One subscription.
Unlimited local AI.
Every plan includes full on-device inference with Gemma 3. Cloud tiers add frontier models through our zero-knowledge pipeline.
Pricing announced at launch. Join the early access list to be notified.
System Requirements
macOS
- Apple Silicon (M1 or later)
- 16 GB unified memory minimum (32 GB recommended)
- macOS 14 Sonoma or later
- ~8 GB free storage
Simple, transparent pricing.
All prices in Canadian dollars. Processed securely by Paddle.
Enterprise
Tailored for teams and multi-seat deployments.
- Everything in Professional
- Multi-seat licensing
- Custom cloud credit allocation
- Priority queue processing
- Dedicated account support
- Volume pricing available
Professional
Maximum capability for demanding professional work.
Less than 10 minutes of billable time per month.
- Full local AI inference (Gemma 3 27B)
- Expanded cloud credit allocation
- All cloud models including Claude Opus
- Priority cloud processing
- Advanced document analysis
- Early access to new features
- PII scrubbing pipeline
- Hardware-backed encryption
- Full audit logging
Essentials
Full AI for everyday professional work.
Less than 6 minutes of billable time per month.
- Full local AI inference (Gemma 3 12B)
- Standard cloud credit allocation
- Standard cloud models
- PII scrubbing pipeline
- Hardware-backed encryption
- Full audit logging
14-day free trial. No credit card required.
Why does the app connect to the internet?
If you use a firewall tool like Little Snitch, you may see Ferox Nodus making an outbound connection. Here is exactly what that connection is:
-
License validation via Paddle (our payment processor)
Verifies your subscription is active. No document data is transmitted.
-
Cloud escalation (optional, consent-gated)
Only when you explicitly choose to use a cloud model. PII-scrubbed data only, routed via Canadian relay.
-
No telemetry, ever
Ferox Nodus does not send usage data, crash reports, or analytics to our servers.
Frequently Asked Questions
What happens when I run out of credits?
Local inference continues working with no limits. Cloud features pause until your monthly reset or you purchase a top-up pack. Details at launch.
Do advanced models cost more credits?
Yes. Standard models (Haiku-class) use 1 credit per query. Advanced models like Opus use proportionally more. We display your credit balance as a percentage bar for easy tracking.
What data goes to the cloud?
Only scrubbed queries — after names, addresses, IDs, and other PII have been replaced with synthetic tokens. Raw data never leaves your device.
Can I use Nodus entirely offline?
Yes. Local inference with Gemma 3 works fully offline after the initial model download. Cloud features require internet.
Get started in
under two minutes.
Ferox Nodus is launching soon. Join the early access list to be first in line.
No spam. Unsubscribe anytime.
Install
Download and install on macOS or Windows.
Download Model
Gemma 3 12B downloads on first launch (~7 GB).
First Query
Start chatting — everything runs locally.