---
date: 2026-11-18
title: Connect Amazon Bedrock with an IAM role
description: Amazon Bedrock LLM connections can assume an IAM role in your AWS account instead of using stored access keys or API keys. Available on Enterprise.
author: Tobias Wochinger
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

Langfuse can now call your Amazon Bedrock models by assuming an IAM role in your AWS account, so you don't need to store long-lived AWS credentials in Langfuse. Use it for:

- Testing prompts against Bedrock models in the [Playground](/docs/prompt-management/features/playground) and in prompt experiments.
- [LLM-as-a-Judge evaluators](/docs/evaluation/evaluation-methods/llm-as-a-judge) that score traces and experiments with Bedrock models.
- [Organization connections](/docs/administration/llm-connection#organization-and-project-connections) that every project inherits, with one role and one external ID.

Each connection gets its own external ID, and every session can only invoke Bedrock models, even if your role allows more. IAM role authentication is available on Langfuse Cloud Enterprise and on self-hosted Enterprise. Self-hosted deployments also need [`LANGFUSE_CROSS_ACCOUNT_ROLE_ARN`](/self-hosting/configuration#cross-account-role) set.

- [Authenticate Bedrock with an IAM role](/docs/administration/llm-connection#bedrock-iam-role)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2026-11-18-bedrock-iam-role-auth.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx @langfuse/cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.
