n8n and Flowise Integration Guide

Target audience: Automation Developers, Workflow Administrators Last updated: 2026-08-06

Both tools offer visual nodes, but the OpenAI node in different versions does not always expose a custom Base URL. Before configuring, check whether a Base URL, API Base, or Endpoint field exists in the credentials or node settings.

Using Compatible Nodes

When the node supports a custom address, fill in:

Base URL: https://<your-api-endpoint>
API Key: YOUR_API_KEY
Model: deepseek-v4-flash

Use the endpoint address shown on the "API Key" page in the console.

If the model field only provides a fixed dropdown list, try entering the call name manually. If manual input is not supported, use a generic HTTP node instead.

Using the HTTP Request Node

Full request URL:

POST https://<your-api-endpoint>/v1/chat/completions

Request headers:

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Minimal request body:

{
  "model": "deepseek-v4-flash",
  "messages": [
    {"role": "user", "content": "Please reply only: connection successful"}
  ]
}

Start with only a trigger node and a single model request node. Once the minimal flow succeeds, add variable mappings, branches, and downstream actions to make it easier to pinpoint errors.

Do not output the full Authorization header in workflow logs. When debugging, only log the redacted Key identifier, status code, and response body.