USAGE BASED PRICING

Easy to understand pricing

Lantern pricing is transparent and easy. Estimate your costs by specifying the number of vectors in your application

Lantern's database bill was 10x lower than Pinecone, it's hard not to switch ...

Principal Engineer @ Amazon

Database Instance Configuration

2 vCPU, 2 GB RAM ($0.16 / hour)
2 vCPU, 4 GB RAM ($0.34 / hour)
2 vCPU, 8 GB RAM ($0.67 / hour)
4 vCPU, 16 GB RAM ($1.34 / hour)
8 vCPU, 32 GB RAM ($2.68 / hour)
16 vCPU, 64 GB RAM ($5.36 / hour)
32 vCPU, 128 GB RAM ($10.72 / hour)

Number of vector embeddings

1M embeddings

1M

10M

100M

250M

500M

1B

2B

10B

$0

Embedding generation + index construction

$120

Instance costs

$0

10GB

Storage for embeddings

$120 / mo

Excluding embedding generation and index construction costs

Assumes OpenAI CLIP embeddings, exact costs vary based on embedding models utilized

CONTROL YOUR COSTS

Save 20x-30x on cloud costs over competing vector databases

Customers switch to Lantern to avoid outrageous cloud costs generated by vector database competitors. Tap into industry leading performance for a fraction of the price

Pinecone logo

1 billion embeddings

$243,200

/mo

Milvus logo

1 billion embeddings

$358,900

/mo

1 billion embeddings

$11,210

/mo

Assumes analogous price performance options like Pinecone's P2 performance-optimized and Milvus Enterprise metrics based on publicly available data for 100M embeddings (~$36,000/mo)

PricingDocsBlog
LoginTry Lantern for Free