Qwen 3.8 Max API: a huge context with no token bill

What Qwen 3.8 Max is for

Qwen 3.8 Max is our recommended everyday model. It keeps a large project or a stack of documents in mind at once, so it asks fewer follow-ups and loses fewer details in long conversations.

It understands images: send a screenshot of an error, a screen mockup or a database diagram and ask it to explain, build or debug. This is handy in the web chat and in agent tools that pass images along.

Strengths

• 256K token context for whole code modules, long specs and threads
• Reads screenshots, mockups and diagrams
• Writes and edits code confidently in popular languages
• Writes well in English and Russian
• Works both in the chat and for agents in Claude Code and Cursor

Typical tasks

• Understand an unfamiliar codebase and plan changes
• Review a pull request with neighbouring files in context
• Build a screen from a mockup screenshot
• Compare contract versions and list the differences
• Long Claude Code sessions with no token bill

Python example

The official openai library works as is, only the address and key change.

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="")

The same with curl

curl https://tenzo-cloud.com/v1/chat/completions \
  -H "Authorization: Bearer tc-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen-3.8-max", "stream": true,
       "messages": [{"role": "user", "content": "Hello!"}]}'