AI Models in n8n
The AI models you can choose inside n8n, grouped by type. Each model page shows the other apps that offer it, so you can compare prices for the same model.
Updated September 2026 · 10 listings
How to pick a model in n8n
Pick the model from the app's model selector (often under the prompt box or in settings). Credit costs usually differ per model, and some apps only offer the newest models on paid plans.
Claude Fable 5.1 🧠 ModelFreemium
Anthropic's Claude models (Fable 5.1, Opus 5.5, Sonnet 5, Haiku 4.5) with 1M-token context
GPT Image 2.5 🧠 ModelFreemium
OpenAI's image model behind ChatGPT Images, with 4K output and up to 16 reference images
GPT-6 Astra 🧠 ModelFreemium
OpenAI's GPT-6 family (Astra, Sol, Luna) behind ChatGPT and the OpenAI API
Gemini 3.1 Pro 🧠 ModelFreemium
Google's Gemini models (3.1 Pro, 3.8 Flash) in the Gemini app, NotebookLM and the Gemini API
Whisper large-v3-turbo 🧠 ModelOpen source
OpenAI's open-source speech recognition for transcripts and subtitles in 99 languages
DeepSeek V4 Pro 🧠 ModelOpen source
DeepSeek's MIT-licensed V4 models with 1M-token context and very low API prices
Qwen3.8 🧠 ModelOpen source
Alibaba's Qwen3.8 family, from Apache-2.0 open weights (27B to 2.4T) to the hosted Qwen3.8-Max
Grok 4.7 🧠 ModelFreemium
xAI's Grok models, built into Grok and X, with a 500K-token context on Grok 4.7
Mistral Medium 3.5 🧠 ModelOpen source
Mistral AI's European models: open-weight Medium 3.5, Large 3 and Small 4, used in Mistral Vibe
Meta Muse Spark 1.3 🧠 ModelFreemium
Meta's model line: closed Muse Spark 1.3, open Muse Glimmer 30B and the older open Llama 4
More for n8n
🧩 Workflows for n8n (2) 🔌 MCP Servers for n8n (29) n8n review