# Pinecone API

**Provider:** Pinecone
**Category:** storage
**Base URL:** `https://api.pinecone.io`
**Auth:** api-key — `Api-Key: YOUR_API_KEY`
**Rate Limit:** 100 requests/sec (free) · Higher on paid plans
**Free Tier:** Yes — [object Object]
**Pricing:** Pay per use (pay-as-you-go)
**Docs:** https://docs.pinecone.io

## Description

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.

## Endpoints

| Method | Endpoint | Description |
|--------|----------|-------------|
| POST | `https://api.pinecone.io/vectors/upsert` | Insert or update vectors in an index |
| POST | `https://api.pinecone.io/query` | Find the K nearest neighbor vectors |
| GET | `https://api.pinecone.io/vectors/fetch` | Fetch vectors by ID |
| POST | `https://api.pinecone.io/vectors/delete` | Delete vectors by ID or metadata filter |
| GET | `https://api.pinecone.io/indexes` | List all indexes in your project |
| POST | `https://api.pinecone.io/indexes` | Create a new vector index |

## Authentication

Pass your Pinecone API key in the Api-Key request header.

```
Api-Key: YOUR_API_KEY
```

## Sample Request

```bash
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"}}}'
```

## Sample Response

```json
{
  "matches": [{
    "id": "doc-42",
    "score": 0.9834,
    "metadata": {
      "text": "Vector databases enable semantic search...",
      "category": "tech",
      "url": "https://example.com/doc-42"
    }
  }]
}
```

## Pricing Details

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).

---

*Source: [API Map](https://apimap.dev/apis/pinecone/) — CC BY 4.0*