# Upstash Vector

Category: [Embeddings and reranking](https://free-web-services.com/web-services/ai/embeddings/)  
Page: https://free-web-services.com/web-services/ai/embeddings/upstash-vector.html  
Documentation: https://upstash.com/docs/vector/overall/getstarted

Upstash Vector is a serverless vector database with a REST API: upsert vectors, or raw text that a built-in model embeds, and query by similarity with metadata filters, for example for chatbot memory. Each index has its own REST URL and token. Free plan with up to 10 indexes, 1 GB of data and 10,000 queries and updates a day; pay as you go after adding a card. An official MCP server (npm package @upstash/mcp-server, remote at https://mcp.upstash.com/mcp) lets AI agents manage Upstash databases, including Vector.

- API key: Needed, free
- Pricing: Free plan with up to 10 indexes, 1 GB of data and 10,000 queries and updates a day; pay as you go after adding a card.
- Formats: JSON
- Interface: REST, MCP
- Provider: upstash.com

Example request:

```sh
curl -X POST 'https://YOUR_INDEX-us1-vector.upstash.io/query-data' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"data":"What is a vector database?","topK":3,"includeMetadata":true}'
```

Replace YOUR_INDEX and YOUR_API_KEY with your own values from your account.