Skip to content

n8n Integration

Connect n8n automation workflows to AWS Bedrock models through stdapi.ai's OpenAI-compatible interface. Existing OpenAI templates from the n8n marketplace work out of the box—simply point them to your stdapi.ai instance and access AWS Bedrock models.

About n8n

🔗 Links: Website | GitHub | Documentation

n8n is a powerful workflow automation platform that enables you to connect any app with an API to build intelligent automations. With its intuitive visual interface, you can create complex AI-powered workflows without writing code, connecting AWS Bedrock models to 400+ services including Slack, Google Sheets, Salesforce, and more.

Key Features:

  • ⭐ 50,000+ GitHub stars - Leading open-source workflow automation platform
  • 400+ integrations - Pre-built nodes for popular services and APIs
  • Visual no-code builder - Drag-and-drop interface with JavaScript customization
  • Self-hosted or cloud - Deploy on your infrastructure or use n8n Cloud
  • AI-native platform - Built-in OpenAI nodes work instantly with AWS Bedrock via stdapi.ai
  • Template marketplace - Thousands of pre-built workflows ready to use

Why n8n + stdapi.ai?

  • Use Existing OpenAI Templates
    stdapi.ai works with n8n's OpenAI nodes. Thousands of marketplace templates and workflows designed for OpenAI run on AWS Bedrock—zero modifications needed.

  • Access AWS Bedrock Models
    Claude 4.6+, Nova 2, Llama 4, DeepSeek v3.2, Stable Diffusion, and 80+ models available in n8n workflows. Switch models without changing automation logic.

  • Automate Business Processes
    Connect AWS Bedrock AI to Slack, Salesforce, Google Workspace, databases, and 400+ services. Build intelligent automation with no-code drag-and-drop.

  • Enterprise Data Control
    All AI processing stays in your AWS account. Self-host n8n and stdapi.ai for complete data sovereignty and compliance.

  • Pay-Per-Use Pricing
    No OpenAI subscriptions or per-automation fees. Pay only AWS Bedrock rates for actual AI usage in your workflows.

%%{init: {'flowchart': {'htmlLabels': true}} }%%
flowchart LR
  n8n["<img src='../styles/logo_n8n.svg' style='height:64px;width:auto;vertical-align:middle;' /> n8n"] --> stdapi["<img src='../styles/logo.svg' style='height:64px;width:auto;vertical-align:middle;' /> stdapi.ai"]
  stdapi --> bedrock["<img src='../styles/logo_amazon_bedrock.svg' style='height:64px;width:auto;vertical-align:middle;' /> AWS Bedrock"]
  stdapi --> transcribe["<img src='../styles/logo_amazon_transcribe.svg' style='height:64px;width:auto;vertical-align:middle;' /> AWS Transcribe"]
  stdapi --> polly["<img src='../styles/logo_amazon_polly.svg' style='height:64px;width:auto;vertical-align:middle;' /> AWS Polly"]

✅ Prerequisites

What You'll Need

  • ✓ stdapi.ai deployed - See deployment guide
  • ✓ Your stdapi.ai URL - e.g., https://api.example.com
  • ✓ Your API key - From Terraform output or configuration
  • ✓ n8n instance - Self-hosted or n8n Cloud

⚙️ Configuration

🔑 Set Up Your Credentials

The foundation of any n8n integration is configuring your API credentials. This one-time setup unlocks all AI capabilities.

Creating Your stdapi.ai Credential

In your n8n interface:

  1. Navigate to Credentials menu
  2. Click Create Credential
  3. Search and select "OpenAI" in the credential list
  4. Configure the following fields: 
    API Key:  YOUR_STDAPI_KEY
Base URL: https://YOUR_STDAPI_URL/v1

What This Does

By setting a custom Base URL, you redirect all OpenAI API calls to your stdapi.ai instance. n8n will use this credential to authenticate and route requests to Amazon Bedrock models instead of OpenAI's servers.

🔧 Configure Nodes

For each node, first select the credentials you previously created in the node parameters. Then, select the model you want to use. If you want to use a model that is not listed, you can enter its ID as an expression in the Model parameter.

💬 Chat completions

Enables: Text generation and conversational AI in workflows.

Supported Node

OpenAI Chat Model

  • Model can be selected directly in the Model parameter
  • ⚠️ Important: Use Responses API parameter must be unchecked (Responses API is not supported yet by stdapi.ai)

n8n calls POST /v1/chat/completions (see Chat Completions API), so the model must be a text/chat-capable model from the correct family.

📚 Embeddings

Enables: Vector embeddings for semantic search and RAG workflows.

Supported Node

Embeddings OpenAI

  • Model can be selected directly in the Model parameter

n8n calls POST /v1/embeddings (see Embeddings API), so the model must be an embeddings-capable model from the correct family.

🎨 Image generation

Enables: Text-to-image creation in workflows.

Supported Node

OpenAI/Generate an image

  • Model ID can be entered as expression in the Model parameter

n8n calls POST /v1/images/generations (see Images Generations API), so the model must be an image-generation model from the correct family.

🖼️ Image editing

Enables: Image transformation and editing in workflows.

Supported Node

OpenAI/Edit image

  • Model ID can be entered as expression in the Model parameter

n8n calls POST /v1/images/edits (see Images Edits API), so the model must be an image-editing model from the correct family.

🔊 Audio generation (TTS)

Enables: Text-to-speech audio generation in workflows.

Supported Node

OpenAI/Generate audio

  • Model ID can be entered as expression in the Model parameter
  • Or use OpenAI model names directly: tts-1 and tts-1-hd work by default thanks to built-in model aliases

n8n calls POST /v1/audio/speech (see Audio Speech API), so the model must match the text-to-speech modality and family.

🎤 Audio transcription (STT)

Enables: Speech-to-text transcription in workflows.

Supported Node

OpenAI/Transcribe a recording

  • Works out of the box with OpenAI's whisper-1 model name
  • The model alias automatically maps to amazon.transcribe

n8n calls POST /v1/audio/transcriptions (see Audio Transcriptions API), so the model must match the speech-to-text modality.

⚠️ Unsupported Nodes

The following nodes are not yet supported:

Known Limitations

  • OpenAI/Message a model — Requires Responses API (not supported yet by stdapi.ai). Use OpenAI Chat Model instead.
  • OpenAI/Analyze image — Requires Responses API (not supported yet by stdapi.ai). Use OpenAI Chat Model instead.