> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cohere.com/v2/docs/model-vault/standard/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cohere.com/_mcp/server.

# Standard Vault Overview

> Standard Vault is Cohere's managed, single-tenant inference environment with dedicated infrastructure and no confidential-computing layer.

A **Standard Vault** is a Cohere-managed, single-tenant inference environment. You get dedicated
infrastructure with full control over model selection, scaling, and performance monitoring, without
operating the underlying serving stack. Your data is protected in transit and at rest, and Cohere
manages maintenance, deployments, updates, and scaling.

Choose Standard Vault when you want dedicated inference and don't require hardware-backed protection of
data **in use** or verifiable remote attestation. If you do, see
[Encrypted Vaults](../../docs/model-vault/encrypted).

## Deploying and using a Standard Vault

Standard vaults use the shared vault flow:

* [Quickstart](../../docs/model-vault/quickstart)
* [Home Page](../../docs/model-vault/vault-home)
* [Creating a Vault](../../docs/model-vault/creating-a-vault)
* [Managing Vaults](../../docs/model-vault/managing-vaults)
* [Monitoring](../../docs/model-vault/monitoring)
* [Model Vault with North](../../docs/model-vault/model-vault-with-north)

## What's specific to Standard Vault

* [Calling a Vault over the API](../../docs/model-vault/standard/api-access)
* [Supported Models](../../docs/model-vault/standard/supported-models)
* [Pricing](../../docs/model-vault/standard/pricing)

## Architecture

These are a Standard Vault's core architectural components:

* **Logically isolated**: Isolates all infrastructure components, including the network load balancer, reverse proxy, serving middleware, inference servers, and GPU accelerators.
* **Minimal shared components**: Shared infrastructure is limited to authentication and underlying Kubernetes/compute resources (nodes, CPU, and memory).
* **Cohere-managed operations**: Cohere handles maintenance, deployments, updates, and scaling.

> **Warning**
>
> When Zero Data Retention (ZDR) is enabled for a Standard Vault (Standalone) deployment, Cohere
> processes inputs and outputs for inference but does not retain any prompts or responses.

> Cohere's API documentation helps developers easily integrate natural language processing and generation into their products.