Private AI inference.
Powered by real Macs.
MACnet routes encrypted requests to verified Apple Silicon providers. Developers get familiar APIs and lower compute costs. Mac owners can earn from hardware they already own.
Explore the console preview now. Live inference and sign-in are being prepared.
Private inference without a new SDK
Change the base URL and keep your existing OpenAI client. Requests are encrypted before they leave your app and routed to verified Apple Silicon providers.
Open API console ↗Turn idle Apple Silicon into earnings
Run a provider on hardware you already own. MACnet matches your Mac with inference demand, and operators keep 100% of inference revenue during the public alpha.
Explore provider console ↗Capacity is bought, rented, repackaged, and metered before it reaches an API call. Each layer adds margin. MACnet routes demand to idle Apple Silicon instead, where the hardware is already paid for and the marginal cost is mostly electricity.
→
→
API providers
→
End users
MACnet turns that idle capacity into a private inference market.
Developers get lower prices without changing SDKs. Mac owners earn from machines they already own. The coordinator matches demand to providers, but prompts stay encrypted and hidden from the operator.
Prompts can contain customer conversations, internal plans, source code, and other sensitive context. A marketplace promise is not enough when inference runs on hardware you do not own.
MACnet is designed around a stricter guarantee: the coordinator can route requests, the provider can serve them, but neither should get a usable view of the prompt.
Private inference requires privacy that can be verified, not just promised.
Operator-blind by design
MACnet removes the practical software paths an operator could use to observe inference data. Four layers work together, with hardware identity verified privately by the coordinator.
Encrypted end-to-end
Requests are encrypted before transmission. The coordinator routes ciphertext, and only the matched provider's hardware-bound key can decrypt the request.
Hardware-verified
Each provider uses a key generated inside Apple's tamper-resistant secure hardware. The attestation chain traces back to Apple's root certificate authority.
Hardened runtime
The inference process is locked down at the OS level. Debugger attachment and memory inspection are blocked so the operator cannot inspect a running request.
Traceable to hardware
Responses carry the verified trust state of the machine that produced them. The coordinator validates Apple's chain and publishes a privacy-redacted verdict without exposing device identifiers.
The operator contributes compute, not visibility.
Your prompt is encrypted before it leaves your app. The coordinator routes traffic it cannot read. The provider serves the request inside a hardened process the operator cannot inspect.
OpenAI-compatible API
Keep your SDK, request shape, and streaming code. Point the client at MACnet and start routing private inference.
from openai import OpenAI
client = OpenAI(
base_url="https://api.macnet.example/v1",
api_key="your-api-key"
)
response = client.chat.completions.create(
model="gemma-4-26b",
messages=[{"role": "user", "content": "Hello!"}],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta.content, end="")50% lower cost, comparable performance
Idle Apple Silicon keeps the cost structure simple. Pay per token with no subscription or minimum, with selected model prices set around 50% below typical API-provider rates for comparable models.
| Model | Input | Output | Typical API | vs typical API |
|---|---|---|---|---|
| Qwen 3.5 9BDense VLM with inline MTP · 256K context | $0.08 | $0.13 | $0.26 | 50% lower |
| GPT-OSS 20BMoE · 128K context | $0.02 | $0.10 | $0.20 | 50% lower |
| Gemma 4 26B128K context | $0.042 | $0.22 | $0.44 | 50% lower |
| Qwen 3.8 27BDense VLM with inline MTP · 256K context | $0.15 | $2.00 | $4.00 | 50% lower |
| Qwen3-VL 30B A3B InstructMoE VLM · 128K context | $0.09 | $0.40 | $0.80 | 50% lower |
| Nemotron 3.5 LightningHybrid MoE · 256K context | $0.065 | $0.18 | $0.36 | 50% lower |
| Qwen3.5 35B A3BMoE VLM with inline MTP · 256K context | $0.08 | $0.75 | $1.50 | 50% lower |
| Qwen 3.6 35B A3BMoE VLM with inline MTP · 256K context | $0.05 | $0.70 | $1.40 | 50% lower |
Prices per million tokens. Typical API means published list rates for comparable models from major API providers.
Earn from your Mac
Install the provider, choose when your Mac is available, and earn from inference jobs matched by the network. During the public alpha, operators keep 100% of inference revenue.
Terminal setup Coming soon
The MACnet provider installer will be published once the live network and domain are ready.
$ Installer available at launchSetup instructions and signed downloads will appear here.
Earnings estimate
Select a Mac model, chip family, and unified memory to see your estimate.