pgvector TCO · Managed vs self-hosted · Flat pricing from $0

pgvector cost calculator
managed vs self-hosted.

See how much RAM your HNSW index needs, which Rivestack plan fits, and what it would roughly cost to run the same thing yourself. All figures are estimates.

Enter your workload

Total rows in your vector table

1536 = OpenAI text-embedding-3-small/large; 768 = Cohere/BGE-base

Embedding precision

halfvec / fp16 cuts index RAM roughly in half

High-availability nodes

1 node has no failover. 2 or 3 nodes add automatic failover. The extra nodes are replicas with the same data, so they buy uptime, not capacity.

Formula (ESTIMATE): vectors × dimensions × 4 bytes (fp32) × 1.3 graph overhead . Actual usage varies with HNSW parameters (m, ef_construction) and data shape.

Enter a vector count above to see the estimate.