Pinecone

API for generating embeddings and reranking with hosted models.

Managed vector database for AI applications with integrated embedding, search, and reranking.

MCP server connecting any MCP-compatible client to Pinecone for vector index management and semantic search.

Command-line interface for direct terminal access to manage Pinecone indexes, namespaces, and records.

Serverless vector and document index for semantic, lexical, and full-text search with automatic metadata filtering.

REST API to store and query records in Pinecone vector database.

Usage-based vector database with serverless indexes charging for read units, write units, storage, and egress.