Postgres for AI workloads.
Without the platform tax.

# if any of this sounds familiar

Your pgvector setup is probably costing you.

// Vector workloads don't fit neatly into general-purpose Postgres pricing. Most teams we talk to are losing money, losing sleep, or both.

# rivestack vs. what you have today

// save 65%+ vs Supabase at the same compute

// * Vector perf on a Starter node (2 vCPU / 4 GB, AMD) at recall@10 0.90, 4 clients; every region runs the same AMD line. Supabase $25 base + ~$80/mo compute add-on for 2 vCPU / 4 GB. Neon usage-based, ~$69+ at moderate usage. Every number is measured and reproducible — full tables at /pgvector-benchmarks-measured. Also runnable with pgvector-bench — we don't publish competitor benchmarks we haven't run. Full methodology →

Supabase and Neon are excellent platforms with broader feature sets — auth, storage, edge functions, realtime. If you need those, use them. If you just need fast Postgres with pgvector, that's all we do.

# semantic search, built into your database

# works with your stack

// it's just PostgreSQL. Use your existing driver.

import psycopg2

conn = psycopg2.connect("postgresql://appuser@db-7q9m2p.eu.rivestack.io/primary")
cur = conn.cursor()

# pgvector is already enabled — just create your table
cur.execute("""CREATE TABLE docs (
    id   BIGSERIAL PRIMARY KEY,
    text TEXT NOT NULL,
    emb  vector(1536)
)""")

# Insert a document with its embedding
cur.execute(
    "INSERT INTO docs (text, emb) VALUES (%s, %s::vector)",
    ("deploy LLMs in production", embedding)
)

# table editor — no SQL required

# provision with terraform

# fixed monthly pricing

// One price per node. No per-query billing, no egress surcharges, no vector-count overage. The bill on day 30 is the same as the quote on day 1.

Prices shown are EU Central, our lowest region. US-East and Singapore are priced higher — full pricing.

# faq