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

# Workspace Settings

> Configure workspace-level options in the dashboard.

The **Settings** page contains workspace-level configuration that applies to all traffic passing through the workspace.

## General

* **Workspace Name** — The display name for this environment.
* **Workspace ID** — The internal UUID used to identify this workspace in logs and routing.

## Data & Privacy

* **Data Retention** — When enabled, the gateway stores the full prompt and response text for every request. When disabled, only metadata (tokens, cost, latency) is stored. Toggle this based on your compliance requirements.

## Caching

* **Semantic Cache** — Enable or disable the gateway's semantic cache for this workspace. When enabled, semantically similar prompts are served from cache instead of hitting the upstream provider, reducing cost and latency.

## Providers

* Navigate to **Providers** under Settings to add your API keys for OpenAI, Anthropic, Google, xAI, Groq, and Together AI. These are your **Bring Your Own Key (BYOK)** credentials. All keys are encrypted at rest.

## Webhooks

* Navigate to **Webhooks** under Settings to configure endpoint URLs that receive real-time notifications for gateway events. See [Alerts & Webhooks](/docs/alerts) for the full event reference.

## IP Allowlist

* You can restrict gateway access to specific IP addresses or CIDR ranges by configuring the **IP Allowlist**. When enabled, requests from unlisted IPs are rejected before authentication.