Route chat prompts to free LLMs with Agnes AI, NVIDIA, and Ollama

by Daniele Crupi ✓ · 68 views · created 2026-08-13 · Personal Productivity, AI Chatbot

What this workflow does

This AI workflow has 12 nodes and runs when someone submits an n8n form (“Free AI Model Playground”). Along the way it connects Ollama Chat Model. It also calls apihub.agnes-ai.com, host.docker.internal:11434 and integrate.api.nvidia.com over HTTP.

How it runs

Trigger: When someone submits an n8n form (“Free AI Model Playground”).

1. Select AI Model (Switch): routes items into 4 branches
2. Agnes Text (HTTP Request): calls apihub.agnes-ai.com (POST)
3. OLLAMA LOCAL FREE (HTTP Request): calls host.docker.internal:11434 (POST)
4. NVIDIA API FREE (HTTP Request): calls integrate.api.nvidia.com (POST)
5. AI Agent: runs an AI agent, with model: Ollama Cloud Model
6. Prepare Agnes AI Response (Edit Fields (Set)): sets 1 field: response
7. Prepare Ollama Local Response (Edit Fields (Set)): sets 1 field: response
8. Prepare NVIDIA API Response (Edit Fields (Set)): sets 1 field: response
9. Prepare Ollama Cloud Response (Edit Fields (Set)): sets 1 field: response
10. Display AI Response (n8n Form): shows the next form page

Services it uses

Ollama Chat Model

HTTP calls to: apihub.agnes-ai.com, host.docker.internal:11434, integrate.api.nvidia.com

Before you upgrade to n8n 3.0

Nodes used (7)

• Ollama Chat Model@n8n/n8n-nodes-langchain.lmChatOllama
• n8n Form Triggern8n-nodes-base.formTrigger
• Switchn8n-nodes-base.switch
• Edit Fields (Set)n8n-nodes-base.set
• n8n Formn8n-nodes-base.form
• AI Agent@n8n/n8n-nodes-langchain.agent
• HTTP Requestn8n-nodes-base.httpRequest

From the author

Quick overview This workflow provides a simple AI playground where users can choose between several free LLM options—NVIDIA Integrate chat completions, Agnes AI chat completions, a local Ollama model, or an Ollama Cloud model via a LangChain agent with…

View the original on n8n.io → Check your own copy