Vespa Cloud by Vespa.ai

Managed Vespa engine for large-scale vector, text and hybrid search with ML ranking.

Vector databases Official MCP server Open source

Price

Free (open source)

you pay only for the compute it runs on

Free tier

Open source

SDK downloads

177K

PyPI pyvespa

Status

—

Pricing

Free tier	—
Cheapest paid plan	—
Usage price	Basic (initial): $0.1 per vCPU-hour, $0.01 per memory GB-hour, $0.0004 per disk GB-hour, $0.07 per GPU memory GB-hour
Good to know	Resource-based hourly billing; unit prices drop with volume. Enterprise requires a $20,000 minimum monthly spend. MCP server is shipped as a sample container app.

From the official pricing page, checked Oct 10, 2026. Prices change: confirm before you buy.

MCP server	Official: `https://github.com/vespa-engine/sample-apps/tree/master/examples/mcp-server-app`
PyPI	`pip install pyvespa`
GitHub	vespa-engine/vespa · 7,122 stars · last push Oct 10, 2026

API	Free	Price	SDK downloads / wk	GitHub stars	MCP
Supabase (pgvector) Hosted Postgres with the pgvector extension, plus auth, storage and APIs.	Free: 500 MB database, shared CPU, 2 active...	Free plan · paid from $25/mo	37.2M	111K	MCP
Elasticsearch (Elastic Cloud) Managed Elasticsearch for full-text, vector and hybrid search over indexed documents.	Open source	Serverless: Ingest as low as $0.14 per VCU per hour; Search as low...	10.5M	78.2K	MCP
pgvector Postgres extension adding vector columns and exact/approximate nearest-neighbor search (HNSW, IVFFlat).	Open source	not published	9M	23.3K
Qdrant Cloud Managed clusters of the open-source Qdrant vector search engine.	Free forever single-node cluster: 0.5 vCPU,...	Free plan	4M	35K	MCP
LanceDB Embedded and cloud vector database on the Lance columnar format for vector, full-text and hybrid search.	Open source	not published	2.4M	11.6K	MCP
turbopuffer Serverless vector and full-text search engine built on object storage.	—	from $16/mo	2.1M	174