Supabase Vector

What it does

Supabase Vector is a vector database built on Postgres and the pgvector extension. You store embeddings, which are numeric representations of text or images, along with metadata, then index and query them by similarity. It connects to LLM and embedding APIs such as Hugging Face, OpenAI and SageMaker.

Typical uses include semantic search over a knowledge base, longer-term memory for chatbots, image similarity checks, and tagging or deduplicating content in a vector store. Embeddings live in the same database as transactional data, so application data and vectors can be handled in one system.

It suits developers and enterprise teams building AI applications, especially those already comfortable with Postgres and SQL. Access requires a Supabase project, either managed in the cloud or self-hosted. A free plan exists with limits such as 500 MB database size; paid plans start from $25 per month.

What it can do

• Store vector embeddings in Postgres using pgvector
• Upsert large volumes of vectors with metadata
• Index and query vectors by similarity
• Client libraries for managing and querying vector stores
• Connect to LLM and embedding APIs such as OpenAI and Hugging Face

Works with

• OpenAI
• Hugging Face
• AWS SageMaker

Before you choose

• Free projects are paused after one week of inactivity and are limited to two active projects.
• Vector storage shares compute and disk with the rest of the Postgres database, so size and plan affect performance and cost.
• Some features such as HIPAA and SSO are paid add-ons or Team/Enterprise items.

Listed under

• Data

Get started

Create a free Supabase project from the sign-up page.

1. Create a Supabase project from the dashboard or sign-up page.
2. Use the Supabase AI documentation and client libraries to store, index and query vector embeddings in Postgres.
3. Connect an embeddings or LLM API such as OpenAI or Hugging Face to generate vectors.

Vector has no separate price; costs follow the Supabase project plan. Pro includes $10/month in compute credits covering one Micro instance; compute is billed hourly and storage, egress and MAU usage above included quotas is billed per unit.

Source: supabase.com/pricing, checked 29 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.

• Supabase Vector | The Postgres Vector database and AI Toolkit ↗supabase.com
• Pricing & Fees | Supabase ↗supabase.com
• Supabase Docs ↗supabase.com

Company website

supabase.com: product, pricing and policy pages

Hacker News

Launch posts and discussion

YC directory mirror

Batch and company name

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

manual_review

Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.