# Qdrant

Canonical: https://inetgeek.com/vector-db/qdrant/

Open-source vector database with a free-forever cloud tier and four selectable similarity metrics.

## Who it suits

Teams that want a choice of similarity metric rather than one fixed default, or that want the option to self-host the same open-source engine the managed cloud runs.

Consider something else if A published, calculator-free entry price matters — Qdrant Cloud's Standard tier pricing is usage-based with no static per-month figure quoted, unlike some competitors' flat entry plans.

## What the documentation says

### Pricing

- Free tier: Yes ([source](https://qdrant.tech/pricing/), read 2026-09-11)
- Pricing model: Usage-based on the Standard tier: billed for compute (vCPU), memory (GB) and storage (GB) consumed by clusters, backup storage, and inference tokens for paid models. ([source](https://qdrant.tech/pricing/), read 2026-09-11)

### Infrastructure

- Regions: Standard and Premium tiers run on AWS, Azure and GCP. ([source](https://qdrant.tech/pricing/), read 2026-09-11)

### Vector

- Similarity metrics supported: Dot product, Cosine similarity (implemented as dot-product over automatically normalized vectors), Euclidean distance, and Manhattan distance. ([source](https://qdrant.tech/documentation/concepts/collections/), read 2026-09-11)
- Metadata filtering: Supported — collections store points (vectors with a payload) and support dedicated filtering on payload fields. ([source](https://qdrant.tech/documentation/concepts/collections/), read 2026-09-11)

## Compared with

- [Qdrant vs Pinecone](https://inetgeek.com/compare/pinecone-vs-qdrant/)
- [Qdrant vs Weaviate](https://inetgeek.com/compare/qdrant-vs-weaviate/)
- [Qdrant vs Turbopuffer](https://inetgeek.com/compare/turbopuffer-vs-qdrant/)
- [Qdrant vs Redis Cloud](https://inetgeek.com/compare/redis-cloud-vs-qdrant/)
- [Qdrant vs Elastic Cloud](https://inetgeek.com/compare/elastic-cloud-vs-qdrant/)