Leverage Private Cloud Compute in your app
Apple launches zero-cost server LLM for developers via Private Cloud Compute with no API keys
“there are no token costs to you, the developer”
Apple is extending its Foundation Models framework to include a server-side model running on Private Cloud Compute, with no developer token costs and no authentication overhead. Users get a daily usage limit baked into Apple Intelligence, with iCloud Plus unlocking higher limits. This positions Apple as a unique player offering privacy-preserving cloud inference as a platform primitive rather than a third-party API.