Blog
Zilliz Cloud Latest Update: A Game-Changer Bringing Elite Performance within Reach of All Developers

Zilliz Cloud Latest Update: A Game-Changer Bringing Elite Performance within Reach of All Developers

Jun 14, 20234 min read

Zilliz Cloud has just released a game-changing update for developers looking to implement generative AI applications. It introduces many new features and much more affordable pricing options, making it accessible to all developers regardless of budget. This update is a significant milestone for Zilliz Cloud in its mission to provide the most advanced and user-friendly vector database solutions in the market. This blog explores these new features and how they can benefit developers and organizations.

Introducing a free tier that makes the vector database service accessible to all

Zilliz Cloud's latest release now includes a free tier option, enabling users to explore our services without financial commitment. The free tier offers up to two collections, each of which can handle up to 500,000 vectors with 768 dimensions and even more if on a smaller dimensional scale. This generous capacity empowers users with substantial data-handling capabilities without requiring extensive infrastructure investments.

Drastic price reductions and more affordable options

Zilliz Cloud's latest release delivers various pricing options, catering to a wide range of requirements: Starter, Standard, Enterprise, and Self-hosted plans. Each plan meticulously balances cost, performance, service quality, and compliance, ensuring every user can find a tailored solution that meets their needs.

Starter Plan: The Starter Plan is a free tier available on GCP, perfect for hobbyists or developers who want to experiment with Zilliz Cloud. No credit card is required, and minimal configuration is needed.
Standard Plan: We designed the Standard Plan for small teams with less than five engineers and less complex workloads. This option is available on both AWS and GCP. By choosing this pricing plan, users can start with $100 worth of credits and have the opportunity to earn up to $200 worth of credits in total.
Enterprise Plan: We designed the Enterprise Plan for large-scale organizations with advanced security and enterprise support requirements. It is available on both AWS and GCP.
Self-hosted Plan: This plan allows users to deploy our vector database services on their Virtual Private Cloud (VPC), providing complete control. It is an ideal option for businesses prioritizing privacy, data security, and regulatory compliance.

For more details, see the pricing page.

Best value for money with a new cost-optimized CU

Zilliz Cloud's latest release introduces a groundbreaking addition to its compute unit (CU) lineup: the Cost-Optimized CU. This new offering provides the same storage capacity as the existing Capacity-Optimized CU, accommodating approximately 5,000,000 vectors with 768 dimensions. However, it costs about 30% less, enabling users to handle large datasets with a high-quality vector database for their applications at an affordable price. The Cost-Optimized CU is most suitable for users with limited budgets who may not require demanding latency or query throughput but still seek top-tier solutions.

Enhanced access control and streamlined collaboration with the Organizations and Roles feature

Zilliz Cloud's new Organizations and Roles feature enables users to manage team access and permissions easier. This major update is underpinned by Role-Based Access Control (RBAC), which provides fine-grained control over resource accessibility. By leveraging this new feature, users can ensure optimum security and flexibility in their collaborative workflows.

This feature is ideal for large organizations with multiple projects and team members who require access to Zilliz Cloud's vector database services.

Accelerated filtering with Partition Key

Zilliz Cloud now offers a Partition Key feature, allowing users to assign a specific field as a partition key when creating a collection. Zilliz Cloud then stores entities in a partition based on values in this designated partition key field.

This Partition Key feature is particularly beneficial during query filtering, as executing conditions on the partition key field is faster than traditional scan-based filtering methods.

Elevated data management and querying potential with the JSON Type Support feature

Zilliz Cloud now supports JSON data types, enabling users to seamlessly store and manage JSON data alongside the existing Approximate Nearest Neighbor (ANN) Search capabilities. This innovative combination opens up endless possibilities for complex querying and data manipulation.

Dynamic schema support

Zilliz Cloud now supports Dynamic Schema. This new feature allows users to insert entities with dynamically varied fields into a collection rather than being limited to a predefined static schema.

A new benchmark tool: unveiling a new standard for vector database comparison

Zilliz Cloud's latest release introduces VectorDBBench, a new open-source benchmark tool, allowing users to measure the performance of our cutting-edge solutions, Milvus or Zilliz Cloud, against other offerings available in the market with your data.

With comprehensive performance metrics and robust evaluation capabilities, users can make data-driven choices that align perfectly with their requirements.

For more detailed information about all new features, see our release notes.

Getting started with Zilliz Cloud

Start for free with the new Starter Plan!
Or start your 30-day free trial of the Standard plan with $100 worth of credits upon registration and the opportunity to earn up to $200 worth of credits in total.
Dive deeper into the Zilliz Cloud documentation.
Check out the guide on migrating from Milvus to Zilliz Cloud.

Robert Guo
Robert Guo is a Partner and Director of Product Management at Zilliz and one of the architects behind Milvus, an open-source vector database revolutionizing AI data analysis. With a Ph.D. in Computer Software and Theory from Huazhong University of Science and Technology, he has presented influential work at prestigious conferences and journals, including SIGMOD, VLDB, USENIX ATC, ICS, DATE, and IEEE TPDS. Previously a key developer for Huawei's ModelArts platform, Robert is skilled at crafting efficient and scalable AI data solutions.