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

# QuickStart: Friendli Dedicated Endpoints

> Get started with Friendli Dedicated Endpoints. Create a project, pick a model, deploy an endpoint, and generate your first inference response.

export const RoundedBorderBox = ({children, caption}) => <div className="rounded-border-box">
    {children}
    {caption && <p className="text-sm text-gray-700 dark:text-gray-400">{caption}</p>}
  </div>;

Get started with [Friendli Dedicated Endpoints](/guides/dedicated-endpoints/introduction). This quickstart walks you through launching your first endpoint and sending your first request.

## 1. Sign Up or Log In

Create an account or log in at [Friendli Suite](https://friendli.ai/suite).

## 2. Navigate to the Dedicated Endpoints Page

Go to [Dedicated Endpoints](https://friendli.ai/suite/~/dedicated-endpoints) to see your endpoint list.

<RoundedBorderBox>
  <img alt="Sidebar" src="https://mintcdn.com/friendliai/SRK7vx0X1v_2rjkU/static/images/guides/dedicated-endpoints/sidebar.png?fit=max&auto=format&n=SRK7vx0X1v_2rjkU&q=85&s=501a86edf5d109705862db2f4e27a468" width="1096" height="936" data-path="static/images/guides/dedicated-endpoints/sidebar.png" />
</RoundedBorderBox>

## 3. Prepare Your Model

Choose a model to serve from [Hugging Face](https://huggingface.co){/* or [Weights & Biases](https://wandb.ai)*/}, or upload your own.

<img src="https://mintcdn.com/friendliai/SRK7vx0X1v_2rjkU/static/images/guides/dedicated-endpoints/hugging-face.png?fit=max&auto=format&n=SRK7vx0X1v_2rjkU&q=85&s=16f21cadd44ca8f50105c4dc2872e490" alt="Hugging Face" width="1696" height="730" data-path="static/images/guides/dedicated-endpoints/hugging-face.png" />

## 4. Deploy Your Endpoint

Deploy the model from step 3 with your chosen GPU. You can also configure replicas and optimization options.

<RoundedBorderBox>
  <img alt="Endpoint Create" style={{ maxWidth: "480px", width: "-webkit-fill-available" }} src="https://mintcdn.com/friendliai/SRK7vx0X1v_2rjkU/static/images/guides/dedicated-endpoints/endpoint-create.png?fit=max&auto=format&n=SRK7vx0X1v_2rjkU&q=85&s=c1a8a7c7dfe61dc1fcc02b128c89479b" width="1190" height="3510" data-path="static/images/guides/dedicated-endpoints/endpoint-create.png" />
</RoundedBorderBox>

<br />

<RoundedBorderBox>
  <img alt="Endpoint Detail" style={{ maxWidth: "480px", width: "-webkit-fill-available" }} src="https://mintcdn.com/friendliai/SRK7vx0X1v_2rjkU/static/images/guides/dedicated-endpoints/endpoint-detail.png?fit=max&auto=format&n=SRK7vx0X1v_2rjkU&q=85&s=fb50d9f7af59077bc7d925cd9a7aec35" width="1644" height="2786" data-path="static/images/guides/dedicated-endpoints/endpoint-detail.png" />
</RoundedBorderBox>

## 5. Generate Responses

Generate responses in two ways: the playground or the endpoint URL.

Use the playground tab to test your model in a chat-style interface.

<RoundedBorderBox>
  <img alt="Endpoint Playground" src="https://mintcdn.com/friendliai/SRK7vx0X1v_2rjkU/static/images/guides/dedicated-endpoints/endpoint-playground.png?fit=max&auto=format&n=SRK7vx0X1v_2rjkU&q=85&s=ac3382400c019d3dfd9fbfcab6d02078" width="1339" height="1044" data-path="static/images/guides/dedicated-endpoints/endpoint-playground.png" />
</RoundedBorderBox>

For programmatic use, send requests to your endpoint address—shown on the endpoint information tab—through our [API](/openapi). See [this guide](/guides/suite/personal-api-keys) for how to create a Personal API key.

<CodeGroup>
  ```python OpenAI Python SDK theme={null}
  import os
  from openai import OpenAI

  client = OpenAI(
      api_key=os.getenv("API_KEY"),
      base_url="https://api.friendli.ai/dedicated/v1",
  )

  chat_completion = client.chat.completions.create(
      model="YOUR_ENDPOINT_ID",
      messages=[
          {
              "role": "user",
              "content": "Tell me how to make a delicious pancake"
          }
      ]
  )
  print(chat_completion.choices[0].message.content)
  ```

  ```python Friendli Python SDK theme={null}
  import os
  from friendli import SyncFriendli

  client = SyncFriendli(
      token=os.getenv("API_KEY"),
  )

  chat_completion = client.dedicated.chat.complete(
      model="YOUR_ENDPOINT_ID",
      messages=[
          {
              "role": "user",
              "content": "Tell me how to make a delicious pancake"
          }
      ]
  )

  print(chat_completion.choices[0].message.content)
  ```

  ```sh curl theme={null}
  curl -X POST https://api.friendli.ai/dedicated/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "X-Friendli-Team: $TEAM_ID" \
    -H "Authorization: Bearer $API_KEY" \
    -d '{
      "model": "YOUR_ENDPOINT_ID",
      "messages": [
        {
          "role": "user",
          "content": "Python is a popular"
        }
      ]
    }'
  ```
</CodeGroup>

<Note>
  For a more detailed tutorial for your usage, please refer to our tutorial for using [Hugging Face models](/guides/dedicated-endpoints/deploy-with-huggingface){/* and [W&B models](/guides/dedicated-endpoints/deploy-with-wandb)*/}.
</Note>