Apple Foundation Models
139 points
5 hours ago
| 15 comments
| platform.claude.com
| HN
harrouet
3 minutes ago
[-]
This is Apple commoditizing LLMs while keeping control of the UX.

They are a hardware company and will keep selling the best machine for AI use. Well done.

reply
rock_artist
1 hour ago
[-]
While I'm happy with Apple introducing this abstraction. my main concern was with local models.

I'd love using Gemma4 as an example. but thinking of a user. if 10 Apps each uses same model and downloads it, the phone will be bloated.

I still didn't understand if Apple provided a way for multiple apps uses same on-device model (without tricky namespaces and permissions).

I didn't see anything suggesting that's the case.

reply
alwillis
3 minutes ago
[-]
Check out “Bring an LLM provider to the Foundation Models framework” - https://developer.apple.com/videos/play/wwdc2026/339
reply
jtfrench
1 hour ago
[-]
That's a great opportunity for Apple to provide a universal unique model ID protocol and some shared storage space to allow devs to register models.
reply
trvz
1 hour ago
[-]
Do you guys not have phones (with at least 1TB of storage)?
reply
rock_artist
51 minutes ago
[-]
Who’s “you guys” a developer from Bay Area? A student with a MacBook Neo? Or John Appleseed who bought basic iPhone 17e?
reply
exitb
38 minutes ago
[-]
I'm guessing it's a BlizzCon joke.
reply
mft_
59 minutes ago
[-]
I have a Mac with 4TB of storage but it’s still annoying when every new AI app I try installs its own virtual environment with a fresh copy of Python, PyTorch, other duplicate libraries, and then models on top of that.
reply
DrScientist
30 minutes ago
[-]
As an occasional python user I'm always amazed and frustrated that it seems that the only way to be able to use/build anything is to create a whole separate environment.

And now given everybody now does this I guess the incentive to stop breaking stuff reduces even further.

Might as well have static binaries.

reply
simondotau
20 minutes ago
[-]
The meme phrase “it’s fractally wrong” applies to the entire python ecosystem, IMHO. Virtual environments are just another layer of the fractal wrongness, in addition to being evidence in favour of this hypothesis.

It’s a useful language though.

reply
klausa
1 hour ago
[-]
The apps can use the system provided on-device model using the same framework and APIs; but there's no affordances to deduplicate custom models between apps.
reply
daniel_iversen
2 hours ago
[-]
Is this Apple encouraging developers to go through their api abstraction layer to use LLMs so that when they launch their own (which I think we’ve heard they’ve been spending lots of money on training and might be somehow involved with Siri or current Apple AI?) that they can easily help devs make a seamless transition? Or is it just a developer nicety or something else?
reply
tarcon
1 hour ago
[-]
Apple has some clever mechanics to protect user data. I had to work with App tracking stuff lately and their approach to keeping user details private with anonymized cohorts (SKAN, Differential Privacy) before reporting tracking events to third party platforms was surprisingly well thought out. There is value in having them in your loop if you care about privacy.
reply
willis936
25 minutes ago
[-]
It would be cool if they offered some kind of prompt sanitation option.
reply
NorwegianDude
1 hour ago
[-]
A dark, but not totally unfair take: It makes it easier for Apple to take payment for the models others provide, and even allows Apple, if they want to, to use the data to build a dataset for training their own models based on how users use third party models. It's only on Apple devices this API is used, so they split up the market by not letting developers use the same system if they want things to work on iOS, locking users even more in.
reply
oefrha
1 hour ago
[-]
Call it Intelligence Store and charge… wait for it… 30%.
reply
klausa
1 hour ago
[-]
This is support for a new framework that ships with reality/mac/iPad/watch/tv/iOS 27 (and that they've promised to open-source later in the year, so presumably you'll also be able to lean on this if you ship Swift on your backend).

The framework's whole deal is that it lets you use the same API to target either the device built-in models, the Apple-hosted online models (Private Cloud Computer), or write your own shims to call out to arbitrarily hosted online models.

You can then dynamically route your calls to a different kind of model/provider, using system APIs, without having to write your own abstraction layer over "I want to use local model for this, but I want to use Claude for that", or having to integrate your own API integration with Anthropic/OpenAI APIs.

