TechPrufer
Get started
Pinecone
Pinecone logoPinecone · Feature trail

Dedicated Read Nodes

5 posts · Apr 2022 – Apr 2026

What this trail covers

Pinecone Dedicated Read Nodes (DRN) are now generally available, offering reserved capacity for queries with predictable performance and cost. This complements the On-Demand service for bursty workloads. DRN provides lower, predictable costs, consistent low-latency and high throughput, and scales for large workloads. It supports billion-vector semantic search, high-QPS recommendation systems, mission-critical AI services, and large enterprise/multitenant platforms. The system scales via replicas for QPS and shards for storage, eliminating rate limits. GA adds configurable performance vs. recall per query, metrics exporting, a web console, and multi-namespace support (early access).

All Pinecone trails
  1. Four New GA Features for Dedicated Read Nodes That Give Teams More Control and ObservabilityThis post announces the General Availability (GA) of Pinecone Dedicated Read Nodes (DRN) and details four new production capabilities: 1) Configurable performance vs. recall per query using `max_candidates` and `scan_factor` parameters to trade off latency/throughput for recall. 2) Metrics exporting for CPU utilization at shard and index levels, integrating with external observability stacks. 3) A web console experience for day-2 operations, showing capacity configuration and performance signals. 4) Multi-namespace support (in early access) for multi-tenant isolation within a single DRN index.
  2. Pinecone Dedicated Read Nodes: Now Generally AvailableThis post announces the General Availability of Pinecone Dedicated Read Nodes (DRN). It details the economic and performance benefits of DRN for sustained, high-volume workloads compared to On-Demand pricing, highlighting lower costs (77-97% reduction in examples), predictable latency and throughput, and the removal of rate limits. It explains how DRN scales via replicas for QPS and shards for storage, and provides a single API call migration path. The post also introduces four new GA features: configurable performance vs. recall, metrics exporting, a web console, and multi-namespace support (early access).
  3. Pinecone Dedicated Read Nodes are now in Public PreviewThis post announces the general availability of Pinecone Dedicated Read Nodes (DRN). It details how DRN provides reserved infrastructure for queries, offering predictable low-latency and high throughput through provisioned nodes and a warm data path. The post explains the scaling dimensions (replicas for throughput, shards for storage) and highlights use cases like billion-vector semantic search and high-QPS recommendation systems. It also provides guidance on creating DRN indexes and migrating from On-Demand to DRN.
  4. Introducing the Enterprise Plan for Mission-Critical ApplicationsIntroduced the Enterprise plan, which offers enterprise-grade features and support with self-serve convenience for mission-critical applications. Key additions include multiple availability zones for greater availability when replicas are added to an index, and Prometheus metrics for greater observability. The plan also includes Premium-level support with availability SLAs, response-time SLAs, and 24/7 support access. The 'Free' plan was renamed to 'Starter', and the 'Dedicated' plan was renamed to 'Enterprise Dedicated'. The usage estimator was made more accurate by allowing users to specify metadata size.