> For the complete documentation index, see [llms.txt](https://docs.tonic.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tonic.ai/fabricate/self-hosting-fabricate/configuring-fabricate/llm-provider.md).

# LLM provider

To support the many Fabricate features that rely on AI, you need to configure a connection to either:

* Amazon Bedrock
* Anthropic
* Azure AI Foundry
* Google Gemini Enterprise Agent Platform (formerly Vertex AI)

## Amazon Bedrock

To use Amazon Bedrock as your Claude LLM provider, in `.env`, uncomment and set the following:

{% code overflow="wrap" %}

```
FABRICATE_BEDROCK_REGION=   # Bedrock model region prefix to prepend to model IDs.
                            # For example, us.anthropic.claude-<model>.
                            # Default is global, to enable cross-region inference.
FABRICATE_BEDROCK_API_KEY=  # API key for Amazon Bedrock
FABRICATE_AWS_REGION= # AWS Region where Fabricate runs.
```

{% endcode %}

Note that `FABRICATE_AWS_REGION` is also used if you use Amazon S3 for cloud storage.

## Anthropic

To use Anthropic as your Claude LLM provider, in `.env`, uncomment and set the following:

```
FABRICATE_ANTHROPIC_BASE_URL=  # URL to connect to Anthropic
FABRICATE_ANTHROPIC_API_KEY=   # API key for Anthropic
```

## Azure AI Foundry

To use Azure AI Foundry as your Claude LLM provider, in `.env`, uncomment and set the following:

{% code overflow="wrap" %}

```
FABRICATE_AZURE_URI=        # Base URL for Azure AI Foundry Anthropic-compatible endpoint.
FABRICATE_AZURE_API_KEY=    # API key for the Azure AI Foundry endpoint.
```

{% endcode %}

## Google Gemini Enterprise Agent Platform

To use Google Gemini Enterprise Agent Platform (formerly Vertex AI) as your Claude LLM provider, in `.env`, uncomment and set the following:

{% code overflow="wrap" %}

```
FABRICATE_VERTEXAI_PROJECT_ID=  # Google Cloud project ID (required).
                                # Falls back to GOOGLE_CLOUD_PROJECT.
FABRICATE_VERTEXAI_GOOGLE_CLOUD_LOCATION=  # Vertex AI region (required).
                                           # Falls back to GOOGLE_CLOUD_LOCATION.
FABRICATE_VERTEXAI_SERVICE_ACCOUNT_KEY=  # Service account JSON key.
                                         # Falls back to VERTEXAI_SERVICE_ACCOUNT_KEY.
```

{% endcode %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.tonic.ai/fabricate/self-hosting-fabricate/configuring-fabricate/llm-provider.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.