It abstracts things like tool calling in one place; and has a bunch of other niceties/oddities (it keeps the same "transcript" going, even if you dynamically switch providers/models during a session) and some other things.

reply
pprotas
2 hours ago
[-]
The cynic (or realist?) in my thinks this abstraction layer is Apple's way of making sure that users give their own Apple Intelligence credit for the underlying LLM functionality, even if another company is actually providing the LLM.
reply
_the_inflator
2 hours ago
[-]
Assembled in Cupertino once more. ;)
reply
coldtea
30 minutes ago
[-]
Yeah, Apple just designs and writes the SoC, CPU, graphics unit, neural unit, compiler (Swift), OS, graphics layer, 3D API, core libs from graphics to persistence, filesystem, broadband chip, and a few more things besides...
reply
saagarjha
25 minutes ago
[-]
Notably good models are not on that list.
reply
geden
4 minutes ago
[-]
Neither are other capex heavy items like chip fabs.
reply
thombles
2 hours ago
[-]
There are already on-device models that you can use through this framework as a developer. Claude would just be an additional one.
reply
FinnKuhn
2 hours ago
[-]
Maybe they plan to have the providers pay for being the default model? So basically, what Google is doing right now for search engines. The difference however is that Google is making money with additional search requests while AIs are (as of now) losing money with additional requests. I don't see the business case for them yet though.
reply
mathisfun123
2 hours ago
[-]
> which I think we’ve heard they’ve been spending lots of money on training and might be somehow involved with Siri or current Apple AI

Lol bro this is literally it this is the model they've been training (was Apple Foundation model not a big enough hint?)

reply
VadimPR
22 minutes ago
[-]
How can you practically use this in software if you're to deploy this to users? Asking a user to create and enter their own API key is a bar too high for good UX.
reply
Maxious
6 minutes ago
[-]
> For production, route requests through your own back end with .proxied

Apple is offering developers with less than 2 million downloads free AI models via their servers https://techcrunch.com/2026/06/08/apple-bets-cheaper-ai-will...

reply
adithyassekhar
1 hour ago
[-]
> Requests go directly from your app to the Claude API; Apple is not in the request path and does not see prompts or responses.

I know this is from a developer perspective. But as a consumer this is just funny.

reply
saretup
29 minutes ago
[-]
Why?
reply
zkmon
2 hours ago
[-]
Coding agent itself an imposed layer. Now they are adding one more layer? Many times I think of coding agent as the vendor supervisor from the body shops of the 90's who promise the customer everything under the sky and thrash the poor contractor to deliver. Coding agents consume 10x more tokens just like how body shops charged their customers vs how they paid the contractors. For a simple test, the same task that makes the model to go out of context length when used via a coding agent, runs fine when prompted directly.

Layers are luxury and remove control and transparency.

reply
klausa
1 hour ago
[-]
You wouldn't use this when building a coding agent.
reply
_pdp_
1 hour ago
[-]
From app developer standpoint why would anyone ship claude keys like that ... or am I missing something? From consumer standpoint - I guess they can use their own keys but it is not something that is very user friendly as you can imagine.
reply
nl
1 hour ago
[-]
it says:

Proxy (production)

For production, route requests through your own back end with .proxied. The relay at baseURL adds the Claude API credential server-side, so the app ships no key. The headers you provide are sent on every request so your proxy can authorize the caller.

https://platform.claude.com/docs/en/cli-sdks-libraries/libra...

reply
21-DOT-DEV
1 hour ago
[-]
> Usage is billed to your Anthropic account at standard API pricing.

While expected, it’s still a bummer.

reply
_josh_meyer_
2 hours ago
[-]
reply
HelloUsername
1 hour ago
[-]
Does "Apple Intelligence" need to be Turned On for this as well?
reply
gregman1
2 hours ago
[-]
So actually the most successful AI was OpenRouter Intelligence? Pronounced as OÏ.
reply
Traster
1 hour ago
[-]
This seems smart. Apple, despite not really leading in AI themselves, are right on the hot path of where developers are going to yolo slop into the ecosystem. Make a tonne of sense to define a nice clean API that places like Anthropic can build on top of and expose to developers.

It's also smart for them to make sure the billing is going direct from Anthropic to the developer. The initial thought is "That means Apple's not taking a cut", but from the other side of it, developers who use this API are going to have to expose that cost to customers somehow, and that translates to subscription/InAppPurchase etc. on top of which Apple will get it's 30%.

reply
me551ah
1 hour ago
[-]
So where does the api key reside? You can’t ship it on the iOS client since anyone can read and abuse it
reply
laxmansharma
31 minutes ago
[-]
reply
jedisct1
59 minutes ago
[-]
Misleading title. This is about Claude for Apple Foundation Models, not about Apple Foundation Models
reply
hit8run
1 hour ago
[-]
Why would I want a nerfed model?
reply