Self-host models with AIP

Self-hosting models with AIP is a Beta feature. Functionality may change during active development.

You can self-host models by backing a registered model with a compute module. Self-hosting allows you to run open-source or custom large language models on your own infrastructure and use them as first-class models in AIP. This is useful when you need:

  • Data sovereignty: Keep all inference traffic within your own network boundary.
  • On-premise or air-gapped deployments: Run models without any external connectivity.
  • Cost control: Use your own GPUs instead of paying per-token for hosted providers.
  • Early access to new models: Deploy newly released open-source models before they are available through a hosted provider.

Prerequisites

Before you begin, review the general prerequisites and registration steps for models backed by compute modules.

How to self-host a model with AIP

  1. Build a container image running an inference server (such as vLLM or Ollama) that serves your model weights and exposes a supported provider API format.
  2. Set the application.port label in your Dockerfile and publish the image to Artifacts. For general container guidance, review the compute modules containers documentation.
  3. Create a compute module with the published image. Set minimum replicas to at least one.
  4. Register the model in Control Panel and configure capabilities.
  5. Select the model in any supported AIP application.