LangChain without a token bill: ChatOpenAI with our models

Why connect it

ChatOpenAI from langchain-openai accepts base_url and api_key, so Tenzo Cloud plugs in without extra adapters.

LangGraph and other libraries built on ChatOpenAI work the same way.

How to connect LangChain

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

   You need langchain-openai.

   terminalCopy

   pip install langchain-openai

2. 2

   Create the model

   Pass the Tenzo Cloud address, key and model id to ChatOpenAI.

   agent.pyCopy

   from langchain_openai import ChatOpenAI
   
   llm = ChatOpenAI(
       model="qwen-3.8-max",
       base_url="https://tenzo-cloud.com/v1",
       api_key="tc-your-key",
       streaming=True,
   )
   
   print(llm.invoke("Hello!").content)

3. 3

   Use it in a chain

   Plug llm into your chains, agents and LangGraph graphs.

Common errors and fixes

The agent hits 429

Parallel branches start several requests at once. Limit parallelism 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.