NeuronCluster
Pricing

License the platform. Own the infrastructure.

No metered per-token bills. NeuronCluster is licensed per deployment, so your costs stay predictable as usage grows.

Starter

Self-hosted

For teams piloting private inference on a single site.

Contact sales
  • Central Management Hub
  • Up to 2 gateways
  • Unlimited compute nodes on your hardware
  • REST, gRPC & WebSocket APIs
  • Community support
Most popular

Business

Custom

For organizations scaling inference across teams and regions.

Talk to sales
  • Everything in Starter
  • Multi-region gateways & subnets
  • Role-based access control
  • Audit logging & observability
  • Priority support & onboarding

Enterprise

Custom

For regulated, air-gapped and mission-critical deployments.

Book a demo
  • Everything in Business
  • Air-gapped & on-prem deployment
  • SSO / SCIM & custom RBAC
  • Dedicated solutions architect
  • Custom SLAs & 24/7 support
FAQ

Common questions

How is NeuronCluster priced?

By deployment, not by token. Licensing scales with the scope of your environment - number of gateways, regions and support level - rather than usage volume. You provide the hardware.

Do you ever see our data?

No. NeuronCluster runs entirely on your infrastructure. Prompts, inputs and outputs never leave your network, and the platform can run fully air-gapped.

What hardware do we need?

Compute nodes run on standard GPUs or CPUs you already operate. The hub and gateways are lightweight services. We'll help size a deployment during onboarding.

Which models are supported?

Any model you can package as TorchScript, ONNX or Safetensors - LLMs, vision, audio, embeddings, classical ML or your own fine-tunes.

Can we start small and scale up?

Yes. Begin with a single-site Starter deployment and grow into multi-region gateways, RBAC and air-gapped operation as your needs evolve.

What support is included?

Starter includes community support; Business adds priority support and onboarding; Enterprise includes a dedicated solutions architect, custom SLAs and 24/7 coverage.

Bring inference in-house

See how NeuronCluster runs your models on your infrastructure - with the control, economics and compliance posture your organization needs.