Support and salesSupport / sales
MODELS
Unlimited Basic subscription: unlimited Qwen 3.8 27B for €14.95/month. GLM + DeepSeek with 5,000 shared AI Credits. Fair use applies.

Qwen 3.8 27B Flex, ready to try.

Ask a question, see the answer arrive token by token, and keep the full OpenAI-compatible request within reach when you want to go deeper.

Qwen 3.8 27B Flex demo

Try the model directly in this chat.

QDivZero chat

Qwen 3.8 27B Flex

Processed 0 / 128k tok
Request JSONmodel, messages, stream and moreEdit

VS Code / Copilot

Bring QDivZero into Copilot.

Add the endpoint as a custom model in VS Code and use QDivZero from the Chat view. No API key is required for this demo.

  1. 01

    Open Manage Language Models

    In VS Code, open the Chat model picker and choose Add Models, then Custom Endpoint.

  2. 02

    Choose Chat Completions

    Use https://qdiv0.com/api/qdiv0/v1 and leave the API key as not-needed.

  3. 03

    Paste the model definition

    Save the generated chatLanguageModels.json and select the model in Chat.

chatLanguageModels.json
[
  {
    "name": "QDivZero",
    "vendor": "customendpoint",
    "apiKey": "not-needed",
    "apiType": "chat-completions",
    "models": [
      {
        "id": "public:qwen/qwen-3.8-27b-flex",
        "name": "Qwen 3.8 27B Flex",
        "url": "https://qdiv0.com/api/qdiv0/v1",
        "toolCalling": true,
        "thinking": true,
        "streaming": true
      }
    ]
  }
]

Keep the API key in VS Code's secret storage. Tool calling requires a model and deployment that expose tool support.