Route LLM requests with Anthropic, OpenAI, Gemini, Postgres, and Slack

by Oneclick AI Squad ✓ · 1 views · created 2026-10-01 · Engineering, AI Summarization

What this workflow does

This workflow has 27 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Postgres and Slack. It also calls api.anthropic.com and api.openai.com over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

1. Set - Fallback Config (Edit Fields (Set)): sets 14 fields: providerOrder, anthropicModel, openaiModel…
2. JS - Normalize Request (Code): runs custom JavaScript code
3. Postgres: run a query
4. JS - Build Provider Chain (Code): runs custom JavaScript code
5. JS - Select Provider (Code): runs custom JavaScript code
6. Switch: routes items into 3 branches
7. HTTP Request: calls api.anthropic.com (POST)
8. HTTP Request: calls api.openai.com (POST)
9. HTTP Request: calls an HTTP API (POST)
10. JS - Normalize & Validate (Code): runs custom JavaScript code

…plus 15 more steps. See the full node list below.

Services it uses

PostgresSlack

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

Before you upgrade to n8n 3.0

Nodes used (11)

• Manual Triggern8n-nodes-base.manualTrigger
• Webhookn8n-nodes-base.webhook
• Edit Fields (Set)n8n-nodes-base.set
• Coden8n-nodes-base.code
• Postgresn8n-nodes-base.postgres
• Switchn8n-nodes-base.switch
• HTTP Requestn8n-nodes-base.httpRequest
• Ifn8n-nodes-base.if
• Waitn8n-nodes-base.wait
• Slackn8n-nodes-base.slack
• Respond to Webhookn8n-nodes-base.respondToWebhook

From the author

Quick overview This workflow exposes a POST webhook that sends a prompt through a resilient LLM fallback chain (Anthropic, OpenAI, then Google Gemini), validates outputs against deterministic rules/JSON schema, logs all attempts to Postgres with a circuit…

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