LLM API in Python: the official openai library, two lines

Why connect it

Tenzo Cloud is compatible with OpenAI Chat Completions, streaming included. Any code on the openai library fits, from a quick script to a production service.

The price is fixed per stream, so batch processing, prompt tests and agents are fine to run.

How to connect Python

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 library

   The official openai library works.

   terminalCopy

   pip install openai

2. 2

   Store the key

   Create a key in the dashboard and put it in an environment variable.

   terminalCopy

   export TENZO_API_KEY=tc-your-key

3. 3

   Send a request

   Set the Tenzo Cloud base_url and a model id. The answer streams in.

   main.pyCopy

   from openai import OpenAI
   
   client = OpenAI(base_url="https://tenzo-cloud.com/v1", api_key="tc-your-key")
   
   stream = client.chat.completions.create(
       model="qwen-3.8-max",
       messages=[{"role": "user", "content": "Hello!"}],
       stream=True,
   )
   for chunk in stream:
       print(chunk.choices[0].delta.content or "", end="")

Common errors and fixes

openai.NotFoundError on the first request

Most likely base_url is missing /v1. The right one is https://tenzo-cloud.com/v1.

Timeouts on long answers

Use stream=True: the answer starts right away and the connection never idles.

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.