liveBook · Manning

Proprietary model

As explained in Rearchitecting LLMs

A closed model is a model whose provider controls access to its implementation, weights, or execution interface.

A proprietary model is controlled by its provider: access to the base model, weights, implementation, or execution interface remains restricted. Fine-tuning uses provider tools, incurs per-token training costs, and produces a hosted artifact rather than an exportable model. section 1.1.2

Evaluate proprietary models through their operational trade-offs:

  • Treat fine-tuning as provider-dependent: the adapted model remains tied to the provider's base model. section 1.1.2
  • Account for recurring cost: training processes tokens through very large models, and inference remains more expensive after adaptation. section 1.1.2
  • Plan for lifecycle changes: pinning a version improves stability, but upgrades or retirement can require repeating fine-tuning and evaluation. section 1.1.2

Closed-model fine-tuning

Fine-tuning Gemini or GPT through provider tools adapts behavior without exporting the base weights; switching providers can therefore require rebuilding the adaptation. section 1.1.2

How Rearchitecting LLMs covers it

How deep it goes
Explains fine-tuning costs, non-exportable weights, version pinning, and retraining implications without examining model internals.
Examples
Uses Gemini and GPT as examples of closed models adapted through provider-controlled fine-tuning tools.
What you can do after
Evaluate provider dependence, recurring costs, portability limits, and retraining requirements before adopting or adapting a model.
How it connects
Connects proprietary models to retrieval-augmented generation, fine-tuning, model providers, and vendor lock-in.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Rearchitecting LLMs. The section links point to the parts of the book it draws on.