# Fine-tuning

> Fine-tuning is further training of an existing language model on your own examples, so it learns a specific format or task without long instructions every time.

- Page: https://methodcrew.com/glossary/fine-tuning
- Last updated: 2026-10-28
- Publisher: [The Method Crew](https://methodcrew.com/)

## How it works

You prepare hundreds to thousands of input and output pairs that show the behavior you want, then train the model further on them. The result is a new model version that follows that pattern more consistently with shorter prompts.

Where you can do this has changed. Google offers supervised tuning for Gemini models on its cloud platform ([Google Cloud tuning documentation](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/tune-models)). OpenAI closed its self-serve fine-tuning to new organizations in May 2026, and existing customers lose the ability to start new training jobs in January 2027 ([OpenAI deprecations](https://developers.openai.com/api/docs/deprecations)). Open-weight models can be fine-tuned on your own infrastructure, often with a lighter method called LoRA ([Hu and colleagues, 2021](https://arxiv.org/abs/2106.09685)) that trains a small set of extra weights.

Fine-tuning teaches behavior. It is a poor way to teach facts. A fine-tuned model still answers from memory, and that memory is out of date the day your price list changes.

## How businesses use it

It is worth the cost in a few narrow cases:

- A high-volume classification or extraction task where a smaller fine-tuned model matches a large model's accuracy at a lower price per call
- A strict output format or house style that prompting alone does not hold
- Specialist vocabulary the base model handles poorly
- Lower latency, for example in [voice agents](https://methodcrew.com/services/voice-ai-agents), where response time is part of the experience

For company knowledge such as policies, product details and contracts, use [retrieval-augmented generation](https://methodcrew.com/glossary/retrieval-augmented-generation). It costs less, updates the same day and can cite its sources.

## Where it goes wrong

Most fine-tuning ideas should start as [prompt engineering](https://methodcrew.com/glossary/prompt-engineering) plus retrieval. Try that first, measure it on a test set, and fine-tune only if a clear gap remains.

The costs that surprise people come after the first training run: assembling clean training data, and redoing the work when the provider retires the base model. A fine-tuned model is tied to the model it came from, so a provider's newer release does not inherit your training.

On a [corporate AI consulting](https://methodcrew.com/services/corporate-ai-consulting) engagement, this is one of the decisions we write down with the costs on both sides, so the call is made on numbers.

## Example (hypothetical)

Hypothetical: a freight audit firm sorts 50,000 invoice line items a month into 40 charge codes. Once a prompted large model works, a smaller model fine-tuned on 5,000 reviewed examples is tested against it, and the cheaper model goes live only if it matches on the test set.

## Related terms

- [Large language model (LLM)](https://methodcrew.com/glossary/large-language-model): A large language model is a neural network trained on huge volumes of text to predict the next token, which lets it write, summarize, classify and answer questions.
- [Prompt engineering](https://methodcrew.com/glossary/prompt-engineering): Prompt engineering is writing and testing the instructions, examples and context given to a language model so it produces the output a task needs, consistently.
- [Retrieval-augmented generation (RAG)](https://methodcrew.com/glossary/retrieval-augmented-generation): Retrieval-augmented generation is a method where a system first searches your own documents for relevant passages, then gives them to a language model to answer from.
- [LLM evaluation (evals)](https://methodcrew.com/glossary/llm-evaluation): LLM evaluation scores a language model system's outputs against a fixed set of real test cases, so you can tell whether a change made it better or worse.

## Services where this matters

- [Corporate AI consulting](https://methodcrew.com/services/corporate-ai-consulting): Use cases ranked by return, the best 1 or 2 piloted on your data, then a costed roadmap. $12,000 to $40,000 per project.
- [Custom AI agents and copilots](https://methodcrew.com/services/custom-ai-agents): Agents that look things up in your CRM or helpdesk and take the next step, with approvals. $15,000 to $90,000 per project.
- [Intelligent document processing](https://methodcrew.com/services/intelligent-document-processing): Invoices, contracts and forms turned into clean, checked data. $12,000 to $40,000 per project.

Full glossary: https://methodcrew.com/glossary