> This page is for version v2 API (default).
> For other versions, use one of these documentation indexes:
> - v2 API (default): https://docs.cohere.com/v2/llms.txt
> - v1 API: https://docs.cohere.com/v1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cohere.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cohere.com/_mcp/server.

# Introduction to Fine-Tuning with Cohere Models

> Fine-tune Cohere's large language models for specific tasks, styles, and formats with custom data.

> **Error**
>
> Cohere's fine-tuning feature was deprecated on September 15, 2025

Our ready-to-use large language models, such as `Command R`, as well as `Command R+`, are very good at producing responses to natural language prompts. However, there are many cases in which getting the best model performance requires performing an **additional** round of training on custom user data. Creating a custom model using this process is called **fine-tuning**.

## Why Fine-tune?

Fine-tuning is recommended when you want to teach the model a new task, or leverage your company's unique knowledge base. Fine-tuning models is also helpful for generating a specific writing style or format.

If you are aiming to use a language model to draft responses to customer-support inquiries, for example, using a model fine-tuned on old conversations with customers will likely improve the quality of the output.

Note that there might be pricing differences when using fine-tuned models. You can use our [Pricing Calculator](https://cohere.com/pricing) to estimate the costs.

## How to Create Fine-tuned Models

Cohere offers two methods of creating fine-tuned models: via the [Cohere Dashboard](https://dashboard.cohere.com/welcome/login?redirect_uri=%2Ffine-tuning), via the [Fine-tuning API,](/reference/listfinetunedmodels) and via the [Python SDK](/docs/fine-tuning-with-the-python-sdk). The fine-tuning process generally unfolds in four main stages:

* Preparing and uploading training data.
* Training the new Fine-tuned model.
* Evaluating the Fine-tuned model (and possibly repeating the training).
* Deploying the Fine-tuned model.

Once you Fine-tune a model, it will start appearing in the model selection dropdown on the Playground, and can be used in API calls.

## Types of Fine-tuning

Models are fine-tuned for use in specific Cohere APIs. To be compatible with the Chat API, for example, a model needs to be fine-tuned on a dataset of conversations. APIs that support fine-tuned models are:

* [Chat](/docs/chat-fine-tuning)
* [Classify](/docs/classify-fine-tuning)
* [Rerank](/docs/rerank-fine-tuning)

## Fine-Tuning Directory

For your convenience, we've collected all the URLs relevant to fine-tuning Cohere models below. Think of this as being like a fine-tuning table of contents.

### Fine-tuning for Chat

* [Preparing the Chat Data](/docs/chat-preparing-the-data)
* [Starting the Chat Training](/docs/chat-starting-the-training)
* [Understanding the Chat Results](/docs/chat-understanding-the-results)
* [Improving the Chat Results](/docs/chat-improving-the-results)

### Fine-tuning for Classify

* [Preparing the Classify Data](/docs/classify-preparing-the-data)
* [Starting the Classify Training](/docs/classify-starting-the-training)
* [Understanding the Classify Results](/docs/classify-understanding-the-results)
* [Improving the Classify Results](/docs/classify-improving-the-results)

### Fine-tuning for Rerank

* [Preparing the Rerank Data](/docs/rerank-preparing-the-data)
* [Starting the Rerank Training](/docs/rerank-starting-the-training)
* [Understanding the Rerank Results](/docs/rerank-understanding-the-results)
* [Improving the Rerank Results](/docs/rerank-improving-the-results)