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 has two components:

1. Cluster compute and storage, billed per hour for as long as the cluster exists.
2. Embedding token consumption, billed through the existing DigitalOcean AI Platform Serverless Inference rate card when you use DigitalOcean-hosted embedding models.

OpenSearch and PostgreSQL reuse the existing Managed Databases pricing unchanged. Adding vector workloads to those engines does not introduce a surcharge. Weaviate is a new engine with its own SKU ladder.

Weaviate Pricing

Embedding storage is covered by the cluster disk allocation shown above. There is no separate vector storage fee.

OpenSearch Pricing

OpenSearch Vector Database clusters are billed at the existing OpenSearch Managed Database rates. Enabling k-NN, ML Commons, or Neural Search does not change pricing.

PostgreSQL Pricing

PostgreSQL Vector Database clusters are billed at the existing PostgreSQL Managed Database rates. Enabling the vector or vectorscale extensions does not change pricing.

Embedding Token Billing

Embedding tokens are billed through the existing DigitalOcean AI Platform Serverless Inference rate card. Charges apply at indexing time (document-to-vector conversion) and at query time (when the query text is embedded). Rates vary by model size.

For the current rate card, see Foundation Model Usage.

If you use a third-party embedding provider (for example, OpenAI or Cohere), embedding costs are billed by that provider directly and do not appear on your DigitalOcean invoice.