It's on-chip silicon, not a marketing feature. This kind of product design is just really hard. Mask sets get well into the billions of dollars, you can't just assemble a list of features as if they're all free. You need to decide upfront, often years in advance, what feature you think people will want to buy for the market you think you'll find yourself in. There are no easy answers.
But just in general, Intel has always prioritized lots of I/O flexibility on its chips. If you look at the datasheets there have always been dozens and dozens of units on every SKU that are never plumbed out to ports on the device. Three or four display outputs, six or eight USB controllers, stuff like that. Apple is the opposite: they won't include something if they aren't absolutely sure they need it. So after the shift from x86 to Apple silicon, laptop users are feeling a squeeze on I/O that used to seem "free".
Even if there are technical limitations that prevent Apple from adding more I/O easily, as a consumer it feels like artificial segmentation/limitation.
Apart from the initial M1 MacBook Pro release, it feels like most products Apple has released in the last few years has always been missing one or two features, and the next release happens to have that feature. E.g. the first M1 Air did not have MagSafe even though the Pros did, and then Apple included MagSafe in M2 Air, but it didn't support multiple displays; now Apple is including multiple displays in M3 Air.
It feels awfully convenient that each generation conveniently has a nontrivial feature upgrade.... Apple has less incentive to make each generation "complete" -- by delaying features (more) consumers will feel obligated to upgrade per generation.
It does seem odd, though, to brand a laptop as "PRO" and limit it to 2 displays, then release a non-PRO device that can handle more.
Edit: Better wording, I suppose, that the non-PRO supports two external monitors with the lid closed, the PRO supports 1. Still an odd overall offering/branding.
In principle I agree. But the M3 chips are similar for the M3 Macbook Pro and M3 Macbook Air. The PRO laptop is the one that only supports 1 display while the AIR supports 2 with the lid closed.
I had a 2019 cheesegrater Mac Pro. With Catalina, I was able to drive two 4K screens at 144Hz in HDR10, because Catalina apparently supported DSC 1.4.
Then they introduced the ProDisplay XDR with Big Sur which had people agog at "how were they able to drive this 6K display given the bandwidth limitations?"
Well, the answer is because they absolutely nerfed/bastardized DSC 1.4 from Big Sur (and it's maybe only been updated in Monterey? Unsure, I no longer have the screens - ironically I bought an XDR) to make it happen with some proprietary magic: those same screens could now only be driven at 60Hz in HDR10 or 95Hz in SDR.
Proof in the pudding was that my monitors (LG27GN950-B) actually allowed you to change the advertised/supported DSC version, and when I "downgraded" the monitors to DSC 1.2, performance actually improved, and allowed 120Hz SDR and 95Hz HDR.
This happened with many many users, across many screen types.
Apple studiously ignored it, and may still be. They simply don't care if you're not using an Apple display.
But just in general, Intel has always prioritized lots of I/O flexibility on its chips. If you look at the datasheets there have always been dozens and dozens of units on every SKU that are never plumbed out to ports on the device. Three or four display outputs, six or eight USB controllers, stuff like that. Apple is the opposite: they won't include something if they aren't absolutely sure they need it. So after the shift from x86 to Apple silicon, laptop users are feeling a squeeze on I/O that used to seem "free".