> ## 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.

# Introduction

> Explore the fundamental concepts of the Together AI platform: Tokens, context windows, when to use serverless vs. dedicated inference, and how the stack works in practice.

The [reference docs](https://docs.together.ai/intro.md) cover *how* to use the platform. This section covers the *why* behind what you're calling. Each topic starts broad and then layers in details, so you can form an accurate high-level mental model of the complete system.

You can read everything in order or cherry-pick whatever's relevant to what you're building:

## Fundamentals

> [card] [How LLMs work](https://docs.together.ai/learn/how-llms-work.md)
>
> Text in, probabilities out, repeat in a loop.

> [card] [Tokens & tokenization](https://docs.together.ai/learn/tokens-and-tokenization.md)
>
> Subword chunks of input and output.

> [card] [Context windows](https://docs.together.ai/learn/context-windows.md)
>
> The model's working memory and hard limits.

> [card] [Inference parameters & sampling](https://docs.together.ai/learn/inference-parameters-and-sampling.md)
>
> How to produce predictable or creative outputs.

> [card] [Context engineering](https://docs.together.ai/learn/prompt-engineering.md)
>
> Structuring prompts for optimal results.

> [card] [Inference metrics](https://docs.together.ai/learn/ttft-and-tps.md)
>
> TTFT and TPS, how fast an LLM feels.

## Core capabilities

> [card] [Function calling & tool use](https://docs.together.ai/learn/function-calling-and-tool-use.md)
>
> Model plans, your code runs the tool.

> [card] [Structured outputs & JSON mode](https://docs.together.ai/learn/structured-outputs.md)
>
> Force schema-valid output via constrained decoding.

## Customization & deployment

> [card] [Fine-tune vs. prompt](https://docs.together.ai/learn/finetune-vs-prompt.md)
>
> Hone a model for a particular task.

> [card] [Choosing a deployment option](https://docs.together.ai/learn/choosing-a-deployment-option.md)
>
> Serverless, dedicated endpoints, or containers.

> [card] [Quantization](https://docs.together.ai/learn/quantization.md)
>
> The JPEG quality slider for a model.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.