Local gateway
Free
$0Free download
Download Nexus and run the local gateway on your machine.
- Free desktop download
- Unlimited gateway requests
- 1 managed machine
- Local gateway for approved apps
- Provider model catalog
- Basic local usage visibility
Pricing
Free to start. Pro and Enterprise when you need shared control.
Nexus is available as a free download. Pro and Enterprise add managed scale, protection controls, logging, and team governance.
Pro editionRecommended
Pro
$9.99per month
$99/yearSave $20.88 with annual billing
Managed Nexus control for advanced access, protection, and observability.
- Unlimited gateway requests
- 3 managed machines
- Load balancer and fallbacks
- PII detection, key blocking, additional guardrails, and basic logging
Enterprise edition
Enterprise
Starts at $499per month
Starts at $4,999/yearSave $989+ with annual billing
Enterprise controls for larger teams, stricter environments, and managed deployments.
- Unlimited gateway requests
- Starting at 125 managed machines
- Teams/RBAC, rate limits, SSO, and priority support
- Cluster, air-gapped support, and team/user logging
| Feature / Attribute | Free | Pro | Enterprise |
|---|---|---|---|
| Usage & Billing | |||
| Gateway Requests | Unlimited | Unlimited | Unlimited |
| Managed machines | 1 | 3 | Starting at 125 included |
| Administration | |||
| Desktop Console | |||
| Cloud console | - | ||
| Teams / RBAC | - | - | |
| Team / User rate limit | - | - | |
| Single Sign-On (SSO) | - | - | |
| Routing & Safety | |||
| Smart Routes | Limited | ||
| Load Balancer | - | ||
| Cluster | - | - | |
| Fallbacks | - | ||
| Logging & Support | |||
| Basic logging | |||
| Team/User logging | - | - | |
| Priority Support | - | - | |
Pricing FAQs
How Nexus capacity is counted.
What is a Managed Machine?
The number of machines or inference runtimes registered with Nexus to provide model inference, such as employee Macs, Mac Studios, or centralized servers.
Do client devices count as managed machines?
Client devices do not automatically count as managed machines. A laptop simply consuming inference from a central server is a client; it only counts as a managed machine if it also provides inference through Nexus.
How are people and AI workloads counted?
Humans and AI workloads are treated equally. A client can be a person, AI agent, application, workflow, or service.
What determines plan capacity?
Published plan capacity is based on the number of managed machines registered with Nexus.
Does Nexus charge by token or gateway request?
No. Nexus does not charge based on the number of tokens processed and has no gateway request limits, so heavy AI usage does not create per-request fees or overages.
What deployment sizes does Nexus support?
Nexus is designed for local and centralized AI. A deployment can range from a few shared inference servers to hundreds or thousands of employee devices contributing local inference.
Does on-prem work the same way?
Yes. Capacity can be enforced locally, allowing Nexus to support private and air-gapped environments without requiring usage telemetry to Msty.