Managed pgvector on NVMe.
3× cheaper than Supabase.
Dedicated PostgreSQL 18 tuned for vector search. NVMe storage, HNSW indexes, automated backups, HA failover. Deploy in minutes.
2,000 QPS•<4ms latency•NVMe-backed
postgresql://appuser@db-7q9m2p.eu.rivestack.io/primary Powering ask.rivestack.io — semantic search over 30 days of Hacker News
How Rivestack compares
Same dedicated compute. Fraction of the cost.
| Rivestack | Supabase | Neon | |
|---|---|---|---|
| Monthly cost | $35 | ~$105 | ~$69+ |
| Compute | 2 vCPU · 4 GB | Shared · 1 GB* | Serverless |
| Storage | NVMe | gp3 SSD | Cloud SSD |
| pgvector | Tuned (HNSW) | Extension only | Extension only |
| Backups | Daily + 14d PITR | Daily | Yes |
| Vector perf | 2,150 QPS · 2.8ms | ~410 QPS · 18ms | Cloud SSD limited |
| Terraform | ✓ | ✓ | ✗ |
Supabase and Neon are excellent platforms with broader feature sets — auth, storage, edge functions, realtime. If you need those, use them. Rivestack is for teams that need fast, affordable, dedicated pgvector and nothing else.
Real numbers
Measured on the $35/month plan. No synthetic loads, no cherry-picked configs.
Throughput
2,000 QPS
p50 Latency
<4 ms
Recall
99.5%
OpenAI text-embedding-3-small (1536 dimensions). Full benchmark methodology and reproduction scripts on our docs.
Try it yourself
ask.rivestack.io runs on a real Rivestack cluster. Every query hits pgvector on NVMe.
Works with your stack
It's just PostgreSQL. Use your existing driver.
package main
import (
"context"
"fmt"
"github.com/jackc/pgx/v5"
)
func main() {
ctx := context.Background()
conn, _ := pgx.Connect(ctx, "postgresql://appuser@db-7q9m2p.eu.rivestack.io/primary")
defer conn.Close(ctx)
// pgvector is already enabled — just create your table
conn.Exec(ctx, `CREATE TABLE docs (
id bigserial PRIMARY KEY,
text text NOT NULL,
emb vector(1536)
)`)
// Insert a document with its embedding
conn.Exec(ctx, `INSERT INTO docs (text, emb)
VALUES ($1, $2::vector)`, "deploy LLMs in production", embedding)
// Nearest-neighbor search in < 4ms
rows, _ := conn.Query(ctx, `SELECT text, emb <=> $1::vector AS dist
FROM docs ORDER BY dist LIMIT 5`, query)
for rows.Next() {
var text string
var dist float64
rows.Scan(&text, &dist)
fmt.Printf("%.4f %s\n", dist, text)
}
}Provision with Terraform
Manage Rivestack like the rest of your infra. Create, scale, and destroy clusters with one file and one command.
Built in France. Infrastructure in EU and US-East.
Built-in SQL editor with AI assist
Write plain English, get working pgvector SQL. No syntax to memorize.
Pricing
Fixed monthly price per node. No hidden fees, no usage surprises. Pause or delete anytime.
Production-ready dedicated PostgreSQL with NVMe storage, automated backups, and monitoring. Add nodes for HA.
- 2 vCPU · 4 GB RAM per node
- 55 GB NVMe storage
- ~1M vectors (1536d)
- pgvector tuned (HNSW)
- HA ready (add nodes)
- Daily backups + 14d PITR
- Monitoring dashboard
- SSL encrypted
- Terraform provider
High-performance dedicated PostgreSQL for demanding workloads. Add nodes for automatic failover.
- 8 vCPU · 16 GB RAM per node
- 295 GB NVMe storage
- ~20M vectors (1536d)
- pgvector tuned (HNSW)
- HA ready (add nodes)
- Daily backups + 14d PITR
- Priority support
- Terraform provider
- Custom PostgreSQL config
FAQ
Common questions about migrating to Rivestack.
Supabase is excellent if you need auth, storage, and edge functions alongside pgvector. But for comparable dedicated compute (2 vCPU, 4 GB RAM), Supabase costs ~$105/month versus $35 on Rivestack. We also run on NVMe storage instead of gp3 SSDs, which makes a measurable difference for HNSW index scans. If pgvector is your primary use case, we give you more performance for less money.
You absolutely can — pgvector on a $30 VPS is a great setup. Rivestack adds automated backups, monitoring, point-in-time recovery, HA failover, and SSL. We're for people who want affordable infrastructure without managing it themselves.
Your data is replicated with Patroni, backed up daily with pgBackRest, and stored on encrypted NVMe drives. Point-in-time recovery covers 7 days. Infrastructure runs on dedicated servers in ISO 27001 certified data centers. We're transparent about our stack — read our architecture docs.
Yes. It's standard PostgreSQL. pg_dump from your current provider, pg_restore to Rivestack. Takes minutes for most databases.
Rivestack is based in France and our EU region runs entirely within the European Union. Your data never leaves EU territory unless you explicitly choose our US-East region. As a French company, we are subject to GDPR by default — data processing agreements (DPA) are available on request.
We don't have SOC2 yet. If you need enterprise compliance certifications today, Supabase or AWS RDS are better choices. We're focused on indie developers, startups, and small teams who prioritize performance and cost.
