Features

  • High performance global network

    High performance global network

    Every deploy is made to a network of data centers running V8 isolates. Your code is powered by Cloudflare's network which is milliseconds away from virtually every Internet user.

  • Automatic scaling

    Automatic scaling

    Forget about auto-scaling, load balancers, or paying for capacity you don't use. Queries automatically routed and load balanced across thousands of servers with global replication and high availability.

  • Instant indexing

    Instant indexing

    Vectors become available immediately for search. Upload your vectors in batches of up to 100MiB with no concurrency limits.

Pricing

  • Select the dimensionality of your vector space. Partitions can have different dimensions. Learn more.

  • Free plan

    10,000 queries per day
    (Across all of your partitions, UTC+0)

    • 100k vectors per partition
    • 10 active partitions
    • Storage for 200k vectors with global replication
    • Runs on 285+ network locations
    • Within 50ms from 95% of the world's internet population

    Note: Inactive partitions are deleted after 7 days.

  • Paid plan

    Starting at $15/month

    • Unlimited queries per day
    • 100k vectors per partition
    • Unlimited active partitions
    Includes monthly usage:
    • 1 million queries, then $5/million
    • Storage for 5.0m vectors, then $1/million

FAQ

What is a partition?

Vectors are stored in partitions to provide a consistent query performance, no matter the amount of concurrent requests. One query scans exactly one partition but you are free to query multiple partitions concurrently and then aggregate the results. This approach guarantees virtually limitless scalability.

What is a vector database?

A vector database is a type of database that stores data as high-dimensional vectors, which are mathematical representations of features or attributes. Each vector has a certain number of dimensions, which can range from tens to thousands, depending on the complexity and granularity of the data.