Start free, scale seamlessly.

With Marqo Cloud you can build, deploy and scale end-to-end vector search applications in minutes, without the need to create and maintain complex infrastructure. Just choose your preferred storage and inference types, and how many instances you require. Vector generation, storage and retrieval are handled for you.

Open Source


Administered and managed by you
Get Started with Open Source


  • Plug and play functionality
  • End-to-end vector creation and storage
  • Horizontally scalable
  • Model customisation
  • Apache 2.0 licence
  • Community support


From $86.58/month

Estimated for a 30 day month at $0.1186/hour
Get Started with Cloud


  • All the functionality of open source
  • Fully managed
  • CPU and GPU instances
  • 24/7/365 dedicated support
  • Scale at the click of a button
  • Access control
  • High availability
  • Low latency

Pricing Calculator

When you use Marqo, you are billed on an hourly basis for the resources you use. Usage is rounded up to 15-minute increments.

Choose your storage


Good for small projects, development, and proof of concept applications. Approx. 2M vectors per shard.



Aimed at production applications with large amounts of data where high availability is a requirement. Approx. 16M vectors per shard.



Designed to support high velocity concurrent requests against tens or hundreds of millions of vectors. Approx. 16M vectors per shard.


Choose your inference


Suitable for small applications, development, and proofs of concept.



Suitable for production applications, especially with smaller models.



The fastest available inference, capable of serving high request velocity with large multimodal models and low latency.


Storage Shards
Storage Replicas
Inference Instances

Estimated Total (USD):


Contact Us
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.


What is vector search?

Vector search allows you to search documents, images and other data by converting items into a collection of vectors. This collection of vectors summarises the data in semantic form and allows us not only to match documents against queries through analysis of the semantic content, but also to understand where and how the document matched the query. With Marqo, inference to create the vectors is included.

What is the best setup for my application?

The number of instances you will need depends on a number of factors. The number of documents, the size of the documents and the type of data (image vs text). When dealing with low search volumes that primarily involve text or when low latency is not crucial, using CPU inference nodes can be a cost-effective solution. On the other hand, GPU inference nodes provide a significant performance boost when indexing and searching with images and are recommended for indexing large datasets and processing high volume, low latency searches. For multimodal models marqo.CPU.large is recommended as a minimum.

The estimates for storage capacity provided in our calculator assume your are using a model that produces 768 dim. vectors.

Do I have to change my code to move from open-source to cloud?

The only changes you need to make are to update your URL and API key when accessing Marqo.

How does billing work?

You will be billed at the end of the month for total inference and shard hours used. Usage is rounded up to 15-minute increments.

Ready to get started?

Integrate AI search with your application and easily scale with demand using Marqo cloud.