Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Apple / Apple Foundation Models 3

AFM 3 Cloud

Third-generation Apple product model co-developed with Google, with hardware and access depending on the specific deployment.

availableClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
10 of 23 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesApple Private Cloud Compute
Output billingSee billing notesAccess and billing notes below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2026-06-08Source for Release date (opens in a new tab)

Model announcement; product rollout followed on 14 September 2026.

Parameters
Not collected
Architecture
Updated Parallel-Track Mixture-of-Experts architectureSource for Architecture (opens in a new tab)
Languages
Not collected
Context caching
Not collected
Deployment
Private Cloud Compute on Apple siliconSource for Deployment (opens in a new tab)
Published price
Product access with variable daily limits; no per-token or per-image tariff verifiedSource for Published price (opens in a new tab)
Documented tool behavior
Multimodal reasoning described; public checkpoint-specific reasoning control not pinnedSource for Documented tool behavior (opens in a new tab)
Developer access
PrivateCloudComputeLanguageModel is available in OS 27; exact routing to named cloud checkpoints is not guaranteed by the reviewed SDK referenceSource for Developer access (opens in a new tab)
Included free allowance
Eligible Small Business Program developers with fewer than 2M first-time App Store downloads can request PCC access without cloud API chargesSource for Included free allowance (opens in a new tab)

Managed entitlement and per-user daily limits apply. Not an unrestricted free public model API. Eligibility loss requires migration within six months after notification.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Apple Private Cloud Compute

Provider source (opens in a new tab)
API model ID
Not collected

Product or SDK model identity, not a verified public HTTP model selector.

Access
Product-integrated model. The exact request selector, checkpoint pin and independent developer access for this specific model are not established.
Regions
Supported Apple devices, OS versions, languages and regions only. A device-local model is not a guarantee of access in every market.
Request quotas
Daily limits vary with feature, complexity, demand and policySource for Request quotas (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Apple describes PCC privacy protections. Supported deployment and region depend on the product; no universal customer-selectable residency is established.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Apple Private Cloud Compute

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

Text preference against AFM Server 2025

Apple · vendor-reported
64.7%

Apple side-by-side human evaluation; 2025 model preferred on 8.7% of prompts. Beta-stage model evaluation, not independently measured production accuracy.

Evaluation source (opens in a new tab)

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Apple documents this proprietary product model. No matching unrestricted public checkpoint was verified in the reviewed Apple weight inventory. Closed-weight classification is inferred for this product identity; OS delivery and member-gated model assets do not imply an open-weight release.

Classification evidence (opens in a new tab)

Lifecycle dates

Model family announced8 Jun 2026Source (opens in a new tab)
Apple Intelligence product rollout begins14 Sept 2026Source (opens in a new tab)

Sources reviewed