Zilliz Cloud
Fully-managed vector database service built on Milvus, designed for speed, scale, and high performance AI applications.
At a Glance
Pricing
Starting point for learning and personal projects
Engagement
Available On
About Zilliz Cloud
Zilliz Cloud is a fully-managed vector database service built by the creators of Milvus, the world's most popular open-source vector database. It simplifies deploying and scaling vector search applications by eliminating the need to construct and maintain complex infrastructure, enabling developers to build AI-powered applications in minutes.
- Easy to Use - No experience required; establish a large-scale vector similarity search service in minutes and focus on business logic instead of operations.
- Optimized Milvus - Built on Milvus with an optimized AUTOINDEX that balances recall and performance, resulting in enhanced efficiency and lower total cost of ownership.
- Blazing Fast Performance - Enables 10x faster vector retrieval speed than standard Milvus with the Cardinal search engine, unparalleled by other vector database systems.
- Highly Scalable - Ideal for large-scale vector data with distributed, high-throughput capabilities; easily scale clusters to 500 CUs serving over 100 billion items.
- High Availability - Offers industry-leading SLAs with 99.95% monthly uptime for all cloud products.
- Security & Governance - Meets SOC2 Type II and ISO27001 standards, supports Role-Based Access Control (RBAC), SSO, and encryption for robust data protection.
- Built-in Embedding Pipelines - Converts unstructured data into searchable vector embeddings, handling data preparation, chunking, model selection, and transformation.
- Multi-Cloud Deployment - Available on AWS, Azure, and GCP across eight regions worldwide.
- AI Integrations - Integrates with leading AI models and frameworks including OpenAI, Anthropic, Cohere, LangChain, LlamaIndex, and more.
To get started, sign up for a free Zilliz Cloud account, grab an official SDK (Python, Java, Go, or Node.js), create your first collection, and conduct vector similarity searches to power your AI application. When ready to launch, upgrade to a pay-as-you-go plan for production workloads.

Community Discussions
Be the first to start a conversation about Zilliz Cloud
Share your experience with Zilliz Cloud, ask questions, or help others learn from your insights.
Pricing
Free Plan Available
Starting point for learning and personal projects
- 5 GB storage
- 2.5M vCUs per month included
- Up to 5 collections
- Shared environment
- Google Cloud provider
30 days
Free trial for Standard and Enterprise plans
- Full access to Standard or Enterprise features
- $200 free credits
Standard Serverless
Managed essentials for non-critical workloads. Best for prototypes and testing environments.
- Fully managed vector databases with core APIs
- Backup, restore, and basic monitoring
- Built-in encryption for data in transit and at rest
- System-managed auto-scaling
- AWS and Google Cloud providers
- Business hours support
Standard Dedicated
Managed essentials for non-critical workloads. Best for prototypes and testing environments.
- Dedicated environment
- Performance-optimized, Capacity-optimized, or Tiered-storage cluster types
- Manual scaling to 32 CUs
- AWS, Google Cloud, Azure providers
- Single availability zone
- Business hours support
Enterprise Dedicated
Enterprise-grade reliability and controls. Best for production applications.
- 99.95% uptime SLA
- Audit logs, SSO (SAML 2.0 based), granular RBAC
- Multi-replica and elastic scaling
- Private endpoint and VPC peering
- Enterprise support included
- Configurable auto-scaling
- Manual scaling to 256 CUs or more
- Multiple availability zones
- 24/7/365 on-call availability
Business Critical
Regulated-ready with maximum resilience. Best for healthcare, finance, and other highly regulated, mission-critical systems.
- Global cluster with high-level availability and disaster recovery
- Advanced security: CMEK and full-path in-transit encryption
- HIPAA-eligible with enhanced data privacy features
- Priority support and rapid incident response
- 99.99% uptime SLA with multi-replica
- Continuous data protection
- Point-in-time recovery (PITR)
- Data masking/tokenization
- 30 min emergency response SLA
Capabilities
Key Features
- Vector similarity search
- Filtered search
- Range search
- Grouping search
- Hybrid search
- Full text search
- Text match
- Query operations
- Data processing
- Cross-cluster migration
- Zero downtime migration
- High speed data import
- Backup and restore
- Snapshot
- Multi-replica support
- Auto-scaling
- Private endpoint
- VPC peering
- Built-in embedding pipelines
- Real-time monitoring dashboards
- Alerts and alerting integrations
- Role-based access control
- API key management
- Data encryption in transit and at rest
- OAuth 2.0
- Enterprise SSO (SAML 2.0)
- Customer managed encryption keys (CMEK)
- Audit logs
- IP address access control