---
date: 2026-06-02
title: Use OpenAI models on Amazon Bedrock
description: Connect Bedrock-hosted OpenAI models to Langfuse LLM Connections with OpenAI Responses API support.
author: tobiaswochinger
canonical: /docs/administration/llm-connection
---

> **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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 canonical documentation for this feature (https://langfuse.com/docs/administration/llm-connection) and the API/SDK reference (https://api.reference.langfuse.com).

Langfuse LLM Connections now support OpenAI-compatible Responses API endpoints. You can use OpenAI models hosted on Amazon Bedrock, including `openai.gpt-5.5` and `openai.gpt-5.4`, in the Langfuse Playground, LLM-as-a-Judge evaluators, and prompt experiments.

Create an OpenAI LLM Connection, enable **Use Responses API**, add your Bedrock API key, configure the Bedrock Mantle endpoint for your AWS Region, and add the Bedrock model IDs you want to use.

## Setup [#setup]

In **Project Settings** > **LLM Connections**, add a new connection with:

- **Provider**: OpenAI
- **API Key**: your Amazon Bedrock API key
- **Base URL**: `https://bedrock-mantle.<aws-region>.api.aws/openai/v1`
- **Custom model names**: `openai.gpt-5.5`, `openai.gpt-5.4`, or another OpenAI model ID available in your Bedrock account
- **Use Responses API**: enabled

## Learn more [#learn-more]

- [LLM Connections](/docs/administration/llm-connection)
- [Amazon Bedrock API keys](https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html)
- [Inference using Responses API on Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/bedrock-mantle.html)
- [OpenAI GPT-5.5 and GPT-5.4 models on Amazon Bedrock](https://aws.amazon.com/blogs/aws/get-started-with-openai-gpt-5-5-gpt-5-4-models-and-codex-on-amazon-bedrock/)

<!-- 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/2026-06-02-openai-on-amazon-bedrock.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>.