> For the complete documentation index, see [llms.txt](https://docs.flxbl.io/flxbl/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flxbl.io/flxbl/sfp-server/configuring-ai-providers/claude-on-amazon-bedrock.md).

# Claude on Amazon Bedrock

codev's AI features — architecture analysis, validation error analysis, and AI-assisted reviews — run through an AI provider you connect once, in the codev UI. You don't edit config files or set environment variables by hand; you add the provider under **Settings → Integrations** and codev wires it into the analysis engine for you.

This page covers connecting **Claude on Amazon Bedrock**, for organizations that run their model traffic and billing through AWS.

## Connect an AI provider in codev

1. In codev, open **Settings → Integrations**.
2. Find the **AI Providers** section.
3. Pick a provider card and click **Connect**.
4. Follow the in-dialog instructions to paste your credential, then **Save**.

<figure><img src="/files/px7Uaap9nzTdu4J23Qlq" alt="The AI Providers section of Settings -> Integrations, showing provider cards including Anthropic, OpenAI, Google AI, GitHub Copilot, and Amazon Bedrock"><figcaption><p>The <strong>AI Providers</strong> section under <strong>Settings → Integrations</strong>. Each card connects one provider.</p></figcaption></figure>

That's it — the next AI command (for example an architecture analysis from the **Analysis** page) uses the connected provider. To confirm it works, run an analysis and check that a real result comes back.

{% hint style="info" %}
If you already have a direct **Anthropic API key**, the **Anthropic (Claude)** card is the fastest way to use Claude — connect it and you're done. The Bedrock path below is for organizations that have licensed Claude through AWS and want model traffic and billing to stay inside their AWS account.
{% endhint %}

## Claude on Amazon Bedrock

There are two parts: first you enable Claude in your **AWS account** (one-time AWS-side setup), then you **connect it in codev**.

### Step 1 — Get Claude working in your AWS account

**1a. Submit the one-time Anthropic use-case form.**

* In the AWS Console, open **Amazon Bedrock** and go to the **Model catalog**.
* Open a Claude model and follow the prompt to submit Anthropic's **use-case form** (your company name, website, use case). Anthropic reviews access requests, so this information is shared with Anthropic to approve your account. This is a one-time step per account.

**1b. Generate a Bedrock API key.**

* In the Amazon Bedrock console, go to **API keys** and generate a **long-term API key**.
* **Copy the key immediately — it is shown only once.** This is the credential codev needs (`AWS_BEARER_TOKEN_BEDROCK`), not an access-key/secret pair.

{% hint style="warning" %}
Use the latest Claude **Sonnet** via a **cross-region inference profile** — codev selects `us.anthropic.claude-sonnet-4-6` (region prefix `us.`) automatically. The bare `anthropic.claude-sonnet-4-6` model id fails for on-demand/serverless invocation ("on-demand throughput isn't supported"); the inference profile is required. Generate the key in **`us-east-1`** unless you have a specific reason to use another region.
{% endhint %}

{% hint style="info" %}
A region showing **"Anthropic (0)"** serverless models is expected, not an error — some regions only reach Sonnet through the `us.`/`global.` cross-region inference profile, which the catalog count doesn't include. Anthropic's own [Claude on Amazon Bedrock guide](https://docs.anthropic.com/en/api/claude-on-amazon-bedrock) is the authoritative reference for which models and regions are available.
{% endhint %}

### Step 2 — Connect it in codev

Once Claude is enabled and you have a Bedrock API key, connect it like any other provider: open **Settings → Integrations → AI Providers**, pick the **Amazon Bedrock** card, then enter your **AWS region** (for example `us-east-1`) and your **Bedrock API key**, and **Add Integration**. To make it the provider codev uses by default, leave **Set as default for this provider category** checked.

<figure><img src="/files/2Xf56JUBlwS8yEn9LlAK" alt="The Amazon Bedrock connect form showing the setup instructions and fields for AWS Region and Bedrock API Key"><figcaption><p>The <strong>Amazon Bedrock</strong> connect form: an <strong>AWS Region</strong> and a <strong>Bedrock API Key</strong>. codev picks the latest available Claude (Opus, then Sonnet) automatically — there's no model field to set.</p></figcaption></figure>

Once saved, the integration shows as **Active** under **Existing Integrations**.

<figure><img src="/files/FBbFO7kSK0FfXDY7aDaM" alt="The Amazon Bedrock integration page showing a connected Bearer Token integration marked Global and Active"><figcaption><p>A connected Amazon Bedrock integration — <strong>Global</strong> (available to all projects) and <strong>Active</strong>.</p></figcaption></figure>

## Verify

Once an AI provider is connected, run any AI command that uses it — a **domain insight** from the Workspace Explorer is a good check — and confirm a real model response comes back. For Bedrock specifically, a successful round-trip confirms the region, API key, model id, and your account's Claude access are all correct.

<figure><img src="/files/nXAOpxTLXwPkC2PQAt46" alt="A generated AI insight report for a domain, produced through the connected Amazon Bedrock integration"><figcaption><p>A domain insight generated through the connected Amazon Bedrock integration — codev resolves the connected provider automatically.</p></figcaption></figure>


---

# 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.flxbl.io/flxbl/sfp-server/configuring-ai-providers/claude-on-amazon-bedrock.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.