tokenlab

TokenLab Chat Model for n8n AI agent workflows (OpenAI-compatible)

Package Information

Released: this month
Downloads: 0 weekly / 0 monthly
Latest Version: 0.1.2
Author: TokenLab

Documentation

n8n-nodes-tokenlab

Use TokenLab chat models as the language model inside n8n AI Agent workflows.

This community node package contains two pieces:

  • Credential TokenLab API (tokenlabApi): a Base URL and an API key.
  • Sub-node TokenLab Chat Model (tokenLabChatModel): emits ai_languageModel, so any AI Agent node can use it as its chat model. The model list is loaded from TokenLab's GET /v1/models?category=chat.

Install

Community nodes have to be enabled on the instance first: Settings → Community Nodes → allow community nodes (N8N_COMMUNITY_PACKAGES_ENABLED=true).

Then open Settings → Community Nodes → Install, enter the package name and confirm:

n8n-nodes-tokenlab

For local development, run npm pack in this directory and install from the resulting tarball, or put the directory into ~/.n8n/custom/ and restart n8n.

Credential

  1. Create an API key in the TokenLab console: https://tokenlab.sh/dashboard/api?tab=keys&utm_source=npm-readme
  2. In n8n create a TokenLab API credential:
    • Base URL: https://api.tokenlab.sh by default; point it at your own proxy if you use one.
    • API key: the key from step 1.
  3. Save. The credential sends Authorization: Bearer <API key> and tests the connection with GET /v1/models?category=chat.

Workflow example

An AI Agent node with a TokenLab Chat Model sub-node connected on the ai_languageModel slot:

{
  "nodes": [
    {
      "parameters": {},
      "id": "agent-1",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.7,
      "position": [0, 0]
    },
    {
      "parameters": {
        "model": "claude-sonnet-5-5",
        "temperature": 0.7,
        "maxTokens": -1
      },
      "id": "model-1",
      "name": "TokenLab Chat Model",
      "type": "n8n-nodes-tokenlab.tokenLabChatModel",
      "typeVersion": 1,
      "position": [-240, 0],
      "credentials": {
        "tokenlabApi": { "id": "REPLACE_WITH_CREDENTIAL_ID", "name": "TokenLab API" }
      }
    }
  ],
  "connections": {
    "TokenLab Chat Model": {
      "ai_languageModel": [[{ "node": "AI Agent", "type": "ai_languageModel", "index": 0 }]]
    }
  }
}

Pick a model from the dropdown or type an ID directly, e.g. claude-sonnet-5-5, claude-haiku-4-5, qwen3.8-max. The full catalog and prices are on https://tokenlab.sh/en/models?utm_source=npm-readme

Step-by-step setup, the workflow example and cost notes are in the docs: https://tokenlab.sh/docs/en/integrations/n8n?utm_source=npm-readme

Notes

  • Built on @n8n/ai-node-sdk (supplyModel, type: 'openai'). That SDK is in preview and may change upstream; the usage is kept in one place (supplyData) and loaded lazily.
  • Chat models only; image, embedding and other capabilities are out of scope for this package.

Discussion