarily going to do anything and it's probably just going to waste some of my token usage here. So I'm just going to go ahead, click on Opus 5 since it is cheaper and I'm going to send this off to Claude. One thing I do want to point out is you could see right here that it's using the Seed Dance 2 .5 model, which is probably the best video model at the time right now.
And one of my favorite parts about using Higgs field is I don't need to go and think which model should I be using if I'm generating images and videos. It automatically knows which model to route it to for any given task. All right, so that took probably like 10 or 12 minutes and now we have these five different video clips that were generated.
So let's take a look at these. They're pretty simple. Obviously, it's just the SpaceX Falcon 9 taking off in this clip.
It looks pretty cool with the clouds. This right here is the Falcon 9 landing in the middle of the ocean. I mean, I think that'll make for a cool visual on the website.
Then we have this one of the Falcon 9 kind of just floating in space, which looks pretty cool. As well as we could always come inside of Higgs field, click on assets, and then we could always view the videos that were generated directly right here. So this is another one that was generated.
of the Falcon 9 kind of like going into orbit. All right, so now that we generated these video assets here, I'm gonna give this exact same prompt to all the different models that we're gonna test this with. So here is the prompt.
It's very, very simple. It simply says, generate a stunning animated landing page for SpaceX. I attached the five clips that I want you to include in our animated website.
And then I did specify not to use the animated website skill because if I were to use this skill that I've created in Cloud, it's gonna make them all look the same and it really won't matter what model we're using. this first one, I'm going to use Fable 5 .1. I'm going to put this on low effort.
I'm going to send that off. All right. So I have all of these running inside of Claude and I'm not going to lie.
I have no clue how much this is going to cost. This is pretty loaded. We'll see if by the end of this video, I'll even have any usage limits left.
But if you guys are enjoying this video and you're enjoying watching me burn all these tokens, make sure to subscribe to the channel for more content like this. Now I need to do the same thing for Chachibit 5 .6 Sol. So let's go ahead and do that right now.
All right. So I let Claude and Chachapiti do its thing for about 30 or 40 minutes.
As you can see, it's actually dark out now. When I was recording earlier, it was still light out. So this took quite a while to go and build all of these different websites and design.
So now we're going to go through this scorecard. So what I'm going to do is I'm going to go through each of these websites and I'm going to look at the design, basically how it flows with these animations that we created. And I'm going to score it on a couple of different things.
I'm going to score on the look. I'm going to write down exactly how long it took for each of these to generate. I'm going to break down the cost.
cost, how much it cost it to run this entire task with this simple one prompt that we use for all of them. So that way you can understand not only the design outputs of these models, but how much time it takes and how much it actually costs, which at the end of the day is probably what you are worried about. Now, in order to make this more exciting for you guys, I'm going to do a blind testing.
So I'm not going to explain what model generated these websites. I'm going to leave it up to you to guess yourself. And then I will share once I give it a rating.
All right. So this is the first one that we're looking at. As you can see, the asset that we generated with Higgs field is embedded.
This looks pretty cool. There's a rocket taking off. We have certain texts going through this and I'm scrolling at a moderate speed here.
It looks like that, you know, Starship is landing right here. I think this is solid, but I'm not going to lie. Some of the graphics aren't flowing basically how we'd like them to.
Oh, I think this is pretty cool. Kind of, you know, showing this little graphic. I didn't instruct for this to generate it like that, but it did.
So I think this one overall is pretty good. Again, I think the animations don't flow as good as they should. Like, for example, this one shoots up.
I think that looks pretty cool. Now, before I give my ranking out of 10, I do want to preface and say, this is obviously completely subjective.
This is just off the first glance of how I think that the website flows. And if I am stunned by the design, because I've created countless amounts of websites like this, so I could kind of see when it's more of a basic vibe coded website design. And a couple of these outputs blew me away with the creativity.
So I'm just going to simply make my judgments on what I find interesting. Now, if I had to rate this one, I'd probably give this maybe a solid six out of 10. I kind of like this right here.
