> 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/gcp-vertex-ai-support.md).

# GCP Vertex AI Support

An Agent SDK can run against GCP Vertex AI as its model backend, alongside the existing AWS Bedrock, Azure AI Foundry, and direct Anthropic API options.

As with the other provider options, this is configured on the Agent SDK's own deployment rather than in AI Admin — see [LLM Models](/docs/armor/agents/llm-models.md) for how provider selection works generally. To route an Agent SDK through Vertex AI, set on its container:

* **`CLOUD_PROVIDER=GCP`**
* **`GOOGLE_CLOUD_PROJECT`** — the GCP project ID Vertex AI calls are billed/scoped to
* **`CLOUD_ML_REGION`** (optional) — defaults to `global` if unset

The preferred authentication method is **Workload Identity Federation** on GKE, which avoids managing a long-lived API key: the GKE service account needs Workload Identity enabled and an IAM binding granting it Vertex AI access.

{% hint style="info" %}
Requests made through this path are automatically tagged with DuploCloud's GCP partner attribution, identifying them as originating through DuploCloud's integration — this happens transparently and needs no configuration.
{% endhint %}

If an Agent SDK's deployment also has `ANTHROPIC_API_KEY` or Azure Foundry variables set, those take priority — Vertex AI is only used when neither of those is configured and `CLOUD_PROVIDER=GCP` is set. With none of these set, an Agent SDK falls back to AWS Bedrock by default.


---

# 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/gcp-vertex-ai-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.