Scientific AI PlatformBeta
Host your model

Want your model here?

If a model you rely on is missing, or you have built one your community should be able to use, Nebius can add it to the platform and run it for you.

What you stop worrying about

We package, host and operate the model behind the same consistent service as every model on the platform. Your team keeps ownership of the science.

  • GPUs

    No sourcing, reserving or right-sizing accelerators for a model your team uses a few hours a week.

  • Infrastructure

    No servers to patch, containers to harden or serving stacks to keep current with the model.

  • Scaling

    Peaks during a campaign and quiet weeks between them are handled for you.

  • Demand prediction

    You do not need to forecast usage months ahead to justify hardware.

  • Long contracts

    Use the model through the same Beta terms as every other model here, with no infrastructure commitment.

How it works

  1. Tell us about the model. Name or link, modality, licence and how you expect to use it.
  2. We review feasibility. Licensing, resource needs and fit with the Beta are checked by the Nebius team.
  3. We propose a plan. You get a clear proposal for hosting, a billing unit and a timeline. Nothing is automatic.
  4. Your model goes live. It appears in the live catalog with the same access, keys and MCP tooling as every other model.

Please do not include patient data, credentials, confidential materials or proprietary model weights in this form.

Tell us about your model

Tell us what you want to run. We will review technical feasibility, licensing and available beta capacity with you before agreeing an onboarding plan.

Fields marked required are mandatory.

We reply to this address.

A public repository, paper or model card is ideal.

Roughly how often and how much you expect to run it.

We use your details to review your hosting inquiry and contact you about next steps. Submitting an inquiry does not automatically approve a deployment. See our Privacy Notice for how we handle your information. Your request is delivered by email through Resend to the Nebius team.

Please do not include patient data, credentials, confidential materials or proprietary model weights in this form.

Requests are reviewed by the Nebius team. API keys are issued manually after approval and onboarding.

FAQ

Hosting questions

Are there usage limits?

Beta capacity is shared and bounded. Billing units describe how usage is measured; request limits vary by model. We do not offer an SLA during Beta; if you need committed throughput, tell us in your request and we will discuss options.

Can Nebius host our own model?

Often, yes. Use the Host your model form to tell us about the model, its licence and expected usage. We will review feasibility and come back with a proposal. We do not accept confidential weights or sensitive data through the form itself.

What data should I use during the beta?

We recommend starting with public, synthetic or non-sensitive research data. If your evaluation requires personal data, patient information or confidential datasets, discuss this with us during onboarding before uploading them. Authorised platform operators can access uploaded data and request logs for support and troubleshooting.

What should I not send?

Please do not include patient data, credentials, confidential materials or proprietary model weights in this form. Describe your use case without including the sensitive material so we can discuss appropriate arrangements first.