It's pretty creative. So I'm going to give that one a 6 out of 10. And the model that generated that output was...
Opus 5 Max. So I'm just going to come here and just say 6 out of 10. Now, let me go ahead and check the usage.
Now, if you are inside of cloud and you want to do the exact same thing, all you have to do is forward slash cost or usage, and it will automatically just pull up this table here. It'll show you your five hour limit, your weekly limit on all models. It'll show your weekly fable limit and will show the cost for this session based on all the models you use.
So for this session, the cost was $10 .70, which isn't terrible. And the API was being used for 14. minutes.
What we're going to focus on is active right here. So 17 minutes in 57 seconds. All right.
So we have the first one logged. We have Opus 5 Max, and I'm going to go through these pretty quickly. We don't need to go into all the details.
Just at first glance, I'm going to rate these, dive into the time and the cost so we could go through this quickly. All right. So here is the next one.
We have our Falcon 9. Again, these are going to be the exact same animation shots that we generated with Higgs field. I mean, this one's pretty solid, nothing crazy.
It's got like all this texture, which the other one didn't necessarily have.
I mean I think this one's good. I don't think it's anything crazy. I'd say this one's probably not as exciting as the last one.
So I'm going to give this one a 5 and the model that generated this one was Opus 5 High. So I'm just going to rank this 5 out of 10 and let's go into the other statistics here. So for this one we have a cost of $11 which is pretty similar to the previous one that we just showed.
This one was active for 22 minutes and 6 seconds. Moving on to the next one let's take a look at this one. So we got Falcon 9 obviously.
We have a little final countdown. I think that's a Nice, cool addition.
I think that's pretty creative. I scroll down, it shows liftoff. One thing that I think is cool about this one is it shows this little like text overlay here where it shows a number.
So it shows number one. And as I scroll, it shows number two behind the main text, number three for the landing, and then built again to fly. I mean, I think this one's pretty solid.
This text looks solid. And then down here, this text, I can't really see for Falcon 9. If I had to rate this one, I'd probably give this a solid like six out of 10.
And that was Fable 5 Max. So this is getting to the better models, obviously. two previous ones were Opus 5 which were the cheapest models and this is on the max effort level as well so we're starting to scale up in terms of like the amount of money we're going to be spending with the models and for me personally so far I'm not seeing a massive difference in terms of the quality.
I think they are all pretty solid so I believe I said 6 out of 10 and now let's go take a look at the price and the time it took. Alright so now is when we're going to start seeing the discrepancy between the cheaper and the more expensive models since this was Fable 5 which is obviously more expensive than Opus and it was the max effort level so this one for this session was $24 as opposed to our previous two that were like around the $10 mark and then this was active for a total of 26 minutes and 41 seconds on to the next one and this one is a bit different than the previous ones we generated so it looks like each of the videos are kind of static like of course they're moving but it doesn't move as i scroll through the website if that makes any sense which i think could be pretty pleasing to the eye it's not as creative in my opinion which is kind of what i'm judging the outputs on but i think that this is the most like real life website i think that you would see because you know it's very easy to read what is on the screen here i'm along with like a cool little video behind this so i think this one is actually pretty solid i'm gonna give this one i'm gonna give this one a 7 out of 10 in the model that generated that one was codex 5 .6 tera light which is actually pretty surprising since
This is one of the cheaper models from Codex. This is the first model that we've tested that is not a Claude model. But I guess this actually makes sense since the design style was a little bit different than the Claude models since it was a little bit more static.
So I guess that's kind of interesting. So 7 out of 10 on the look or the design. As far as the time, this one took about 10 minutes and 53 seconds, which is on par with some of the lower Claude models.
Now, unfortunately for the cost, it wasn't as simple as Claude was where I could just type slash usage. would bring up that card in order to show me how much this costed for this specific session. So unfortunately, I'm not going to be able to track this for both of the Chachapiti models, but hopefully you can get a sense of, you know, the design that it can create and how long it will take compared to the Claude models.
