> For the complete documentation index, see [llms.txt](https://docs.duplocloud.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.duplocloud.com/docs/armor/agents/direct-anthropic-api-support.md).

# Direct Anthropic API Support

An Agent SDK can call the Anthropic API directly, instead of routing through AWS Bedrock, GCP Vertex AI, or Azure AI Foundry.

This isn't something you turn on in the app — as noted in [LLM Models](/docs/armor/agents/llm-models.md), which underlying provider an Agent SDK actually runs on is determined by environment variables on that Agent SDK's own deployment, not by any setting in AI Admin. To use the Anthropic API directly, set an `ANTHROPIC_API_KEY` on the Agent SDK's container. No other provider-related variable is needed.

{% hint style="info" %}
Provider selection is per-Agent-SDK, not a single platform-wide switch. Since every registered Agent SDK is its own deployed service, different Agent SDKs in the same portal can run against different providers at the same time — one calling Anthropic directly while another runs on Bedrock, for example.
{% endhint %}

If an Agent SDK's deployment has more than one provider's variables set, `ANTHROPIC_API_KEY` takes priority over GCP Vertex AI or Azure Foundry configuration — direct Anthropic API access wins whenever a key is present.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.duplocloud.com/docs/armor/agents/direct-anthropic-api-support.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.