# Create a cluster

[Weaviate Cloud (WCD)](/go/console?utm_content=cloud) provides two cluster types.

- **[Free clusters](#free-clusters)**: Free clusters are free forever and need no credit card, which makes them the easiest way to get started. They are perfect for learning, hobby projects, and small workloads, and you can upgrade to a paid plan at any time without losing your data. For the current free tier limits, see the [pricing page](https://weaviate.io/pricing).
- **[Shared Cloud clusters](#shared-cloud-clusters)**: Shared Cloud clusters are robust, paid clusters designed for production use.

When you log into the Weaviate Cloud web console, the `Clusters` panel lists your clusters. There are no clusters when you log in to a new account.

## Free clusters

Free clusters are the easiest way to start building with Weaviate. They are free forever, need no credit card, and are ideal for learning, hobby projects, and small workloads. Each user can create one free cluster, and you can upgrade to a paid plan at any time without losing your data.

The free tier includes a monthly allowance for the database, [Weaviate Embeddings](../cloud-weaviate-embeddings/overview.md), and the [Query Agent](../agents/overview.md). For the current limits, see the [pricing page](https://weaviate.io/pricing).

[Embedded content embed](https://app.guideflow.com/embed/mk6l470aqk)

:::accordion{title="Steps to create a free cluster"}
To create a free cluster, follow these steps:

1. In the clusters sidebar, click the plus button.
2. Select the `Free` option.
3. Choose a name for your cluster.
4. The [optimization profile](#optimization-profile) is set to `Cost Optimized` for free clusters.
5. Select a cloud provider (GCP by default).
6. Configure the `Advanced configuration` settings if needed (auto schema generation and CORS settings).
7. Click the `Create cluster` button.

#### Advanced cluster configuration

The following advanced configuration settings are available:

- [`Enable auto schema generation`](../reference-configuration/collections.md#auto-schema)
- `Allow all CORS origins`

The [MCP server](../ai-assisted-vibe-coding/configuration-mcp-server.md#weaviate-cloud) is always enabled on Weaviate Cloud clusters. The `Enable MCP Read-Only` switch, which restricts it to its read tools, is off by default (so the write tool is available) and is not part of the free cluster creation form. Set it after creation from the cluster's `Advanced configuration`, no restart needed.
:::

:::callout{intent="note" title="Free cluster lifecycle"}
A free cluster runs for as long as you use it. After **7 days of inactivity**, the cluster is **suspended** and your data is preserved. You can reactivate a suspended cluster from the [Weaviate Cloud console](https://console.weaviate.cloud/).

If a cluster stays inactive, it is permanently deleted after **30 days** of total inactivity (about 23 days after it is suspended). Weaviate sends a warning email **1 day before** the cluster is deleted. To keep a cluster running indefinitely, or to run production workloads, [upgrade to a paid plan](https://weaviate.io/pricing).
:::

## Shared Cloud clusters

Shared Cloud clusters require billing details. Weaviate Cloud prompts you to add billing details if you have not already added them.

[Embedded content embed](https://app.guideflow.com/embed/9r250xgior)

:::accordion{title="Steps to create a Shared Cloud cluster"}
To create a Shared Cloud cluster, follow these steps:

1. In the clusters sidebar, click the plus button.
2. Select the `Shared Cloud` option.
3. Choose a name for your cluster.
4. Select an [optimization profile](#optimization-profile) (`Cost Optimized` or `Performance Optimized`).
5. Select a cloud provider (GCP by default).
6. Select if you need high-availability (enabled by default).
7. Configure the `Advanced configuration` settings if needed (auto schema generation, CORS, and the MCP read-only setting).
8. Click the `Create cluster` button.

#### Advanced configuration for Shared Cloud clusters

The following advanced configuration settings are available:

- [`Enable auto schema generation`](../reference-configuration/collections.md#auto-schema)
- `Allow all CORS origins`
- [`Enable MCP Read-Only`](../ai-assisted-vibe-coding/configuration-mcp-server.md#weaviate-cloud)

The [MCP server](../ai-assisted-vibe-coding/configuration-mcp-server.md#weaviate-cloud) is always enabled on Weaviate Cloud clusters. `Enable MCP Read-Only` is off by default, so the write tool is available. Turn it on to restrict the server to its read tools, on the creation form or at any time after creation without a restart.
:::

## Optimization profile

When you create a cluster, the **Optimization profile** sets the default [vector index](../indexing/vector-index.md) and [compression](../how-to-configure-weaviate/compression.md) for new collections in that cluster. Choose the profile that matches your workload:

- **Cost Optimized**: Uses the **[HFresh](../indexing/vector-index.md#hfresh-index)** vector index for a lower memory footprint and reduced storage costs. Suitable for small or non-latency-sensitive workloads.
- **Performance Optimized**: Uses the **HNSW** vector index for efficient in-memory retrieval that balances speed and search quality. Suitable for most workloads.

