Route AI prompts between Anthropic, Google Gemini, Mistral and OpenAI

by Triple 8 Labs ✓ · 77 views · created 2026-06-13 · Engineering, AI Summarization

What this workflow does

This workflow has 12 nodes and runs when another workflow calls it. It uses only n8n's built-in nodes. It also calls api.anthropic.com, api.mistral.ai and api.openai.com over HTTP.

How it runs

Trigger: When another workflow calls it.

1. CONFIG (Edit Fields (Set)): sets 8 fields: DEFAULT_PROVIDER, DEFAULT_ANTHROPIC_MODEL, DEFAULT_GOOGLE_MODEL…
2. Normalize Input (Code): runs custom JavaScript code
3. Validate Token Budget (Code): runs custom JavaScript code
4. Which Provider? (Switch): routes items into 4 branches
5. Anthropic Chat (HTTP Request): calls api.anthropic.com (POST)
6. Google Chat (HTTP Request): calls an HTTP API (POST)
7. Mistral Chat (HTTP Request): calls api.mistral.ai (POST)
8. OpenAI Chat (HTTP Request): calls api.openai.com (POST)
9. Merge Provider Response (Code): runs custom JavaScript code
10. Cost Tracking (Code): runs custom JavaScript code

…plus 1 more step. See the full node list below.

HTTP calls to: api.anthropic.com, api.mistral.ai, api.openai.com

Before you upgrade to n8n 3.0

Nodes used (5)

• Execute Workflow Triggern8n-nodes-base.executeWorkflowTrigger
• Edit Fields (Set)n8n-nodes-base.set
• Coden8n-nodes-base.code
• Switchn8n-nodes-base.switch
• HTTP Requestn8n-nodes-base.httpRequest

From the author

Quick overview A reusable sub-workflow that routes text prompts to Anthropic Claude, Google Gemini, Mistral, or OpenAI and returns a normalised response - including estimated token usage and cost - regardless of the provider. Drop it into any workflow via…

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