# Anyscale

[Anyscale](https://www.anyscale.com/endpoints) provides fast, cost-efficient, serverless APIs for LLM serving and fine tuning

## Preparation[​](https://doc.chathub.gg/custom-chatbots/openai#preparation) <a href="#preparation" id="preparation"></a>

Sign up to Anyscale and generate an API key from <https://app.endpoints.anyscale.com/console/credentials>.

## Configuration <a href="#configuration" id="configuration"></a>

<figure><img src="https://3481753452-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FzYU2cjsYvY3seDzkySsN%2Fuploads%2FiPJL1muUGXq5Zbk5hS55%2Fimage.png?alt=media&#x26;token=22fcb3de-95bc-4591-ab4f-e4c46bb39c5b" alt=""><figcaption></figcaption></figure>

We're using the `mistralai/Mixtral-8x7B-Instruct-v0.1` model in this example.

You can find all the available models from Anyscale website: <https://docs.endpoints.anyscale.com/category/supported-models>