---
date: 2025-07-18
title: AWS SDK Default Credential Provider Chain Support
description: Self-hosted deployments can now use the AWS SDK default credential provider chain for Amazon Bedrock LLM connections.
author: Hassieb
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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).

Self-hosted Langfuse deployments can now leverage the **AWS SDK default credential provider chain** when connecting to Amazon Bedrock for LLM operations inside the Langfuse platform (e.g. [playground](/docs/playground), [evals](/docs/scores/model-based-evals)).

**What's New**

Previously, self-hosted deployments required explicit AWS credentials (access key and secret key) to connect to Amazon Bedrock. Now you can use any of the AWS SDK's default credential sources:

- **IAM roles** for EC2 instances
- **ECS task roles** for containerized deployments
- **AWS profiles** from `~/.aws/credentials`
- **Environment variables** (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`)

**Benefits**

- **Simplified deployment**: No need to manage explicit credentials in your configuration
- **Enhanced security**: Follow AWS security best practices with IAM roles
- **Flexible authentication**: Use the most appropriate credential method for your deployment environment
- **Seamless integration**: Works with existing AWS infrastructure and security policies

**Usage**

When configuring Amazon Bedrock connections in your self-hosted deployment, you can now omit the explicit AWS credentials and let the SDK automatically discover them through the default provider chain.

**Availability**

This feature is available from Langfuse platform image version 3.83.0

**Learn More**

- [AWS SDK Credential Provider Chain](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/setting-credentials-node.html)
- [Langfuse LLM playground](/docs/playground)
- [Langfuse evaluations](/docs/scores/model-based-evals)

<!-- 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/2025-07-18-aws-sdk-default-credential-provider.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>.