Cost

What does an open-source multimodal AI stack cost?

The bill is the engine, the hosted database if you use one, the media bytes, and the model APIs those pipelines call. A free license does not make the model calls free, and a low subscription does not make you a content-delivery network.

Updated

What the bill is

A multimodal stack charges you in layers. The software license is one layer. Hosting the database is another. Storing video and images is another. Calling an embedding model or a language model is usually the one that surprises people, because it is billed by the model vendor, not by the database.

“Cheapest” is only meaningful after you name the layer. A free engine with an expensive model is not a free application. A hosted plan with no egress line is not an object-storage alternative.

How the layers split

Read a price by asking which layer it covers.

  • Engine. An open-source build you run yourself has no license fee. You still pay for the machine, and for any model API the computed columns call.
  • Hosted database. A cloud plan covers the database, a media store with a hard cap, and a database-storage allowance. Going past the allowance is a storage charge, not a per-question charge.
  • Your bucket. Pointing media at a bucket you already pay for does not add a second storage meter on the database plan. The bucket provider still bills you.
  • Model APIs. Transcription, embeddings, and chat completions are the provider’s invoice. Caching a computed column avoids repeat calls for a row that has not changed. It does not make the first call free.

What this cost is not

This is not a ranking of the cheapest vector database, the cheapest CDN, or storage with no egress as a general object store. Those are different products. The numbers below are for this stack: a multimodal schema you can run locally, and the hosted plans that run the same schema.

Published plan limits. Model APIs are a separate invoice.

Published plan limits. Model APIs are a separate invoice.
Self-hostedCommunityPro
SoftwareApache 2.0, freeSame engine, hostedSame engine, hosted
PriceNo license feeFree, Limited Beta$29/month, in preview
Cloud databasesYou run it1Up to 3
Media storeYour disk or bucket1 TB, hard limit1 TB, hard limit
Database storageYour disk10 GB, hard limit10 GB included, then $0.40 / GB-mo
Per query, I/O, egressNone from the engineNo separate meterNo separate meter
Model APIsYou pay the providerYou pay the providerYou pay the provider

Where Pixeltable fits

Pixeltable’s self-hosted engine is Apache 2.0. pip install pixeltable runs it on your machine with no account. Community is free and in Limited Beta: 1 cloud database, 1 TB of Media Store, and 10 GB of database storage, both hard limits. Pro is $29/month in preview, with up to 3 cloud databases and database storage above 10 GB at $0.40 / GB-mo.

Standard plans do not add a per-query, I/O, or egress meter. Managed media has no egress fee. Storage in a bucket you bring is not billed again by Pixeltable; your bucket provider still charges you. The current table is on the pricing page.

import pixeltable as pxt
TableModel = pxt.model_base()
class Docs(TableModel, name='docs'):
document: pxt.Document
# Local, no account: pxt schema update app.py my_app
# The same class is what a cloud database runs.

Questions

Is the open-source version actually free?
The license is Apache 2.0. Running it locally has no Pixeltable license fee and needs no account. You still pay for the computer, and for model APIs if your columns call them.
Are there egress fees on managed media?
No. Standard plans do not bill a separate per-query, I/O, or egress meter. Managed media has no egress fee. A bucket you bring is billed by that bucket’s provider.
Does a free database make RAG free?
No. Embedding and chat calls are billed by the model provider. A computed column that caches its result avoids a second call when the row has not changed. The first call still costs whatever that provider charges.