Integrations
Bring AI to the tools you already use
Tenzo Cloud speaks the OpenAI protocol and has a compatible mode for Claude Code. Change the address and key, and your editors, agents and scripts keep working, just without a token bill.
How it works
Every tool connects the same way: the address https://tenzo-cloud.com/v1, your key from the dashboard and a model id. The dashboard has a ready config for each tool with your key filled in and a connection test.
One subscription covers everything: editor, agent, chat and your scripts. Only concurrent requests are limited, as many as the streams you bought.
Minimal example
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="")Integrations
- IntegrationsClaude CodeHow to connect Claude Code to GLM 5.3 and Qwen 3.8 Max in compatible mode: three environment variables, no VPN and no subscription limits. Step-by-step guide and common errors.Learn more
- IntegrationsCursorHow to use your own model in Cursor through an OpenAI-compatible address: Qwen 3.8 Max and GLM 5.3 with no request limits and no VPN. Step-by-step guide and common errors.Learn more
- IntegrationsCodex CLIHow to add Tenzo Cloud to Codex CLI as a separate provider in config.toml: GLM 5.3 and Qwen 3.8 Max with no token limits, no VPN. Guide, rollback and common errors.Learn more
- IntegrationsOpenCodeHow to connect OpenCode to Tenzo Cloud with opencode.json: GLM 5.3 and Qwen 3.8 Max with no token limits and no VPN. Ready config, check and common errors.Learn more
- IntegrationsVS Code + ContinueHow to connect the Continue extension for VS Code to Qwen 3.8 Max and GLM 5.3 through an OpenAI-compatible API: a ready config.yaml, no token limits and no VPN.Learn more
- IntegrationsClineHow to connect Cline in VS Code to GLM 5.3 and Qwen 3.8 Max through the OpenAI Compatible provider: an agent with no token limits and no VPN. Guide and common errors.Learn more
- Integrationsn8nHow to connect n8n to Tenzo Cloud models through OpenAI credentials with a Base URL: AI Agent and OpenAI Chat Model with no token bill and no VPN. Step by step, with errors.Learn more
- IntegrationsPythonHow to call Qwen 3.8 Max and GLM 5.3 from Python with the official openai library: streaming, a key in an environment variable, error handling. No token limits, no VPN.Learn more
- IntegrationsNode.jsHow to connect Qwen 3.8 Max and GLM 5.3 in Node.js and TypeScript with the official openai SDK: streaming, a key in the environment, common errors. No token limits, no VPN.Learn more
- IntegrationsLangChainHow to connect LangChain to Qwen 3.8 Max and GLM 5.3 through ChatOpenAI with the Tenzo Cloud base_url: agents and RAG with no token bill and no VPN. Code and common errors.Learn more
FAQ
How much does it cost and is there a token limit?
A subscription to a model at a fixed price per stream for 3, 7 or 30 days. Tokens are not counted; only concurrent requests and 120 requests a minute per account are limited. The first 3 hours are free, no card.
Do I need a VPN?
No. The API, site and chat work directly from Kazakhstan, Russia and the CIS.
Are my requests stored?
No. Prompts and answers sent through the API are not saved, neither in the database nor in logs. The journal keeps only time, model, status and token count.
Try it on your own work
Three free hours with every model, no card and no VPN. Connect Cursor, Claude Code or your own code in a minute.