AI inference from Postgres. Zero infrastructure overhead.

Connect to external LLMs, generate embeddings, and process massive datasets with a SQL-first experience. Your data stays in your VPC.

query.sql
-- pgInfer: Summarize 1k rows in one query
SELECT ai_live.summarize(content)
FROM production_logs
WHERE created_at > now() - interval '1 hour';

Two Modes of AI Inference

Choose the mode that fits your needs

Live Proxy

The Speed King

Instant access to OpenAI and Anthropic via SQL. No Python "glue" code needed. Real-time results.

Economic Batch

The Budget Optimizer

Save 50% on token costs using the remote Batch API. Perfect for massive historical data enrichment.

Built for the World's Most Regulated Industries

Enterprise-grade security and compliance

Zero-Egress

With Native mode, inference happens on your hardware. No data ever leaves your VPC.

Metadata-Only Gateway

We never store your data or use your queries for training. We process tokens, you keep the intelligence.

Integrated Audit Logs

Track usage, costs, and intent using the SQL tools you already own.

Built by Engineers, for Engineers

We spent years building fragile AI pipelines that broke every time a schema changed. We got tired of "glue code" and the security risks of moving production data to the cloud. V1 turns PostgreSQL into a native AI engine.

Pricing

Choose the plan that fits your scale

Developer Trial

Perfect for testing and development

$0/mo
  • 100 Live Proxy requests/day
  • Single-user license
  • Community support
  • Core features access

Pro

For production workloads

$49/mo per instance
  • Full Batch API access
  • High-concurrency Live Proxy
  • Priority support
  • Usage analytics

Enterprise

For enterprise-scale deployments

Custompricing
  • Native Inference mode
  • Per-vCPU licensing
  • 24/7 support
  • Custom SLA