# Replicate

## **Connector Overview**

<figure><img src="/files/v8eqBo18NV6Clfy7DsYI" alt=""><figcaption></figcaption></figure>

Replicate is a cloud platform that lets developers run open-source machine learning models through simple APIs, enabling easy deployment of AI capabilities without managing infrastructure or requiring deep ML expertise.

## **Supported Models**

Various models including Llama, SDXL, etc.

## **Authentication Type**

Basic

## **Webhook Supported**

No

## **Secrets**

* PAN\_SEC\_REPLICATE\_API\_KEY

## **API Client Supported**

No

## **Requirements for Provisioning**

In order to provision your connector, the following Replicate information must be gathered:

* API Key

To obtain the information required for provisioning the Replicate Connector, perform the following steps:

1. Log in to your [Replicate Dashboard](https://replicate.com/signin)
   1. You will need to sign in with your GitHub account
2. Navigate to Account Settings > API Tokens
3. Enter a Token Name and select **Create Token**

## **API Resources**

For more information on how to utilize the Replicate API, feel free to reference the following [documentation](https://replicate.com/docs).


---

# Agent Instructions: 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:

```
GET https://docs.pandium.com/connectors/connectors-101/replicate.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
