Skip to content
SPECIFICTION
Get listed

Cloudflare Vectorize

developers.cloudflare.com

Free plan WebAPI
Visit developers.cloudflare.com
Spec score 8.0 #8 of 27 in Vector Databases

What it is

Cloudflare Vectorize is a globally distributed vector database for AI applications built with Cloudflare Workers. It supports semantic search, recommendations, classification, anomaly detection, and supplying context to large language models. Vectors can come from Workers AI models or services such as OpenAI. Workers connect to indexes through a Vectorize binding configured in Wrangler or the Cloudflare dashboard, while a REST API can insert and query vectors. Search results can reference images in R2, documents in KV, and user profiles in D1. Metadata filters support indexed string, number, and boolean properties, with up to 10 metadata indexes per index. Each index can hold up to 20 million vectors, with a maximum of 1,536 dimensions at 32-bit precision. Queries return up to 50 results with values or metadata, or 100 without them. Cloudflare lists a free plan and paid usage from $5/mo. The Workers Free plan includes stated monthly queried and stored dimension allowances. Cloud deployment is available through API and web access.

Spec sheet

Product
Vectorize is a globally distributed vector database for building AI powered applications with Cloudflare Workers.Read 3 Oct 2026 · developers.cloudflare.com
Support
Cloudflare directs Vectorize users to its #vectorize Discord channel for questions, discussion, bug reports, and feedback.Read 3 Oct 2026 · developers.cloudflare.com
Headquarters
San Francisco, California, United StatesRead 28 Sep 2026 · developers.cloudflare.com
Founded
2009Read 28 Sep 2026 · developers.cloudflare.com
Access security
Cloudflare describes Workers bindings as a capability and API, with the underlying secret never exposed to Worker code.Read 3 Oct 2026 · developers.cloudflare.com
API access
Vectorize supports a REST API for operating on indexes, including inserting and querying vectors.Read 3 Oct 2026 · developers.cloudflare.com
Billing
Vectorize does not bill for CPU, memory, active index hours, or the number of indexes, and does not charge for data transfer or egress.Read 3 Oct 2026 · developers.cloudflare.com
Capacity
An index can contain up to 20 million vectors, with a maximum of 1,536 dimensions per vector at 32 bit precision.Read 3 Oct 2026 · developers.cloudflare.com
Cloudflare integrations
Vector search results can reference images in R2, documents in KV, and user profiles in D1.Read 3 Oct 2026 · developers.cloudflare.com
Embeddings
Vectors can come from Workers AI models or be supplied from platforms such as OpenAI.Read 3 Oct 2026 · developers.cloudflare.com
Metadata filtering
Metadata filters support string, number, and boolean indexed properties, with up to 10 metadata indexes per Vectorize index.Read 3 Oct 2026 · developers.cloudflare.com
Query limits
Queries can return up to 50 results with values or metadata, or up to 100 results without them.Read 3 Oct 2026 · developers.cloudflare.com
Use cases
It supports semantic search, recommendations, classification, anomaly detection, and providing context to large language models.Read 3 Oct 2026 · developers.cloudflare.com
Worker access
Workers connect to an index through a Vectorize binding configured in Wrangler or the Cloudflare dashboard.Read 3 Oct 2026 · developers.cloudflare.com

Plans and prices

Workers Free Free Vectorize usage includes 30 million queried vector dimensions per month and 5 million stored vector dimensions. 100 indexes per account · 1,000 namespaces per index Read 3 Oct 2026 · developers.cloudflare.com
Workers Paid Price not published First 50 million queried vector dimensions per month and first 10 million stored vector dimensions included; then $0.01 per million queried dimensions and $0.05 per 100 million stored dimensions. 50,000 indexes per account · 50,000 namespaces per index Read 3 Oct 2026 · developers.cloudflare.com

Every Cloudflare Vectorize plan and price →

Strong points and limits

Strong points

  • Free plan includes monthly vector allowances
  • Supports semantic search and recommendations
  • Indexes hold up to 20 million vectors
  • REST API supports inserting and querying vectors
  • No data transfer or egress charges

Limits

  • Queries with values or metadata return up to 50 results
  • No hybrid search support
  • Sparse vectors are not supported
  • Paid usage starts from $5/mo

Who it suits

It suits developers building AI applications with Cloudflare Workers, especially those needing vector search, recommendations, classification, or model context. API, Go, TypeScript, and Python users can connect to it.

Verdict

Vectorize combines Cloudflare Workers integration with vector search, filtering, and REST access. Its free allowance and stated capacity suit projects that fit the documented limits, while larger or paid workloads need to account for dimension-based charges.

Where Specifiction places it

Alternatives to Cloudflare VectorizeAll alternatives →