Pinecone is a fully managed vector database optimized for machine learning applications. Store dense vector embeddings and query them at low latency using approximate nearest neighbor (ANN) search with metadata filtering. Supports sparse-dense hybrid search, namespaces for multi-tenant isolation, and real-time upserts. Widely used for semantic search, RAG (retrieval-augmented generation), recommendation systems, and anomaly detection.
https://api.pinecone.io
Auth type
API Key Header
Auth header
Api-Key: YOUR_API_KEY
Rate limit
100 requests/sec (free) · Higher on paid plans
Pricing
Pay per use
Free quota
2GB storage, 5 indexes (serverless)
Documentation
https://docs.pinecone.io
Endpoint status
Server online — HTTP 401 — server is online but path returned an error (may require auth)713ms
(checked Mar 29, 2026)
Builder score
B
66%
builder-friendly
Pass your Pinecone API key in the Api-Key request header.
Api-Key: YOUR_API_KEY
Serverless Free: 2GB storage, 1M read units/month. Serverless Standard: $0.033/GB stored + $0.08/1M read units. Pod-based: from $0.096/hour (p1.x1 pod).
| Method | Path | Description |
|---|---|---|
| POST | /vectors/upsert |
Insert or update vectors in an index |
| POST | /query |
Find the K nearest neighbor vectors |
| GET | /vectors/fetch |
Fetch vectors by ID |
| POST | /vectors/delete |
Delete vectors by ID or metadata filter |
| GET | /indexes |
List all indexes in your project |
| POST | /indexes |
Create a new vector index |
curl "https://my-index-abc123.svc.us-east1-gcp.pinecone.io/query" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"vector":[0.1,0.2,0.3],"topK":5,"includeMetadata":true,"filter":{"category":{"$eq":"tech"}}}'
{
"matches": [{
"id": "doc-42",
"score": 0.9834,
"metadata": {
"text": "Vector databases enable semantic search...",
"category": "tech",
"url": "https://example.com/doc-42"
}
}]
}
Data sourced from API Map. Always verify pricing and rate limits against the official Pinecone documentation.