Here is the next one. I kind of like how this has pretty big text here. We got Falcon 9.
As I scroll, it's launching. We have liftoff. Here it is landing.
I think this one's actually pretty solid. I'm not going to lie. I think it's clean.
I like the big text and typography. And then I honestly really like this section as well as well as this this is probably I'm not gonna lie my favorite one that I've viewed so far I'm gonna give this one a solid 8 out of 10 and I'm curious if you had to guess what do you think that this one is gonna be I'll give you a couple seconds to think about it and this was fable 5 .1 high which I guess makes sense since it was my favorite design all right I think I gave this one actually an 8 out of 10 which is the highest ranking so far now let's look at time and cost now this one is very surprising to me the cost for this was actually only $8 .78 which is the cheapest output that we've gotten, as well as it was active for 18 minutes, which isn't anything crazy.
We've had some that were up to like 26 minutes so far, I believe. So this is pretty surprising. And if we're learning anything here, at least for me, it's that sometimes a model doesn't necessarily matter that we are using.
Now, let's see if we can find a new favorite. This one, let's go through this one. Okay, so.
So far, I think this one's kind of basic. I'm not a fan of this text here. Scrolling again, nothing too fancy.
Probably getting tired of watching the same visuals over and over again, as am I. I think this one is okay. If I'm not going to lie, I'll probably say this is my least favorite one so far.
I'm going to give this one a four out of 10. All right, next on the list, and I'm going to try to speed this up because I know this is taking quite a while, but hopefully you guys are enjoying this. So this one is pretty simple.
And if you remember previously, this might look similar to one that we generated earlier on. I think if you like simple websites, this might be like really enticing to you. You'll probably really like this one.
I think it's clean, but... If I had to judge this in terms of the creativity, I'd probably have to give this a 6 because it's nothing, you know, super creative. But I do like the way this one looks.
And if you remember the previous Chachaviti model, you might have guessed that this was also generated by Chachaviti. And that is correct. This was the Codex 5 .6 Sol High.
Again, there's no way for me to check how much this costed, unfortunately. But this did work for 13 minutes and 7 seconds, which is actually pretty surprisingly low. Moving on and this one is pretty unique.
So first of all as I scroll nothing crazy and then boom we have this like explosion as there is liftoff on the rocket. I think that's pretty cool.
And then as this lands as well it also does this like shake. So I think this one's cool. I think this one's pretty creative.
As long as I like the big text down here. This one might be near the top for me. I'm not gonna lie just because it's creative with you know the kind of the the shaking.
of the frames here i haven't seen any of the other ones do something similar to this so i might have to give this one a solid seven all right so the website that you just saw generated is fable 5 .1 max and i'm going to give this a 7 out of 10 let's calculate the time and cost now all right so let's now break down the cost of fable 5 .1 max to run this generation here so cost it about 10 .67 which honestly is incredibly surprising since the max effort level on fable 5 .1 is supposed to be pretty high based on everything that i've seen online so far since it's released and in terms of how long this took it took 26 .9 minutes so basically 27 minutes that is pretty long i think this is like the longest generation out of all these models now we only have three more websites to test so let's move on to the next one and i'm gonna make this quick so here is this one here this one is honestly pretty terrible there's no video that is playing for these animations the text kind of it just looks pretty bland yeah this one is not good at all i'll give this one
a 2 out of 10. Now this one makes sense I guess because this was Opus 5 on the low effort level so this was the worst model and the cheapest model and me personally I could tell the difference between the other outputs and I'd assume you probably think that one was pretty bad too so that was a 2 out of 10 in my book and in terms of pricing this was only $6 .58 which I think is probably the cheapest which makes complete sense and then this ran for 10 minutes and 16 seconds.
Alright moving on to the next one I think we only have two left after this so we're getting close to the end. This one is cool.
I think the typography is cool. Obviously, we're using the same graphics here in the background. This one is actually moving.
