About
Pinecone is a fully managed vector database platform built to help teams develop knowledgeable AI applications at production scale. It provides fast similarity search, hybrid retrieval, namespaces for data partitioning, and real-time indexing for dynamic datasets.
The platform is designed for developers and enterprises that need reliable retrieval for use cases such as semantic search, recommendations, agents, and retrieval-augmented generation. Pinecone also offers hosted inference, reranking, and assistant capabilities, along with integrations across cloud providers, models, and frameworks.
- Purpose-built vector database for production AI workloads
- Serverless architecture with automatic scaling
- Advanced retrieval features including filters, rerankers, and namespaces
- Enterprise security, compliance, and operational controls
- Support for search, recommendations, agents, and RAG workflows
What's included in the free tier
- Free Starter plan for trying out and small applications.
- Access to Pinecone Database On-Demand.
- Access to Pinecone Inference.
- Access to Pinecone Assistant.
- Console Metrics included.
- Community support via Discord included.
- Up to 2 GB storage.
- Up to 2 million write units per month.
- Up to 1 million read units per month.
- Up to 5 indexes.
- Up to 100 namespaces per index.
- Access to all available embedding models.
- Access to all reranking models except cohere-rerank-3.5.
- Up to 1 project.
- Up to 2 users.
- Access to encryption at rest and in transit.
- Access to user RBAC.
- Access to API key RBAC.
- Access to SOC 2 compliance.
- Access to GDPR compliance.
- Access to ISO 27001 compliance.
- United States region only.
- AWS cloud only.
See Pinecone pricing for current limits.
