Infino Cloud

Infino Cloud is live

The same open-source Infino engine, served as a fully managed, object-storage-native service. Full-text, vector, hybrid, and SQL search, with no servers to run or size. You pay for what you use.

Same API

One line changes

A program written against a local directory or your own S3 bucket moves to Infino Cloud by changing only the connect target. Every table and search call stays the same.

import infino

# local
db = infino.connect("./data")

# Infino Cloud: only the connect target changes
db = infino.connect("https://api.platform.infino.ws/my-app", api_key="inf_...")
What you get

Managed retrieval, same engine

01
Fully managed
No servers to provision, patch, or scale. Storage grows with your data, and table maintenance runs for you.
02
Object-storage-native
Your data is stored as standard Apache Parquet on object storage, the same open format the engine uses locally. No proprietary lock-in.
03
The same retrieval surface
BM25, vector kNN, hybrid, and SQL over one copy of your data, indexed once.
04
Usage-based
Pay for storage and query usage rather than provisioned, always-on capacity.
Deployment

Cloud or self-hosted

Infino is open source, and you can always run the engine yourself against local disk or your own bucket. Choose Infino Cloud when you want retrieval as a service and want to go from an API key to a working table in minutes. Self-host when data and compute must stay entirely inside your own environment. The code you write is the same either way, so you can start on one and move to the other without rewriting your application.

Get an API key and run your first search in minutes.