For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

DigitalOcean Vector Databases pricing includes two components:

1. Cluster compute and storage, billed hourly while the cluster exists.
2. Embedding token usage, billed through serverless inference pricing when you use DigitalOcean-hosted embeddings models.

Cluster Compute and Storage

OpenSearch and PostgreSQL Vector Database clusters use existing Managed Databases pricing, with no vector workload surcharge:

• OpenSearch clusters are billed at OpenSearch Managed Database rates, and enabling k-NN, ML Commons, or Neural Search doesn’t change pricing.
• PostgreSQL clusters are billed at PostgreSQL Managed Database rates, and enabling the vector or vectorscale extensions doesn’t change pricing.

Weaviate public

Weaviate is in public preview. The pricing below reflects current public preview rates and is subject to change before general availability.

The cluster disk allocation includes embedding storage. There is no separate vector storage fee.

Embeddings Token Usage

Embeddings tokens are billed at the existing serverless inference rates. Charges apply when documents are converted to vectors during indexing and when query text is embedded during search. Rates vary by model and size.

If you use a third-party embeddings model provider, such as OpenAI or Cohere, that provider bills embedding costs directly. These charges don’t appear on your DigitalOcean invoice.