LLM API in Node.js: the official openai SDK without rewriting code

Why connect it

The openai SDK for Node.js works with any OpenAI-compatible address. Pass baseURL and the key when creating the client.

Streaming answers arrive as a regular async iterator, handy for chats and Telegram bots.

How to connect Node.js

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

1. 1

   Install the package

   The official openai package works.

   terminalCopy

   npm install openai

2. 2

   Store the key

   Put the key into the TENZO_API_KEY environment variable.

   terminalCopy

   export TENZO_API_KEY=tc-your-key

3. 3

   Send a request

   Create a client with the Tenzo Cloud baseURL and pick a model.

   index.mjsCopy

   import OpenAI from 'openai'
   
   const client = new OpenAI({ baseURL: 'https://tenzo-cloud.com/v1', apiKey: process.env.TENZO_API_KEY })
   
   const stream = await client.chat.completions.create({
       model: 'qwen-3.8-max',
       messages: [{ role: 'user', content: 'Hello!' }],
       stream: true,
   })
   for await (const chunk of stream) {
       process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
   }

Common errors and fixes

404 on the first request

Check that baseURL ends with /v1.

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.