The optimization profile only sets the _default_ for new collections. You can still configure the [vector index and compression for each collection](../how-to-manage-collections/vector-config.md) when you create it.

:::callout{intent="note" title="Free clusters"}
Free clusters support the **Cost Optimized** (HFresh) profile only. To use the **Performance Optimized** (HNSW) profile, [upgrade to a paid plan](https://weaviate.io/pricing).
:::

## Authentication

Weaviate Cloud clusters use API key authentication. The authentication approach depends on whether [RBAC (Role-Based Access Control)](../authorization-and-authentication/weaviate-configuration-rbac.md) is enabled:

#### Authentication with RBAC enabled

New clusters with Weaviate version `v1.30` (or later) have RBAC enabled by default. With RBAC enabled, you create API keys with specific roles for granular access control.

When you develop your client application, use an API key to connect your client to the cluster. For detailed instructions on finding and managing your API keys, including creating new keys and managing roles, check out this guide:

- **[Manage clusters: Authentication](authentication.md)**

#### Authentication with RBAC disabled (deprecated)

If RBAC is not enabled (before `v1.30`), clusters use the traditional approach with two default API keys:

- **Admin keys**: Provide read-write access to the database
- **ReadOnly keys**: Provide read-only access to the database

Shared Cloud clusters can create, delete, edit, and rotate API keys, while free clusters cannot modify the default keys.

## Weaviate Database version

When you provision a new cluster, Weaviate Cloud uses the latest version of Weaviate to set up the new cluster. There may be a short delay between the release of a new Weaviate version and its availability in Weaviate Cloud.

Weaviate Cloud automatically updates existing clusters as new Weaviate versions become available.

For more details on Weaviate Cloud versioning, see:

- **[Account management: Server version](../cloud-account-management/version.md)**.

## Number of clusters

Each user can create one (1) free cluster. By default, an organization can have up to six (6) Shared Cloud clusters at the same time. To change these limits, [contact support](https://support.weaviate.io).

## Support

If you use **Weaviate Cloud** (Database cluster(s) or Weaviate product in the cloud) or have a self-hosted support package, open a ticket in the [Support Portal](https://support.weaviate.io) or email [Weaviate support](mailto\:support@weaviate.io) directly. To add a [support plan](https://weaviate.io/support-plans), contact [Weaviate sales](https://weaviate.io/pricing#contact-sales).

Use the **Support Portal** for direct help from the Weaviate team: open and track tickets, and we'll respond in line with your support plan. The **Community Forum** is open to everyone, and a great place to ask questions, get help with your cluster, and connect with other developers. For all the ways to get help, see the [Support overview](../support/overview.md).

::::card-grid
:::card{title="Weaviate Support Portal" href="https://support.weaviate.io" icon="headset"}
Direct help from the Weaviate team for Weaviate Cloud. Open and track tickets in the **Support Portal**.
:::

:::card{title="Weaviate Community Forum" href="https://forum.weaviate.io/c/support" icon="messages-square"}
Ask questions, share ideas, and connect with other developers on our **Community forum**.
:::
::::

## Related pages

- [Agents](./agents-index.md)
- [AI-assisted Weaviate code generation](./ai-assisted-vibe-coding-index.md)
- [APIs](./apis-index.md)
- [Authorization and authentication](./authorization-and-authentication-index.md)
- [Benchmarks](./benchmarks-index.md)
- [Best practices](./best-practices-index.md)
- [Client libraries](./clients-index.md)
- [Client Libraries / SDKs](./client-libraries-index.md)
- [Cloud](./cloud-index.md)
- [Cloud account management](./cloud-account-management-index.md)

# Agent Instructions

This portal answers questions programmatically. To receive a synthesized,
source-cited answer instead of crawling page by page, append the `?ask=`
query parameter to any page URL on this site:

    /guides/quickstart?ask=how+do+I+authenticate

Optional parameters:

- `&goal=<what-you-are-trying-to-do>` steers the answer toward your
  objective (e.g. `&goal=write+a+python+client`).
- `&version=<label>` scopes the answer to a mounted version when the
  portal publishes more than one.

The response is `text/markdown`: the answer followed by a `# Sources` list
of the portal pages it was grounded in. Status codes are the contract:

- `200` — the answer; `402` — the portal owner’s plan or answer credits are
  exhausted (surface this to your operator; do NOT retry); `429` — you are
  rate-limited; back off for the `Retry-After` seconds; `503` — the answer
  lane is temporarily unavailable; fall back to crawling the `.md` pages.

For the full corpus map read `llms.txt` at the site root; for the tool
surface (search + page fetch as MCP tools) see `/mcp`.
