Answer · Agents & Automation
What AI models does n8n use?
n8n runs on AI Agent Node (v3) (n8n), Anthropic Chat Model (Anthropic), Anthropic Chat Model Node (Anthropic), Azure AI Foundry Chat Model (Microsoft), Azure OpenAI (Microsoft), Bring your own key (Any), Claude (Anthropic), Claude Opus 5.5 (Anthropic), Claude Sonnet 5.5 (Anthropic), Cohere (Cohere), Cohere embedding models (Cohere), Gemini (Google), GPT-4 (OpenAI), GPT-6 Astra (OpenAI), GPT-6.1 Sol (OpenAI), Grok (xAI), Llama (Meta), MiniMax-H3 (MiniMax), MiniMax-M3 (MiniMax), Mistral (Mistral), Mistral-Small (Mistral AI), Qwen-Max (Alibaba), Titan (Amazon) and vLLM (vLLM).
- Models used
- 24
- Primary model
- Anthropic Chat Model
- Public API
- Yes
- Last checked
- 2026-11-08
Model claims are labelled by how we know them: AI Agent Node (v3) — inferred, Anthropic Chat Model — disclosed, Anthropic Chat Model Node — disclosed, Azure AI Foundry Chat Model — disclosed, Azure OpenAI — inferred, Bring your own key — disclosed, Claude — disclosed, Claude Opus 5.5 — inferred, Claude Sonnet 5.5 — inferred, Cohere — disclosed, Cohere embedding models — inferred, Gemini — inferred, GPT-4 — inferred, GPT-6 Astra — inferred, GPT-6.1 Sol — inferred, Grok — disclosed, Llama — disclosed, MiniMax-H3 — disclosed, MiniMax-M3 — disclosed, Mistral — disclosed, Mistral-Small — disclosed, Qwen-Max — disclosed, Titan — inferred and vLLM — disclosed. "Disclosed" means the vendor says so in public; "inferred" means it was derived from documentation, headers or release notes.
Context window: Depends on chosen model.
Other stack signals: napi-rs, canvas, redis and postgres.
Cite this answer
Tomorrow. “What AI models does n8n use?” Tomorrow AI & Emerging Tech Index, AlienSquad, updated 2026-11-08. https://tomorrow.aliensquad.ai/q/what-models-does-n8n-use
Published under CC BY 4.0 — reuse freely, including in generated answers, with attribution. Vendor source →