# Supported Models

## Architecture

Model Vault Encrypted runs on the same isolated, single-tenant, Cohere-managed architecture as a
[Standard Vault](/guides/model-vault-standard-overview), and adds on top:

- **Confidential computing**: inference runs inside hardware-backed trusted execution environments (a confidential VM such as Intel TDX or AMD SEV-SNP on the CPU, and an NVIDIA GPU in confidential-computing mode), so data stays protected **in use**, not just in transit and at rest. See the [Security Model](/guides/model-vault-encrypted-security-model) and [Confidential Computing Primer](/guides/model-vault-encrypted-confidential-computing).

:::callout{intent="note"}
For how data is protected in transit, at rest, and in use, and how Zero Data Retention (ZDR) is
handled, see [Encryption & Key Management](/guides/model-vault-encrypted-encryption-key-management).
:::

## Supported models

Encrypted Vaults support the following model families:

| Model family             | Type                          |
| ------------------------ | ----------------------------- |
| Embed                    | Embeddings                    |
| Rerank                   | Reranker                      |
| Parse                    | Vision parser                 |
| Compass                  | Embed + Rerank + Parse bundle |
| North Mini Code          | Generative (code)             |
| Cohere Transcribe        | Speech recognition (ASR)      |
| Customized Cohere models | Varies                        |

The families above are what we support in the Model Vault Encrypted **beta**, and we are expanding this
support over time, so availability can differ from a
[Standard Vault](/guides/model-vault-standard-supported-models). To confirm availability for a specific
model, check the model dropdown when [creating a vault](/guides/model-vault-creating-a-vault) with the
Encrypted option selected, or contact Cohere.

## Supported GPUs

Encrypted Vaults run on confidential-computing-capable NVIDIA GPUs. To confirm the
options available for your model, capacity, and region, contact Cohere.

For pricing per model and performance tier, see
[Model Vault Encrypted Pricing](/guides/model-vault-encrypted-pricing).

## Related pages

- [Creating a Vault](/guides/model-vault-creating-a-vault)
- [Standard Vault supported models](/guides/model-vault-standard-supported-models)
- [Security Model](/guides/model-vault-encrypted-security-model)

## Related pages

- [Encrypted Vault Overview](./model-vault-encrypted-overview.md)
- [Calling an Encrypted Vault over the API](./model-vault-encrypted-api-usage.md)
- [Security](./model-vault-security.md)
- [Model Vault Encrypted Pricing](./model-vault-encrypted-pricing.md)
- [Frequently Asked Questions About Model Vault Encrypted](./model-vault-encrypted-faq.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.