ToolPicker
Pinecone Rerank

Pinecone Rerank

44/100

Hosted rerank models in Pinecone Inference.

docs.pinecone.io

// scorecard · 44/100

verified 1mo ago
methodology →
Agent-readiness23/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server9/9
llms.txt3/3
Reliability & performance0/15
Actively maintained
Production-ready0/4
Updated recently
Pricing5/13
Itemized public pricing0/6
Free tier / trial4/4
Free-tier generosity1/3
Docs & DX2/12
Docs quality
Public API2/2
Quickstart / examples0/2
Security & compliance10/12
SOC 26/6
ISO 270012/2
GDPR0/2
Security / trust page2/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity0/3
Company size
Years operating

// rankings · cost per standard workload

#7 in Rerankers$2/ 1k rerank searches

pinecone-rerank-v0 $2/1k requests (up to 100 docs) x1 = $2/mo (per-request)

pinecone.io/pricing

// overview

Pinecone is a fully managed vector database for building accurate and performant AI applications at scale. It supports creating indexes for semantic search with integrated embeddings, sparse-vector lexical search, or full-text search on document schemas with BM25. Core workflows include upserting text or vectors, searching with text or vectors, filtering by metadata, and reranking results, along with namespace management for multitenancy.

Best for: AI applications at scale in production requiring high-performance semantic, lexical or hybrid search

// security & compliance

SOC 2 ISO 27001 GDPR HIPAA

// features

  • Semantic search with integrated embedding models
  • Full-text search with BM25 on FTS-enabled fields
  • Hybrid search combining dense/sparse vectors and lexical matching
  • Filter by metadata and rerank results
  • Namespaces for data partitioning and multitenant isolation
  • Index management, backups, and cost monitoring

sources