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

# Developer overview

> Build on Easy-Peasy.AI with the REST API, the MCP server, and the OpenAI-compatible chat endpoint.

Everything you can create in the Easy-Peasy.AI dashboard is also available to your own code and AI agents. They all use your account's API key and draw from the same plan allowance as the dashboard.

<Columns cols={2}>
  <Card title="REST API" icon="square-terminal" href="/docs/api-reference/introduction">
    Generate text, images, videos, speech, and transcriptions from your backend.
  </Card>

  <Card title="MCP server" icon="plug" href="/docs/mcp/introduction">
    Connect Claude, Cursor, Windsurf, and other MCP clients without writing API code.
  </Card>

  <Card title="Chat Completions" icon="messages" href="/docs/api-reference/endpoint/chat-completions">
    Point the OpenAI SDK at Easy-Peasy.AI and use the same chat models as Marky.
  </Card>

  <Card title="Agents API" icon="robot" href="/docs/api-reference/endpoint/chat-with-bot">
    Send messages to an AI agent you built in the dashboard.
  </Card>
</Columns>

## Get an API key

Open [**Settings** > **API/MCP**](https://easy-peasy.ai/settings/api) in the dashboard and create a key. Send it in the `x-api-key` header. Keep keys on your server, never in browser code or public repositories.

## What the API covers

| Area           | What you can do                                                                         | Start here                                                               |
| -------------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------ |
| Text           | Run the dashboard's writing tools, from blog posts to SOAP notes                        | [Generate text](/docs/api-reference/endpoint/generate)                        |
| Images         | Generate and edit images with Nano Banana, GPT Image, FLUX, Seedream, and more          | [Generate image](/docs/api-reference/endpoint/generate-image)                 |
| Video          | Text-to-video, image-to-video, and reference-to-video with the dashboard's video models | [Video models](/docs/api-reference/video-models)                              |
| Talking videos | Animate a face with your script or audio                                                | [Generate talking video](/docs/api-reference/endpoint/generate-talking-video) |
| Audio          | Text to speech, sound effects, and transcription                                        | [Text to speech](/docs/api-reference/endpoint/generate-tts)                   |
| Chat           | OpenAI-compatible chat completions with streaming                                       | [Chat Completions](/docs/api-reference/endpoint/chat-completions)             |

<Note>
  In the dashboard, the text generators are called **tools**. In the API they're called **presets**, because that's the name of the request field (`preset`).
</Note>

## Quick example

```bash theme={null}
curl -X POST https://easy-peasy.ai/api/generate \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "preset": "blog-post",
    "keywords": "How to get started with AI",
    "tone": "professional",
    "outputs": 1
  }'
```

API calls use the same allowance as the dashboard. See [Plans and credits](/docs/account/plans-and-credits) for how usage is counted.