gpuos

Integration · Automation

Use n8n AI nodes with a self-hosted LLM

Run n8n AI workflows and agents on your own GPUs with an OpenAI credential pointing at gpuos.

Base URL
https://gpuos.si/v1
API key
gpuos_key_… from the dashboard
Model
a catalog id, e.g. qwen3-32b

Create the credential

  1. In n8n, create a new OpenAI credential.
  2. Paste your gpuos key as the API key.
  3. Set Base URL to https://gpuos.si/v1.
  4. Use the credential in the OpenAI Chat Model node of an AI Agent or Basic LLM Chain, and type the model id, for example qwen3-32b.

Give n8n its own gpuos key with a monthly token quota, so a runaway workflow cannot use up your GPUs.

Official documentation: n8n.io

Questions

Can n8n agents call tools with a self-hosted model?
Yes, with models that support function calling, such as GLM-4 32B or Qwen3 32B.
Does it work with self-hosted n8n?
Yes. n8n only needs outbound HTTPS access to gpuos.si.

Related

Use n8n with models on your GPUs

Free for one GPU. Connect a machine, deploy a model, then paste the base URL and your key.

Join early accessRead the quickstart