Start small,
scale instantly.

Scalable pricing and flexible ways to engage for any team and budget.
Starter
from

Serverless

$0/hr

The easiest way to experience
a GPU-powered AI database.

    check Vector database
    check Inference service
    check Document store
    check $0.05/hr per GB GPU cache
    check Multi GPU burst capability
    check Instant scalability up to 128 workers
    check Advanced sharding functionality
Established Workloads
from

Dedicated

$.60/hr

Dedicated cluster with fixed
hardware. Ideal for SMBs.

    check Vector database
    check Inference service
    check Document store
    check Dedicated GPUs
    check Multi GPU burst capability 
    check Instant and endless scalability: Horizontal and vertical 
    check Multiple databases 
    check Automated backups
    check Metrics & Logs
Enterprise

Custom

Bespoke build with your hardware.
Ideal for enterprise orgs.

    check Vector database
    check Inference service
    check Document store
    check Custom hardware
    check Solution architecture support
    check Private virtual cloud
    check On-prem deployments
    check Access control
PostgresML Logo PostgresML

solutions

Overview Chatbot Site Search (coming soon!) Fraud Detection (coming soon!) Forecasting (coming soon!)

Resources

Company

About Careers Privacy Terms of Service Contact

Community

GitHub Discord Formerly Twitter YouTube LinkedIn

PostgresML 2023 Ⓒ All rights reserved.