> ## Documentation Index
> Fetch the complete documentation index at: https://docs.together.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Adapt a base model to your task or domain by training it on your data.

Fine-tuning adapts a pretrained model to a smaller, targeted dataset so it performs better on a specific task or domain. Together AI handles every step of the process, from data preparation to hosting the resulting model for inference.

## When to fine-tune

Use fine-tuning when:

* Prompting alone does not give you the behavior you need.
* You have a well-defined task with labeled examples (hundreds to thousands).
* You want lower latency or cost than routing every request to a large general model.
* You need the model to understand a private domain: your data, your terminology, or your output format.

If you only need factual grounding, try retrieval-augmented generation (RAG) before fine-tuning.

## Fine-tuning types

Together supports two modes of supervised fine-tuning:

* **LoRA (Low-Rank Adaptation).** Trains a small set of adapter weights on top of the frozen base model. Faster, cheaper, and the right choice for most use cases. The fine-tuning API defaults to LoRA. See [LoRA training and inference](/docs/lora-training-and-inference) for details.
* **Full fine-tuning.** Updates every weight in the base model. Uses more compute, but can outperform LoRA on tasks where the base behavior needs to shift substantially.

## Specialized fine-tuning

Beyond standard supervised fine-tuning, Together supports:

* [Preference fine-tuning](/docs/preference-fine-tuning). Align a model with rankings over preferred and dispreferred responses.
* [Function-calling fine-tuning](/docs/fine-tuning-function-calling). Train a model to call tools reliably.
* [Reasoning fine-tuning](/docs/fine-tuning-reasoning). Train a model to produce chain-of-thought outputs.
* [Vision-language fine-tuning](/docs/fine-tuning-vlm). Fine-tune vision-language models (VLMs) on image-text pairs.
* [Bring your own model](/docs/fine-tuning-byom). Upload a base model from outside the Together catalog and fine-tune it.

## Data and models

* [Data preparation](/docs/fine-tuning-data-preparation). Supported formats (conversational, instruction, preference, generic text), JSONL and Parquet schemas, and validation rules.
* [Fine-tuning models](/docs/fine-tuning-models). Every base model available for fine-tuning, along with the modes each one supports.

## Pricing

Fine-tuning is billed per token of training data, scaled by model size and run type. Once training finishes, inference runs on a [dedicated endpoint](/docs/deploying-a-fine-tuned-model). See [fine-tuning pricing](https://www.together.ai/pricing#fine-tuning) for current rates.

## Next steps

* Run through the [fine-tuning quickstart](/docs/fine-tuning-quickstart) end-to-end.
* Check the [fine-tuning FAQ](/docs/fine-tuning-faqs) for common questions.