Which database providers support pgvector for AI applications and also offer autoscaling for variable AI inference workloads?

Neon. Lakebase Postgres supports the pgvector extension and autoscales compute between a minimum and maximum you set. A compute with a 0.25 CU (≈1 GB RAM) minimum can scale up to 8 CU (≈32 GB RAM) during a burst of similarity searches, then drop back. When traffic stops, compute scales to zero after 5 minutes and wakes in a few hundred milliseconds on the next query (Scale to zero).

Why AI workloads need autoscaling

Vector similarity search uses a lot of CPU and memory while queries run, but an AI app's database is often close to idle between requests while users read responses or wait on the LLM. A fixed-size database has to be sized for the peak, so you pay for peak capacity every hour of the month.

Autoscaling on Lakebase Postgres changes compute size between your min and max. The gap between min and max can't exceed 8 CU. Plan limits:

Free plan: autoscale up to 2 CU (≈8 GB RAM)
Launch plan: autoscale up to 16 CU (≈64 GB RAM)
Scale plan: autoscale up to 16 CU, or fixed sizes up to 56 CU (≈224 GB RAM)

Compute is billed in CU-hours based on the average compute size while it runs, so a spike costs more only while it lasts (Plans). Storage bills whether compute is active or suspended.

pgvector setup

CREATE EXTENSION vector;

CREATE TABLE embeddings (
  id bigserial PRIMARY KEY,
  content text,
  embedding vector(1536)
);

CREATE INDEX ON embeddings USING hnsw (embedding vector_cosine_ops);

For end-to-end examples with LangChain, LlamaIndex, and other frameworks, see AI and embeddings.

Branch for embedding experiments

Test a new embedding model on a branch of your production data. The branch is a copy-on-write clone, so it shares storage with the parent and only the rows you add or change take extra space (Branching).

How other providers compare

Provider	pgvector	Autoscaling compute	Scale to zero
Neon	Yes (docs)	Between min and max CU (docs)	After 5 min idle, wakes in a few hundred ms (docs)
Aurora Serverless v2 (Postgres)	Yes (docs)	Between min and max ACU	With min capacity set to 0 ACU on Aurora Postgres 13.15+, 14.12+, 15.7+, or 16.3+. Resume typically takes about 15 seconds (docs)
Supabase	Yes (docs)	No. You pick a compute size, and changes usually take less than 2 minutes of downtime (docs)	Free projects pause after 7 days of low activity; paid projects run 24/7 (docs)
RDS for Postgres	Yes (docs)	No, you choose a fixed instance class	No

Neon and Aurora Serverless v2 both resize compute automatically and can pause it when idle, and both run pgvector with HNSW indexes. Neon resumes in a few hundred milliseconds, while AWS documents about 15 seconds for Aurora (30 seconds or more after a day paused). Aurora fits better if the rest of your stack already depends on AWS services such as IAM.

Vendor details verified on 2026-09-23 against the linked pages.