> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bioptimus.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Deployment overview

> Choose the right way to access Bioptimus models.

Bioptimus models are available three ways. The on-premise and SageMaker options share the same JSON API and are both supported by the [Bioptimus SDK](/guides/get-started/sdk), so your inference code is portable between them.

<CardGroup cols={3}>
  <Card title="AWS & SageMaker" href="/deployment/platforms/aws-sagemaker">
    Managed cloud endpoints from AWS Marketplace. Best for production and scale.
  </Card>

  <Card title="On-premise" href="/deployment/platforms/on-premise">
    Self-hosted container. Best for data residency and air-gapped environments.
  </Card>

  <Card title="Hugging Face" href="/deployment/platforms/hugging-face">
    Direct H-Optimus weights for non-commercial academic research.
  </Card>
</CardGroup>

## Which should I choose?

| Consideration                | AWS & SageMaker                | On-premise             | Hugging Face           |
| ---------------------------- | ------------------------------ | ---------------------- | ---------------------- |
| Time to first inference      | Minutes                        | Moderate (infra setup) | Minutes                |
| Data leaves your environment | Within your AWS account/region | No                     | No                     |
| Commercial use               | Yes                            | Yes                    | **No** — academic only |
| Models                       | H-Optimus, M-Optimus           | H-Optimus, M-Optimus   | H-Optimus only         |
| Best for                     | Cloud-native production        | Regulated / air-gapped | Academic research      |

<Note>
  For data residency and PHI considerations, see [Security & compliance](/documentation/resources/security-compliance).
</Note>