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

# Use in Dify

> Integrate AnyFast AI models with Dify — build AI workflows and agents fast.

## 1. Get an API Key

Open the [AnyFast console](https://www.anyfast.ai/) and sign up (or log in if you already have an account). After signing up, go to **API Keys**, create a new API Key, and copy it for later use.

## 2. Use AnyFast language models in Dify

### 2.1 Add AnyFast as a model provider

In Dify, go to **Settings** → **Model Provider** in the top-right menu.

Click **Add Custom Provider** and choose **OpenAI API-compatible**.

Fill in the connection details:

* **Model Name**: Select from the [AnyFast model list](https://www.anyfast.ai/) (e.g., `gpt-4o`, `claude-opus-4-7`)
* **API Key**: Paste the API Key from the AnyFast console
* **API Endpoint URL**: `https://www.anyfast.ai/v1`

Click **Save**. Once verified, you'll see AnyFast models in your model list and can use them in your Dify applications.

### 2.2 Use models beyond the built-in list

For models not listed in the default provider menu, use the **OpenAI API-compatible** provider option:

* Open Dify **Settings** → **Model Provider**
* Add an **OpenAI API-compatible** provider
* Fill in the model name, API Key, and endpoint as described above

## 3. Use AnyFast image generation models in Dify

AnyFast image models (like `wan2.7-image-pro`) can also be accessed in Dify via the OpenAI-compatible image endpoint. Configure them the same way using the `/v1` base URL.

<script src="/feedback.js" />