Qdrant Vector Search Engine

Looking for a Free Vector Database? Start Free on Qdrant Cloud

Store your embeddings and search them with filters on a free Qdrant Cloud cluster with 1 GB RAM, room for about 1 M vectors, and no credit card.

Vector database

What to Test When You Choose a Vector Database

Whether you searched for a vector database, a vectordb, or a db vector, the same questions decide the pick. Qdrant is an open source vector search engine, written in Rust under Apache 2.0.

A query vector with a filter walks only the matching points of the HNSW graph and returns results that all match.
  • Filter inside the search.

    Qdrant applies payload filters while it traverses the HNSW graph, so every result already matches the user, product, or date range you scoped.

  • Match keywords and meaning in one call.

    Run dense and sparse retrieval in one Query API request and fuse the two rankings with Reciprocal Rank Fusion (RRF).

  • Boost memory efficiency.

    Scalar quantization stores your vectors in 4x less memory than float32, and binary or product quantization compresses them further.

Start free with Qdrant Cloud

Vector embedding database

Keep Each Embedding Next to the Data You Filter On

In a vector embedding database setup, each Qdrant point holds its vectors and a JSON payload, so you filter and rank in the same place you store.

Store several vector types per point.

Keep dense and sparse vectors next to each other in one collection.

Create embeddings in the cluster.

Qdrant Cloud Inference generates dense, sparse, and multimodal embeddings inside Qdrant Cloud.

Index the fields you filter on.

Create a payload index on a field, and Qdrant adds filter-aware links to the HNSW graph.

Managed vector database

Let Qdrant Cloud Run the Cluster for You

Qdrant Cloud runs the same engine as a managed service on AWS, GCP, or Azure, and handles operations like scaling and upgrades for you.

Scale from the Console.

Begin on a free cluster, then scale up or out. Qdrant Cloud rebalances data automatically when you add nodes.

Upgrade while you serve.

Qdrant Cloud runs version upgrades as rolling, zero-downtime updates when your multi-node cluster’s collections have a replication factor of 2 or more.

Use the client you know.

Call Qdrant over REST or gRPC, or from the official Python, TypeScript, Rust, Go, .NET, or Java client.

Start free with Qdrant Cloud

Results

What Teams Run on Qdrant Cloud

Bayer

about 135 million points on a four-node Hybrid Cloud cluster for 116,000 employees, with more than 10,000 knowledge bases in one shared collection.

Read the Bayer case study

Tripadvisor

over a billion user contributions indexed, and travelers who use its AI trip planner generate 2 to 3 times more revenue.

Read the Tripadvisor case study

My AskAI

about 75% of support requests deflected by AI agents running on Qdrant Cloud.

Read the My AskAI case study
Start free with Qdrant Cloud

Getting started

From Sign-Up to Your First Vector Search

Create a free cluster.

Sign up for Qdrant Cloud with no credit card.

Create a collection.

Set the vector size and distance metric your embedding model uses.

Upload and search.

Upload vectors with their payloads, then query with a vector and a filter.

Start Free

Common Questions

How do I get started with Qdrant Cloud?

A free Qdrant Cloud cluster has 1 GB RAM, 0.5 vCPU, 4 GB disk, and one node, enough for about 1 M vectors of 768 dimensions, with no credit card. Move to a Standard cluster when you need dedicated resources, multi-node high availability, backups, and SLAs.

Is Qdrant open source?

Yes. The Qdrant engine is open source under the Apache 2.0 license. The project has more than 35,000 GitHub stars and passed 250 million downloads across its packages.

Which vector database use cases does Qdrant cover?

Teams run semantic and hybrid search, retrieval augmented generation, recommendations, and memory for AI agents on Qdrant.

Start Your Free Qdrant Cloud Cluster

Store, filter, and search your embeddings on a cluster that grows with your app.

Rocket flying over globe illustration