Msty Nexus
Open web app

Connect AI apps to local and online models.

Connect AI apps to local and online models, choose which MCP tools they can use, and review usage in one place.

Open web app

Manage models, access and usage in one place.

Use Nexus to connect your apps to the models you choose. Set model access, manage app tokens, review requests and usage, and add routing and protection controls when you need them.

Abstract access gateway approving business AI app and model connections.

Control AI access

Reduce shadow IT by giving your business one governed place to approve apps, providers, keys, and model access.

Abstract local AI server protected by a privacy boundary with optional cloud access.

Run local models

Keep sensitive data private and secure on local infrastructure, while still using online models when the job needs them.

Abstract layered guardrails filtering requests before they reach model infrastructure.

Add guardrails

Apply extra protections like scoped tokens, PII redaction, key blocking, and routing rules before requests reach models.

Connect apps through Nexus.

Nexus gives teams and power users one place to connect AI models and MCP tools, protect sensitive data with guardrails, and keep provider credentials out of every application.

01

Connect models and MCP tools

Bring local runtimes, hosted providers, and MCP servers into one Nexus-managed gateway.

02

Set presets, routes, and guardrails

Standardize model settings and apply Data Protection, PII redaction, key blocking, and routing rules before requests reach models.

03

Scope access per application

Give each client token only the models and MCP tools it needs, with allow, ask, or block policies for tool calls.

04

Route, protect, and monitor

Nexus routes inference, applies configured protections, and records model and tool activity without exposing provider credentials.

Msty Nexus machine dashboard showing providers, runtimes, models, system metrics, and local inference status

Route, balance, and scale model work.

Nexus is more than a gateway. It can choose the right model path, distribute traffic, and coordinate inference capacity so every request does not land on the most expensive model.

Abstract gateway routing one request to multiple model destinations.

Dynamic model routing

Send each request to the right model for the job. Keep expensive models for work that needs them, and route routine tasks to cheaper or local models to reduce token costs.

Abstract gateway distributing request streams across multiple runtime nodes.

Load balancing

Distribute requests across available runtimes and machines so teams can keep throughput steady without pointing every app at one overloaded endpoint.

Abstract cluster of machines connected to a shared inference gateway.

Clustered inference

Coordinate multiple machines as shared inference capacity for larger local workloads, central servers, or teams that need more horsepower behind the gateway.

Models, tools and access controls.

Use Nexus as the operating layer for local runtimes, hosted providers, governed app access, and practical usage visibility.

Model gateway

Give applications one governed catalog across local runtimes and hosted providers, including AWS Bedrock and Azure AI.

MCP tools gateway

Connect tool integrations through Nexus so approved clients can discover and call tools with scoped permissions, approvals, and activity logging.

Credential control

Keep provider credentials in one controlled place instead of copying them across tools.

Compatible endpoints

Connect approved applications through familiar OpenAI- and Anthropic-compatible endpoints.

Runtime control

Manage supported Ollama, llama.cpp, and MLX runtimes alongside hosted model access.

App tokens

Issue scoped tokens per application instead of sharing one master key across every integration.

Usage visibility

See requests, latency, and usage by application and provider from one place.

Model testing and benchmarks

Chat with models, presets, routes, and load-balanced paths from inside Nexus, then benchmark performance before routing production traffic.

Connection approvals

Review and approve new model or provider connections before applications can use them.

Network boundary

Keep the gateway off the LAN by default and open access only when you choose to.

Connect device, server and online models.

Run Nexus across your team’s macOS, Windows, and Linux devices, operate your shared models on private infrastructure, and reach approved cloud providers through a protected route only when your work calls for them.

Explore Enterprise deployments
Msty Nexus connecting employee devices and private inference infrastructure directly to Nexus, with optional cloud access behind a separate security gateway

On-device AI

Runtime for macOS, Windows & Linux

Private AI infrastructure

Runtime + Console on private infrastructure

Cloud AI

Approved external providers

Compare Nexus Free, Pro and Enterprise.

Nexus is available as a free download. Pro and Enterprise add managed scale, protection controls, logging, and team governance.

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
Enterprise edition

Enterprise

Custom pricingContact sales for a tailored quote

Shared controls for small teams through larger enterprises, stricter environments, and managed deployments.

  • Unlimited gateway requests
  • Starting at 25 managed machines
  • Starting at 25 client tokens
  • Cross-platform runtime for macOS, Windows, and Linux
  • Teams/RBAC, rate limits, SSO, and priority support
  • MDM deployment support for AI governance
  • Cluster, air-gapped support, and team/user logging
Feature / AttributeFreeProEnterprise
Usage & Billing
Gateway RequestsUnlimitedUnlimitedUnlimited
Managed machines13Starting at 25 included
Client tokens1020Starting at 25 included
Deployment
Operating systemsmacOS, Windows & LinuxmacOS, Windows & LinuxmacOS, Windows & Linux
AWS Bedrock & Azure AI providersNot includedIncludedIncluded
Administration
Desktop ConsoleIncludedIncludedIncluded
Cloud consoleNot includedIncludedIncluded
Teams / RBACNot includedNot includedIncluded
Team / User rate limitNot includedNot includedIncluded
Single Sign-On (SSO)Not includedNot includedIncluded
MDM deployment & AI governanceNot includedNot includedIncluded
Routing & Safety
Data ProtectionNot includedIncludedIncluded
GuardrailsNot includedLocal policiesOrganization-wide policies
Smart Routes3IncludedIncluded
Load BalancerNot includedIncludedIncluded
MCP tools gatewayAllow or block all toolsTool profiles and rulesTeam tool profiles
ClusterNot includedNot includedIncluded
FallbacksNot includedIncludedIncluded
Logging & Support
Basic loggingIncludedIncludedIncluded
Team/User loggingNot includedNot includedIncluded
Priority SupportNot includedNot includedIncluded