Qdrant
Qdrant · Berlin, Germany · founded 2021
What it is
Qdrant is a vector similarity search engine and API for storing, searching and managing vectors alongside payload data. Points can pair vectors with JSON metadata that can filter search results. It supports dense, sparse and multivector configurations, as well as hybrid retrieval that combines semantic and lexical search for use cases such as semantic search and recommendations. Qdrant can run locally using Docker or through Qdrant Cloud. It provides REST and gRPC APIs, official client libraries for Python, JavaScript/TypeScript, Rust, Go, .NET and Java, and integrations including LangChain, LlamaIndex, Airbyte, Unstructured, DocArray and AutoGen. The free cloud tier is intended for tests and prototypes and is limited to a single-node cluster with 1GB RAM and 4GB disk. Qdrant Cloud includes TLS and encryption at rest; self-hosted deployments require configuration for those controls. Self-hosted open-source installations do not enable authentication or encryption by default. The maker is based in Berlin and was founded in 2021.
For and against
For
- Supports dense, sparse and multivector configurations.
- Hybrid retrieval combines semantic and lexical search.
- Provides REST and gRPC APIs.
- Official client libraries cover six languages.
Against
- Free cloud tier is limited to one node.
- Free tier has 1GB RAM and 4GB disk.
- Self-hosted deployments require security configuration.
- Community support is Discord-only.
The verdict
Qdrant offers flexible vector configurations, filtering and hybrid retrieval, with local and cloud deployment choices. The free cloud tier is constrained, and self-hosted users must configure authentication and encryption themselves.
Who it suits
Qdrant suits developers building semantic search or recommendation systems who need vector storage, metadata filtering or hybrid retrieval. It offers both local self-hosting and cloud deployment options.
Plans and prices
Free Tier
Single Node Cluster · 0.5 vCPU / 1GB RAM/ 4 GB Disk · Free Cloud Inference With Selected Models
Read 2 Oct 2026 · qdrant.tech
Hybrid Cloud
Managed clusters on your own infrastructure · Data stays in your network · Fully managed through Qdrant Cloud
Read 2 Oct 2026 · qdrant.tech
Premium Tier
SSO · Private VPC Links · 99.9% Uptime SLA · Extra Support
Read 2 Oct 2026 · qdrant.tech
Private Cloud
Dedicated, isolated deployment · Custom SLAs · Full isolation
Read 2 Oct 2026 · qdrant.tech
Standard Tier
Dedicated Resources · Flexible Vertical and Horizontal Scaling · Highly Available Setups · Backup & Disaster Recovery
Read 2 Oct 2026 · qdrant.tech
On the record
- APIs and clients
- Qdrant provides REST and gRPC APIs and official client libraries for Python, JavaScript/TypeScript, Rust, Go, .NET, and Java.qdrant.tech · read 2 Oct 2026
- Cloud security
- Qdrant Cloud includes built-in TLS and encryption at rest, while self-hosted deployments require customer configuration for these controls.qdrant.tech · read 2 Oct 2026
- Compliance
- Qdrant says its compliance documentation for SOC 2 Type 2 and HIPAA is available through its Trust Center.qdrant.tech · read 2 Oct 2026
- Data and filtering
- Qdrant points can contain vectors and JSON payload metadata, which can be used to filter search results.qdrant.tech · read 2 Oct 2026
- Deployment
- Qdrant can be run locally using its Docker image or used through Qdrant Cloud.qdrant.tech · read 2 Oct 2026
- Free-tier limit
- The free cloud tier is intended for testing and prototypes and is limited to a single-node cluster with 1GB RAM and 4GB disk.qdrant.tech · read 2 Oct 2026
- Hybrid retrieval
- Qdrant supports hybrid retrieval combining semantic and lexical search.qdrant.tech · read 2 Oct 2026
- Integrations
- Qdrant lists integrations including LangChain, LlamaIndex, Airbyte, Unstructured, DocArray, and AutoGen.qdrant.tech · read 2 Oct 2026
- Product
- Qdrant is a vector similarity search engine with an API to store, search, and manage vectors with additional payload data.qdrant.tech · read 2 Oct 2026
- Search use cases
- Qdrant describes vector databases as useful for semantic search and recommendation systems.qdrant.tech · read 2 Oct 2026
- Security configuration
- Self-hosted open-source deployments do not enable authentication or encryption by default, while Qdrant Cloud enables security features by default.qdrant.tech · read 2 Oct 2026
- Support
- The pricing page lists community support as Discord-only and paid support options with 10h/day business-hours or 24/7 coverage.qdrant.tech · read 2 Oct 2026
- Vector support
- Qdrant supports dense, sparse, and multivector configurations.qdrant.tech · read 2 Oct 2026
