lesson
55 min

Three Ways to Get a Model

Compare hosted APIs, open-weight models, and managed services on control, effort, quality, and exit.

Objective

By the end of this lesson, you can explain the trade-offs of hosted APIs, open-weight models, and managed cloud services, and name which parts of a system a team should own no matter which it picks.

The three options

Almost no community organization trains a large language model from scratch. Training a frontier model takes data, hardware, and staff on a scale few institutions have. So the real choice is how you get access to a model someone else trained.

Hosted API. You send text to a provider's servers and get text back. The provider runs the model. You pay nothing to host it, and you get strong models quickly. You also send your data to someone else and depend on their uptime, terms, and model retirement schedule.

Open-weight model. The model's trained numbers (its weights) are published, so you can download and run it yourself. Llama, Mistral, Gemma, and Qwen model families are examples, each with its own license. You control where data goes. You also take on hardware, updates, security patches, and the skill to run it.

Managed service. A cloud provider runs models for you inside your cloud account, often with business contracts about data handling and region. It sits between the two: less work than self-hosting, more control than a public API, and more setup than either.

The trade-offs side by side

FactorHosted APIOpen-weight, self-hostedManaged cloud service
Time to first working versionFastestSlowestMedium
Where data goesProvider's systems, under their termsYour systems onlyYour cloud account, under a contract
Staff skill neededLow to mediumHighMedium
Model quality ceilingHighest availableVaries; often a step behind on hard tasksDepends on which models are offered
Exit difficultyDepends on how much you ownEasiestMedium
Who patches and monitorsProviderYouShared

Read the license and the data terms for every option. "Open" does not always mean you may use a model for any purpose. "We don't train on your data" may have exceptions, such as logs kept for abuse monitoring. Ask in writing.

What you own in every case

The model is the part you are most likely to swap. The parts that hold your judgment are the parts you should own:

  • Your prompts, versioned like code (Module 3).
  • Your retrieval layer: documents, chunking, and index (Module 4).
  • Your test sets and evaluation results (Module 7).
  • Your guardrails and permission rules (Modules 7 and 8).
  • Your logs and metrics (Module 10).

This is the blend pattern. You rent the model and own everything that makes the system yours. If a provider changes terms or retires a model, you run your test set against a replacement and switch with evidence.

Quiz: Options check

  1. 01Your organization must keep client records inside systems it controls. Which option fits best by default?

    Choose one.

  2. 02Which part of the system is usually safest to rent rather than own?

    Choose one.

A national example

Practice

What would you own?

Private. Saved only in this browser. No one else can see it.

Go deeper: Own the code: building internal tools over rented software

Ask. Answer. Build together.