Use n8n with InferFoundry¶

n8n is an open-source workflow automation platform. Connect it to InferFoundry to use Claude and other models in your automations, with your data processed in your chosen region.

Prerequisites¶

n8n running (installation guide)
An InferFoundry API key and endpoint from portal.dev.if-service.ai

Connect InferFoundry as an OpenAI-compatible provider¶

n8n's AI nodes use OpenAI-compatible APIs. InferFoundry's endpoint is a drop-in replacement.

In the n8n UI¶

Go to Settings → Credentials
Click Add Credential and search for OpenAI API
Fill in:

Field	Value
Base URL	`https://gateway.dev.if-service.ai/v1`
API Key	your InferFoundry API key

Save and test the credential

In a workflow node¶

When you add an AI node (e.g. AI Agent, Chat Model, Text Classifier):

Select OpenAI Chat Model as the model type
Choose the credential you just created
Set the model name (e.g. claude-sonnet-4-5)

See Available Models for the full list.

Connect pgvector (optional)¶

For RAG workflows, InferFoundry provides a managed pgvector database. To get pgvector credentials for your workspace, contact ai.support@amazee.io.

In n8n, use the Postgres node or Vector Store node with:

Field	Value
Host	`vectordb.dev.if-service.ai`
Port	`5432`
Database	your database name
Username	your username
Password	your password
SSL	required

Embeddings¶

To generate embeddings in n8n (e.g. for a vector store workflow), use the Embeddings OpenAI node with your InferFoundry credential and model set to amazon.titan-embed-text-v2:0.

Troubleshooting¶

"Model not found" error: Use the exact model ID from Available Models. n8n does not auto-complete model names for custom providers.
Credential test fails: Make sure the Base URL ends in /v1. The test call hits /v1/models — verify that URL returns a valid response with your key.
Requests timing out on long automations: Increase the timeout in your n8n node settings. Long-running tasks (document processing, multi-step chains) may need 120–300 seconds.