> For the complete documentation index, see [llms.txt](https://docs.cestus.network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cestus.network/api-reference/readme.md).

# API

The Cestus API provides a unified, high-performance gateway to run multimodal inference across a decentralized execution network. Built on top of standard OpenAI endpoint formatting, the Cestus API acts as a seamless drop-in replacement for existing AI workflows, allowing you to integrate state-of-the-art models into your applications with minimal code adjustments.

Through a single API key, Cestus grants access to a diverse ecosystem of specialized generative models spanning multiple operational modalities:

* **Text Generation**: Large language models optimized for instruction following, chat, coding, context-heavy reasoning tasks and agent integrations.
* **Image Synthesis**: Diffusion models capable of photorealistic rendering and art generation.
* **Video Generation**: Motion and temporal diffusion architectures for text-to-video pipelines.
* **Audio & Music Creation**: Algorithmic composition and generative audio models designed for music synthesis and dynamic soundscapes.

### Pre-requisite

Before making request calls to any Cestus inference endpoints, you must generate an authentication token. All requests to the network require a valid Bearer token passed in the HTTP request headers.

#### Getting Started

{% stepper %}
{% step %}

#### Create an account

Navigate to the Cestus Web Platform at <https://cestus.network/> and log into your account.
{% endstep %}

{% step %}

#### Get your API key

Go to the API Access section and click NEW API KEY.
{% endstep %}

{% step %}

#### Make your first request

Copy your newly generated key and store it securely.
{% endstep %}
{% endstepper %}

This key grants access across the entire range of Cestus API endpoints and services. Keep your API key private and avoid exposing it in client-side code repositories or public terminal logs.

<figure><img src="https://2473088455-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FrZmrosYyMBiwSLYHCXfR%2Fuploads%2FLnIyib4PMftMCGH4wErh%2Fimage.png?alt=media&amp;token=8b20ebc9-4d3b-4d95-a32f-964b33078a31" alt=""><figcaption></figcaption></figure>

{% content-ref url="/pages/f3bf9c5f1c422c980652043d61e91e2adac0e68c" %}
[Cestus API](/api-reference/readme/cestus-api.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.cestus.network/api-reference/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.