# Pinecone API

Category: [Embeddings and reranking](https://free-web-services.com/web-services/ai/embeddings/)  
Page: https://free-web-services.com/web-services/ai/embeddings/pinecone-api.html  
Documentation: https://docs.pinecone.io/guides/index-data/create-an-index

Pinecone is a managed vector database with hosted embedding and reranking models, for semantic search or retrieval-augmented generation (RAG). Requests are JSON over HTTPS with an Api-Key header. Free on the Starter plan: up to 2 GB storage, 1 million read units and 2 million write units a month, 5 million embedding tokens a month per hosted model and 500 rerank requests a month. An official MCP server (npm package @pinecone-database/mcp) lets AI agents search and manage indexes.

- API key: Needed, free
- Pricing: Free on the Starter plan: up to 2 GB storage, 1 million read units and 2 million write units a month, 5 million embedding tokens a month per hosted model and 500 rerank requests a month.
- From the browser: Yes (CORS)
- Formats: JSON
- Interface: REST, MCP
- Provider: docs.pinecone.io

Example request:

```sh
curl -X POST 'https://api.pinecone.io/embed' \
  -H 'Api-Key: YOUR_API_KEY' \
  -H 'X-Pinecone-Api-Version: 2025-10' \
  -H 'Content-Type: application/json' \
  -d '{"model":"llama-text-embed-v2","parameters":{"input_type":"passage"},"inputs":[{"text":"The quick brown fox"}]}'
```

Replace YOUR_API_KEY with your own key. The JavaScript works in a web page as well as in Node.js 18 or newer.