Sign in

Models

Strong open models over an API, with no token bill

Pick a model for the job: code and agents, careful reasoning, large codebases or fast high-volume work. You pay for streams, not for every token, and switch models with one line.

Try it freefrom $11 a month per stream · 3 hours with every model, no card

Every model and what it is good at

Context size, image support and status update automatically.

How to choose

If you do not want to think about it, start with Qwen 3.8 Max: the largest context, reads screenshots and diagrams, writes solid code and text. For agents and long tasks in Claude Code and Cursor pick a model marked “code and agents”, for tricky logic pick “reasoning”, for bots and classification use the fast Flash models.

You can switch at any time: in the chat with the model picker, in code with the model parameter. A subscription is bought for a specific model, and streams for one model stack.

Pricing for every model

Price per stream for the chosen period.

  • Qwen 3.8 Max

    Operational
    1 stream4+ streams, each
    3 days$2.73₸1,150$2.10₸880
    7 days$5.33₸2,280$4.10₸1,750
    30 days$14.30₸6,180$11₸4,750

  • GLM 5.3

    Coming soon
    1 stream4+ streams, each
    3 days$2.86₸1,240$2.20₸950
    7 days$5.72₸2,470$4.40₸1,900
    30 days$15.73₸6,830$12.10₸5,250

  • DeepSeek V4 Pro

    Coming soon
    1 stream4+ streams, each
    3 days$2.21₸950$1.70₸730
    7 days$4.55₸1,950$3.50₸1,500
    30 days$12.74₸5,530$9.80₸4,250

  • GLM 5.3 Flash

    Coming soon
    1 stream4+ streams, each
    3 days$2.47₸1,040$1.90₸800
    7 days$4.81₸2,080$3.70₸1,600
    30 days$13.91₸6,020$10.70₸4,630

  • DeepSeek V4.1 Flash

    Coming soon
    1 stream4+ streams, each
    3 days$2.47₸1,040$1.90₸800
    7 days$4.81₸2,080$3.70₸1,600
    30 days$13.91₸6,020$10.70₸4,630

Price per stream. Volume discount: 2–3 streams pay 88%, 4 or more pay 77% of the single-stream price. Streams and periods stack. Prices sync from the dashboard automatically.

Connect in two lines

main.py
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="")

Models

FAQ

How are these models different from ChatGPT?

They are strong open models (Qwen, GLM, DeepSeek) that we provide on a fixed subscription. You get both a web chat and an OpenAI-compatible API for Cursor, Claude Code, your bots and services. Tokens are not counted; only concurrent requests are limited.

Can I switch between models?

Yes. In the chat you pick a model in the composer, over the API you set the model parameter. Access covers the models you subscribe to; the 3 free hours cover all of them.

Which model is best for coding?

Qwen 3.8 Max for large projects and screenshots. GLM 5.3 for agents and multi-step tasks, DeepSeek V4 Pro for reviews and tricky logic once it is on sale. Each model page shows its current status.

Do I need a VPN?

No. The site, chat and API work directly from Kazakhstan, Russia and the rest of the CIS.

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.

Start freeSee pricing