The AI platform that got a 70-95% reduction in token consumption per agent with Pinecone - Read the case study
Serverless Pricing

Pods Pricing

Pinecone runs on fully managed infrastructure that scales with you. Start building today with product and support plans tailored to your needs.

SELECT A CLOUD MARKETPLACE

s1-storage-optimized

Pod SizeApproximate CapacityStandard ($/hour)
1x5 million vectors
$0.1110
2x10 million vectors
$0.2220
4x20 million vectors
$0.4440
8x40 million vectors
$0.8880

p1 - performance optimized

Pod SizeApproximate CapacityStandard ($/hour)
1x1 million vectors
$0.1110
2x2 million vectors
$0.2220
4x4 million vectors
$0.4440
8x8 million vectors
$0.8880

p2 - 2nd gen performance

Pod SizeApproximate CapacityStandard ($/hour)
1x1 million vectors
$0.1666
2x2 million vectors
$0.3333
4x4 million vectors
$0.6666
8x8 million vectors
$1.3332

Approximate Capacity estimated for 768 dimensional embeddings without metadata.

Collections Pricing

Vector data can be saved in Collections at a rate of $0.000035/GB/month