I think this one's solid, but again, it's nothing crazy. If I had to give this a rating out of 10, I'd give this one maybe a 6 out of 10. This was Fable 5 High, giving it a 6 out of 10.
And this one was $5 .78 to run, which is the cheapest so far. And this ran for only 2 minutes and 11 seconds, which is pretty surprising. This is kind of interesting.
All right, so one more after this. Let's take a look at this one. Falcon 9.
This one's good. It's got some pretty big typography.
I think it takes up a little bit too much on the screen here. I'm not a huge fan of this text right here. Seems like a bland kind of space in our website here compared to some of the other ones.
But again, it's nothing bad. It's nothing great. If I had to give this one a rating, I'd give this one maybe a five.
And finally, this is the last website. This is CloudFable 5 Low. And I think this one's pretty solid.
It's pretty basic. It kind of reminds me of the Codex ones that we created. But I think this one's solid.
I like the orange accents. I like this cool little thing, cool bar going. across my screen.
I think this one's pretty creative. I'd honestly give this one probably like a 7 out of 10. Now for Fable 5 Low, in terms of the time and the cost, this was actually pretty good.
So it only took about 5 minutes and 4 seconds, and it was $9 .70. I guess it was actually $9 .76 in order to generate it. Now, here is the final scorecard.
Now, if we're going off the model that was ranked the best in looks, in my humble opinion, of course, this is completely subjective. The one that wins is Fable 5 .1 High, which ranked an 8 out of 10. Now, here is the final ranking scoreboard here, broken down in two categories.
First, let's go through the look, and then we're going to go through the cost right here. So, in terms of the model that got the highest look, that is Fable 5 .1 High, which got 8 out of 10. Next below that is Fable 5 Low, which got a 7 out of 10, which is pretty interesting because there's a big discrepancy there.
We have Fable 5, the previous model on the low effort level compared to Fable 5 .1, which is this new hyped up model that is on the high effort level, which makes sense. But the fact that these are very close and in terms of the design output, like honestly, I probably wouldn't be able to tell the difference between the two.
It's pretty interesting. Next, the model that you would think would be at the very top, Fable 5 .1 Max. I have this tied in second place, 7 out of 10.
Next. Codex Soul Light, which is 7 out of 10, which is pretty interesting. Completely different model from OpenAI.
And then I'm going to go down to the bottom. We have Opus 5 Low, which honestly makes complete sense. It's the worst model.
It's the cheapest model. And I gave that a 2 out of 10. Next up above that, I have Fable 5 .1 Low, which is a 5 out of 10.
This is pretty interesting. If anything, this tells us that the low effort level models obviously aren't very good when it comes to design and specific complex tasks like this. And that goes for even 5 .1, which When I started this, I honestly thought this would be ranked closer to the highest.
Now, in terms of cost, let's break this down because this is pretty interesting. Fable 5 High was the cheapest. It was $5 .78.
Next, we have Opus 5 Low, which obviously makes complete sense. It should be the cheapest. Then Fable 5 .1 High got $8 .78, which seems pretty interesting.
You would think that this would be quite a bit higher. Fable 5 .1 Max, this is probably the most like random cost out of all of these. It is $10 .67.
ranking in spot number five which you would think this by far would probably be the most expensive model but according to this test it simply was not. Next the most expensive model was Fable 5 Max which I guess makes sense since it is one of the higher effort level models and if I walk away from this test learning anything it is that these models fluctuate in the price as well as the quality of their outputs.
