Choose the model behind each automation step
Ops & admin automation · Dev, web & IT · checked 2026-10-16
Call a model through its API from Make, n8n or your own code, picking a model per step by cost, speed or policy. Gab AI’s OpenAI-compatible API is one option; Claude, ChatGPT, Gemini and Grok APIs work the same way.
Independent review. IonBin has no partnership with any tool on this page and was not paid for this page. Our evaluation is our own, based on public documentation and our research. Product names are trademarks of their owners and are used for identification only. How disclosure works.
Goal
Control which model handles which job, and swap models without rebuilding the workflow.
Connects through: API
Steps
| # | Who | What happens | How | Status |
|---|---|---|---|---|
| 1 | n8n (or Make) | Sends the step’s prompt to a model API (HTTP or a built-in AI node) n8n’s HTTP Request node can call any REST API, including OpenAI-compatible model endpoints. | API | Confirmed · source ↗ |
| 2 | Gab AI (example) | Answers through its OpenAI-compatible API One OpenAI-compatible endpoint (https://gab.ai/v1) reaches models including GPT, Claude, Gemini and DeepSeek; Plus subscribers get 10,000 requests a day, and Gab AI says API calls aren’t used for training. | API | Confirmed · source ↗ |
| 3 | You | Test outputs on real examples before switching a live step; review costs monthly | Human step | Confirmed |
Confirmed means the vendor documents it (linked). It doesn't mean IonBin has tested it. AI-platform and human steps need no source.
You approve model changes on live workflows.
Still to verify: Each model’s data-retention terms.
Starter prompt
Goal: Control which model handles which job, and swap models without rebuilding the workflow. Tools involved: n8n (or Make), Gab AI (example). Work step by step, show me each draft or proposed change, and wait for my approval before anything is sent, published, signed, filed or changed in a live system.
Assembled from this page’s goal and steps. Paste it into your AI platform and adjust it to your situation.
Tools in this workflow
Which AI platforms can run it
| Platform | Status | Why |
|---|---|---|
| Claude (incl. Claude Code) | Confirmed | Every MCP and API step is documented for this platform. |
| OpenAI Codex | Confirmed | Every MCP and API step is documented for this platform. |
| Google Antigravity | Confirmed | Every MCP and API step is documented for this platform. |
| ChatGPT | Confirmed | Every MCP and API step is documented for this platform. |
| Gemini | To verify | n8n (or Make): code execution to verify (or run it in Make or n8n); Gab AI (example): code execution to verify (or run it in Make or n8n) |
| Perplexity | To verify | n8n (or Make): code execution to verify (or run it in Make or n8n); Gab AI (example): code execution to verify (or run it in Make or n8n) |
Computed from the MCP and API steps only: "Confirmed" needs the tool's docs to name the platform and the platform to support the connection. Browser, upload and human steps work from any platform.
Sources
- Gab AI API docs · Gab AI · official · accessed 2026-10-16
- HTTP Request node · n8n · official · accessed 2026-10-16
To verify Each model’s data-retention terms
Related workflows
No affiliate links on this page. No paid placements in workflows. How IonBin makes money.