Fixed price, unlimited inference

Simple, transparent pricing

Dedicated Apple Silicon for AI workloads. No per-token fees, no shared resources. Fixed monthly price, cancel anytime.

MonthlyAnnualSave 20%

Starter

Up to 14B LLM, single agent

$119/mo

$149/mo billed annually

16 GB
512 GB SSD
1 deployment
  • Full catalog access
  • OpenAI-compatible API
  • Run up to 14B models
  • SSH & VNC access
  • 99.9% uptime SLA

Standard

Up to 32B LLM, 2–3 agents

$239/mo

$299/mo billed annually

32 GB
512 GB SSD
2 deployments
  • Everything in Starter
  • Run 24–32B models
  • AI development environment
  • Priority provisioning
Most Popular

Advanced

Llama 70B Q4, multi-agent stacks

$479/mo

$599/mo billed annually

64 GB
1 TB SSD
3 deployments
  • Everything in Standard
  • Run 70B models (quantized)
  • Multi-agent orchestration
  • Priority support

Pro

70B FP16, demanding production

$959/mo

$1199/mo billed annually

96 GB
2 TB SSD
5 deployments
  • Everything in Advanced
  • Run 70B at full precision
  • Dedicated ML engineer support
  • 99.9% uptime SLA

Max

120B+ frontier OSS models

$1599/mo

$1999/mo billed annually

128 GB
4 TB SSD
5 deployments
  • Everything in Pro
  • Run 120B+ frontier models
  • Mac Studio M4 Max
  • Maximum API rate limits

Need a custom configuration? Use our configurator →

<1 min
Average deploy time
99.9%
Uptime SLA
24/7
Support included
$0
Setup fees

Compare all features

Every plan includes dedicated hardware, pre-installed AI stacks, and full macOS access.

Starter

$119/mo
Max model size14B
Active deployments1
OpenAI-compatible API
Catalog access
Requests/min60
Tokens/min50k
Concurrent requests4
RAM16 GB
Storage512 GB
Dedicated hardware
SSH & VNC access
Uptime SLA99.9%
Support channelEmail
Response time24h

Standard

$239/mo
Max model size32B
Active deployments2
OpenAI-compatible API
Catalog access
Requests/min150
Tokens/min150k
Concurrent requests8
RAM32 GB
Storage512 GB
Dedicated hardware
SSH & VNC access
Uptime SLA99.9%
Support channelEmail
Response time12h

Advanced

$479/mo
Max model size70B Q4
Active deployments3
OpenAI-compatible API
Catalog access
Requests/min300
Tokens/min400k
Concurrent requests16
RAM64 GB
Storage1 TB
Dedicated hardware
SSH & VNC access
Uptime SLA99.9%
Support channelPriority
Response time4h
Priority provisioning

Pro

$959/mo
Max model size70B FP16
Active deployments5
OpenAI-compatible API
Catalog access
Requests/min600
Tokens/min1M
Concurrent requests32
RAM96 GB
Storage2 TB
Dedicated hardware
SSH & VNC access
Uptime SLA99.9%
Support channelDedicated
Response time1h
Priority provisioning
Dedicated ML engineer

Max

$1599/mo
Max model size120B+
Active deployments5
OpenAI-compatible API
Catalog access
Requests/min1,200
Tokens/min2M
Concurrent requests64
RAM128 GB
Storage4 TB
Dedicated hardware
SSH & VNC access
Uptime SLA99.9%
Support channelDedicated
Response time1h
Priority provisioning
Dedicated ML engineer

Pricing FAQ

Common questions about billing and plans.

Yes! You can change your plan at any time. Upgrades take effect immediately with prorated billing. Downgrades take effect at the next billing cycle.

MacYou does not offer a free trial or refunds for unused subscription time. Refunds are available only if we fail to provision your server within 24 hours of payment or if you are charged in error — see our Refund Policy for full details. You can cancel a monthly subscription at any time and keep access until the end of the current billing period.

We support monthly and annual billing. Annual plans save 20% versus monthly. We also offer hourly and daily billing for short-term workloads via the configurator.

Teams with 5+ active deployments qualify for volume pricing. Contact [email protected] for custom enterprise quotes with dedicated support.

MacYou accepts major credit and debit cards through our payment processor. The exact options available are shown at checkout. Annual plans may be paid by wire transfer on request to [email protected].

Absolutely. Use our configurator to choose your chip, RAM (16–128 GB), storage (256 GB – 8 TB), and add-ons. Custom configs are priced dynamically based on your needs.

Ready to deploy?

Start with any plan and scale as you grow. Upgrade, downgrade, or cancel at any time — no lock-in, no penalties.