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

# llms.txt

> Structured documentation index optimised for LLM and AI agent consumption.

Jupiter provides structured documentation files purpose-built for LLMs and AI agents, following the [llmstxt.org](https://llmstxt.org) standard. They complement the [MCP server](https://developers.jup.ag/docs/ai/mcp.md), which serves the same documentation as tools, and the [agent skills](https://developers.jup.ag/docs/ai/skills.md).

> [!NOTE]
>
> Jupiter's `llms.txt` is auto-generated from the documentation structure. Every page includes an `llmsDescription` field in its frontmatter, a description specifically optimised for LLM consumption, separate from the human-readable description. This ensures AI tools get the most relevant context for each page.

## llms.txt

A plain Markdown file containing a structured index of all Jupiter documentation with titles and descriptions for each page:

* **Site title** as an H1 heading
* **Sections** for each major area (Docs, API References, Guides, Tool Kits, etc)
* **Links with descriptions** for every page, each pointing to the page's Markdown version (`.md`)
* **OpenAPI specifications** listed once at the end, for agents that need a whole product's endpoints and schemas in one file

> [card] [llms.txt](https://developers.jup.ag/docs/llms.txt)
>
> Open the llms.txt for Jupiter docs

```mdx theme={null}
# Jupiter

## Swap

- [Solana Swap API](https://developers.jup.ag/docs/swap/index.md): Overview of Jupiter's unified Swap API at api.jup.ag/swap/v2...
- [Get Order (Swap API)](https://developers.jup.ag/docs/api-reference/swap/order.md): GET /order endpoint for Jupiter Swap API V2...

## OpenAPI specifications

- [Swap API V2](https://developers.jup.ag/docs/openapi-spec/swap/v2/swap.yaml): OpenAPI 3 spec, 4 documented endpoints.
```

This is the perfect entrypoint for LLMs and AI agents to get started. It allows them to efficiently locate relevant content at a high level without processing the entire documentation.

## llms-full.txt

> [card] [llms-full.txt](https://developers.jup.ag/docs/llms-full.txt)
>
> Open the llms-full.txt for Jupiter docs

While `llms.txt` provides a concise index, `llms-full.txt` contains the **entire documentation site** as context, including every description, code example, and parameter detail.

Use `llms-full.txt` when:

* Your AI tool needs **complete, granular context** for deep indexing
* You're building **custom RAG pipelines** over Jupiter docs
* You want **every code example** available for reference

## Markdown Export

Any documentation page can be accessed as raw markdown, making it easy for AI agents to consume individual pages programmatically.

**Method 1: Append `.md` to the URL**

```bash theme={null}
curl https://developers.jup.ag/docs/swap.md
curl https://developers.jup.ag/docs/swap/order-and-execute.md
```

**Method 2: Use the `Accept` header**

```bash theme={null}
curl -H "Accept: text/markdown" https://developers.jup.ag/docs/swap
```

Both methods return the page content as `text/markdown`.


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