n8n and AI without a token bill: automation at a fixed price

Why connect it

In n8n the OpenAI and AI Agent nodes use OpenAI credentials where you can set a custom Base URL. Point it to Tenzo Cloud and every AI step of your flows runs on the subscription.

Fast models fit streams of similar tasks; for complex text processing use Qwen 3.8 Max.

How to connect n8n

You need a key from the dashboard: 3 free hours start right after sign-up. Replace tc-your-key with your key.

1. 1

   Get a key

   Create a key in the dashboard; for a server you can restrict it by IP.

2. 2

   Create OpenAI credentials

   In n8n open Credentials → New → OpenAI, paste the key and set the Tenzo Cloud Base URL.

   n8n → Credentials → OpenAICopy

   API Key:  tc-your-key
   Base URL: https://tenzo-cloud.com/v1
   Model:    qwen-3.8-max

3. 3

   Choose the model

   In the OpenAI Chat Model (or OpenAI) node pick the new credentials and set the model id. If the model is not listed, enter it manually.

4. 4

   Run the flow

   Execute the node in test mode and the model answer appears in the output.

Common errors and fixes

The model list in the node is empty

Set the model id manually in Expression mode, for example qwen-3.8-max.

429 during batch processing

The node processes items in parallel. Lower the batch size in the node settings or add streams.

401 invalid_api_key, “key not found”

Make sure the whole key is copied with no spaces or quotes and is enabled in the dashboard. Expired keys also return 401.

403 no_access, “no access to this model”

There is no active subscription for this model, or the key does not allow this model or your IP. Check Plans and the key restrictions in the dashboard.

404 model_not_found

The model id is wrong. Use an id from the model list, for example qwen-3.8-max or glm-5.3.

429 concurrency_limit

All your streams are busy or you exceeded 120 requests a minute. Retry in a few seconds or buy more streams, they stack.

503 model_unavailable

The model is under maintenance. Each model’s status is on the status page; switch models with one line.