# Use Anthropic Models

Use Anthropic models through Anthropic API in your pipelines.

***

You can use Anthropic's embedding and ranking models as well as LLMs. For a full list of supported models, see [Anthropic documentation](https://docs.anthropic.com/en/docs/about-claude/models).

## Prerequisites

You need an active Anthropic API key to use Anthropic's models. 

## Use Anthropic Models

First, connect <ProductName /> to Anthropic through the Integrations page. You can set up the connection for a single workspace or for the whole organization:
<AddIntegration />

Then, add a component that uses an Anthropic model to your pipeline. Here are the available components:

- [AnthropicVertexChatGenerator](/docs/reference/pipeline-components/integrations/google-vertex/AnthropicVertexChatGenerator.mdx): Generates text using Anthropic models on Google Vertex.
- [LLM](/docs/reference/pipeline-components/ai/LLM.mdx): Generates text using Anthropic models.

:::info Legacy
The previously used `AnthropicChatGenerator` and `AnthropicGenerator` are now legacy components. Use the `LLM` component instead.
:::

Click the component card to open the configuration panel and choose the model and other settings.

## Use Anthropic Models on Azure

To use Anthropic models on Azure, create a custom model definition and choose *Anthropic on Azure* as the model provider:
1. Depending on the scope of the custom model definition:
  - For a workspace-wide custom model definition, go to _Workspace>Integrations_ and click **Configure** on the Custom Models Card.
  - For an organization-wide custom model definition, go to _Organization>Integrations_ and click **Configure** on the Custom Models Card.
2. Click **Add model**.
3. Enter the following details:
  - *Model name*: A descriptive name for your custom model
  - *Provider*: Choose *Anthropic on Azure*.
4. Configure the YAML settings:
  - Chat Generator: Define the component configuration including the endpoint or resource, and model name.
  - Model Parameters: Specify model parameters, like temperature and max output tokens. You can choose a model to copy its default parameters and adjust them as needed.
6. Save your changes.

The model is now available in the model list when you add an Anthropic component to your pipeline.

## Related Information

- [Add Custom Model Definitions](/docs/how-to-guides/managing-access/add-custom-model-definitions.mdx)
- [LLM](/docs/reference/pipeline-components/ai/LLM.mdx)