Model VaultEncrypted Vault

Supported Models

Architecture

Model Vault Encrypted runs on the same isolated, single-tenant, Cohere-managed architecture as a Standard Vault, 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 and Confidential Computing Primer.

For how data is protected in transit, at rest, and in use, and how Zero Data Retention (ZDR) is handled, see Encryption & Key Management.

Supported models

Encrypted Vaults support the following model families:

Model familyType
EmbedEmbeddings
RerankReranker
CompassEmbed + Rerank + Vision Parser bundle
North Mini CodeGenerative (code)
Cohere TranscribeSpeech recognition (ASR)
Customized Cohere modelsVaries

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. To confirm availability for a specific model, check the model dropdown when 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.