Naturally when Fable 5 .1 released I was thinking of making a video breaking down how to make insane websites with this new model but I realized that the biggest thing that people using these models are starting to realize is that it's not necessarily the outputs that we're getting from these models that is very interesting it's how much does it actually cost to get a decent output i really do feel like if you are a average consumer of ai using a model like fable 5 .1 max at the highest effort level is probably overboard for whatever it is you're trying to do like for example in this video i'm generating animated websites that would usually be something you'd use a top model for but when it comes to the designs there's really not a huge discrepancy between the two as well as for the pricing it could be kind of hit or miss depending on what it is you generate so anyways i know this video is probably all over the place i wanted to do this so you could just get a sense of the design outputs from these different models as well as the cost breakdown since i know a lot of you guys are asking which model you should be using and how to optimize your token usage if you guys enjoyed this video make sure to leave a like subscribe to the channel and honestly just let me know your thoughts about this in the comments below i'm interested to hear if you're feeling like model fatigue i'm getting really
tired of new models dropping and feeling like I'm missing out by not using them. But genuinely, I feel like there's not a massive difference as of right now. Thanks for saying the end and I'll see you in the next video.
Peace.
The Hook
The bait, then the rug-pull.
Anthropic released Fable 5.1 with a headline claim of a 75% cheaper prompt-caching rate, so this video puts that number to the test: the same website-build prompt, run twelve times across four models and three effort levels, scored blind on looks before anyone checks what it cost.
Frameworks
Named ideas worth stealing.
18:20list
The 12-Build Scorecard
Fable 5.1 High — 8/10 look, $8.78, ~18 min
Fable 5 Low — 7/10 look, $9.76, 5:04
Fable 5.1 Max — 7/10 look, $10.67, 26:54
Codex Sol Low — 7/10 look, cost n/a, 10:53
Fable 5 High — 6/10 look, $5.78, 2:11
Fable 5 Max — 6/10 look, $24.01, 26:41
Codex Sol High — 6/10 look, cost n/a, 13:07
Opus 5 Max — 6/10 look, $10.70, 17:57
Fable 5.1 Low — 5/10 look, $11.41
Opus 5 High — 5/10 look, $11.01, 22:06
Codex Sol Max — 4/10 look, cost n/a
Opus 5 Low — 2/10 look, $6.58, 10:16
Four models (Fable 5.1, Fable 5, Opus 5, Codex Sol) each ran the identical animated-landing-page prompt at Low, High, and Max effort, twelve builds total, scored blind on design before any cost was revealed.
Steal forany bake-off comparing AI tool cost against output quality before committing to a paid tier
01:27concept
Prompt caching discount
$10 / million uncached input tokens
$1 / million cached tokens on Fable 5
$0.25 / million cached tokens on Fable 5.1 (75% cheaper than Fable 5's cached rate)
The '75% cheaper' claim around Fable 5.1 refers specifically to its cached-token rate versus the prior model's cached rate, not a blanket price cut on every token.
Steal forunderstanding what a 'cheaper model' pricing claim actually covers before assuming it lowers your real session cost
CTA Breakdown
How they asked for the click.
VERBAL ASK
21:30subscribe
“if you guys enjoyed this video make sure to leave a like subscribe to the channel and honestly just let me know your thoughts about this in the comments below”
Folded into the closing recap rather than a hard sell, paired with a direct question about model fatigue to prompt comments instead of just asking for the subscribe.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
Anthropic merged Claude's memory between chat and Cowork so both remember the same things, but the sync only works if Cowork runs in the cloud, not on your own machine.
A 72-minute, screen-by-screen course on turning Claude Cowork into an entire marketing department — voice skills, image and video generation, lead scraping, live dashboards, auto-scheduling, and AI SEO.
00:12
00:22
00:51
01:34
01:50
02:16
02:55
03:10
03:26
03:37
04:17
04:35
05:00
05:06
05:27
05:41
06:18
06:34
06:47
07:25
07:42
07:59
08:15
08:32
08:43
09:27
09:38
09:56
10:20
10:33
10:56
11:10
11:32
11:51
12:04
12:27
12:45
13:18
13:33
13:53
14:04
14:20
14:38
14:50
15:22
15:31
15:55
16:10
16:27
16:41
16:56
17:11
17:34
17:39
17:55
18:38
18:55
19:12
19:30
20:03
20:19
20:50
21:05
21:30
13:03
10:15
09:35
1:12:16
10:57
15:30