n8n AI Agent with an uncensored model
To run n8n AI Agent with an uncensored model, put a custom Base URL in the OpenAI credential and set an abliterated model in the OpenAI Chat Model sub-node.
API Key <your Silk Compute key>
Base URL https://api.silkcompute.com/v1- OpenAI format
- Base URL in the OpenAI credential
- Anthropic format
- Base URL in the Anthropic credential
- Tool calling
- Tool sub-nodes
- Streaming
- Enable Streaming
- Browser use
- Not documented
- Memory
- Simple Memory
Labels link to n8n AI Agent's own docs, read November 18, 2026. Compare all 11
Point the agent only at systems, files and accounts you own or are allowed to test.
Deploy it
3 steps, with Kimi K3.1 Pro.
- 01
Create an OpenAI credential. Its Base URL field defaults to https://api.openai.com/v1. Replace it.
See OpenAI credential above - 02
Build the agent. Add an AI Agent node, attach an OpenAI Chat Model sub-node with this credential, and set Model to the id below.
SettingsModel: kimi-k3.1-pro-uncensored - 03
Add memory and tools. The node needs at least one tool sub-node. Simple Memory keeps the chat.
SettingsAI Agent Chat Model OpenAI Chat Model Memory Simple Memory Tool HTTP Request (your own API)
Which model
Kimi K3.1 Pro
Long runs, image and video input
- Id
kimi-k3.1-pro-uncensored- Per 1M in / out
- $3.50 / $8.00
DeepSeek V4.1 Flash 1017
Value, image input
- Id
deepseek-v4.1-flash-1017-uncensored- Per 1M in / out
- $0.24 / $0.90
The config uses the Silk Compute base URL, which serves both models with a 1,048,576-token context.