Use n8n with the LLM gateway
Add the Manifest community node to an n8n workflow: connect the Manifest Chat Model to an AI Agent, or call Chat Completions and Responses directly. Requests route through the models and providers configured in the gateway. Use Manifest Cloud or point the credential at your own deployment.
11 models routed through the gateway over the last 30 days.
Why use n8n with the gateway
The community node turns the gateway into a reusable workflow step. Keep the routing policy there while n8n handles triggers, data preparation, and downstream automation.
- Plug the Manifest Chat Model into n8n AI Agents with streaming and native tool calling
- Use a native Manifest node instead of a generic HTTP Request
- Create Chat Completions and Responses API calls
- List the models available to the selected Manifest agent key
- Use model auto to apply the gateway routing
- Connect to Manifest Cloud or a self-hosted URL
Set up the Manifest node
Install n8n-nodes-manifest, add a Manifest
node, and create credentials with the values below.
n8n has reviewed and published the node as a verified community node. Install it from Settings > Community Nodes on n8n Cloud or self-hosted n8n.
Open the npm package or read n8n's community-node installation guide.
n8n-nodes-manifest
https://app.manifest.build
mnfst_YOUR_KEY
auto
Use the root Base URL without /v1. For a self-hosted gateway, replace it
with a URL reachable from the n8n process.
n8n tokens processed by the gateway
Models in use
|
# Model
|
Auth type | Tokens / last 30 days |
|---|---|---|
1.Ministral 8b Latest | API Key | 10 M |
2.Ministral 14b Latest | API Key | 9 M |
3.Ministral 8b 2512 | API Key | 3 M |
4.Gpt Oss 20b | API Key | 1 M |
5.Gpt Oss 120b | API Key | 1 M |
6.Ling 3.0 Flash Fin | API Key | 704 K |
7.Ministral 14b 2512 | API Key | 132 K |
8.Deepseek V4 Pro 0813 | API Key | 26 K |
9.Lfm 2.5 2.6b | API Key | 22 K |
10.Qwen3.8 27b | API Key | 21 K |
11.Qwen3.6 27b | API Key | 15 K |
