Blogs›Pinecone›Dedicated Read Nodes
Pinecone has introduced a new Enterprise plan that offers enterprise-grade features and support with self-serve convenience for mission-critical applications. This plan includes multiple availability zones for greater availability when replicas are added to an index, and Prometheus metrics for enhanced observability by allowing users to monitor Pinecone indexes by ingesting performance metrics into their own Prometheus instances or compatible tools. The plan also comes with Premium-level support, including availability SLAs, response-time SLAs, and 24/7 support access. The 'Free' plan has been renamed to 'Starter', and the 'Dedicated' plan to 'Enterprise Dedicated'. The usage estimator has been improved to allow specifying metadata size. This plan is designed for users who need enterprise-grade support and availability but do not require a dedicated, single-tenant cloud environment.
4/15/2026
Introduces four new production capabilities for Dedicated Read Nodes (DRN): configurable query-time parameters (`max_candidates`, `scan_factor`) to trade off performance and recall, metrics exporting for CPU utilization at shard and index levels, a dedicated web console experience for day-2 operations, and early access to multi-namespace support for multi-tenant isolation.
4/15/2026
This post announces the General Availability (GA) of Pinecone Dedicated Read Nodes (DRN). It details the benefits of DRN for sustained, high-volume vector workloads, including lower and more predictable costs, consistent low-latency and high throughput via dedicated provisioned nodes with a warm data path, and scalable throughput without rate limits. It highlights cost savings on real production workloads (77-97% reduction) and explains the scaling dimensions (replicas for QPS, shards for storage). The post also mentions four new GA features for deeper control and observability, and provides guidance on choosing between DRN and On-Demand services based on workload characteristics.
12/1/2025
This post announces the Public Preview of Pinecone Dedicated Read Nodes (DRN). It details the architecture of DRN, explaining how it provides reserved capacity for queries with predictable performance and cost. It elaborates on the scaling dimensions: replicas for throughput and availability, and shards for storage capacity. The post also provides performance benchmarks from customer use cases and outlines the steps for creating a DRN index through the Pinecone console, including configuration options for node type, shards, and replicas. It also mentions the API for creating DRN indexes and the process for migrating from On-Demand to DRN.
4/6/2022
The Enterprise plan introduces multiple availability zones for increased availability when replicas are added to an index, distributing them across availability zones within the same cloud region. It also adds Prometheus metrics for enhanced observability, allowing users to ingest performance metrics into their own Prometheus instances or compatible monitoring tools. This plan provides Premium-level support with availability SLAs, response-time SLAs, and 24/7 support access.