Alibaba's cloud division has launched Qwen3.6-Plus, a model featuring a default context window of 1 million tokens, enhanced agent capabilities for programming, and improved multimodal perception and reasoning.

The chatbot is accessible via the Alibaba Cloud Model Studio API and is compatible with third-party coding assistants, including OpenClaw, Claude Code, and Qwen Code.

Performance and Multimodality

Qwen3.6-Plus integrates reasoning, memory, and execution. In code correction tests, the model closely approached market leaders, and it outperformed competitors in task automation and complex terminal operations.

The new version demonstrates some of the best results in long-term planning and the use of external tools. Qwen3.6-Plus also sets records in STEM reasoning evaluations, information extraction from extremely long contexts, and multilingual environments.

Alibaba continues to enhance the product's capabilities, shifting focus from basic machine vision to complex multimodal analysis and autonomous AI agent operations.

The updated model better understands the structure of complex documents, writes code, and analyzes videos and physical world objects. Qwen3.6-Plus can identify connections between large datasets and autonomously determine the optimal algorithm for solving a given task.

Based on screenshots of interfaces, product prototypes, design layouts, or multimodal instructions, the model generates frontend pages.

Ecology and Integrations

The model is compatible with several popular tools:

  • Qwen Code — an open-source AI agent designed for terminal work, specifically tailored for this series. It helps analyze complex codebases, automate routine tasks, and speed up development;
  • Claude Code — the Alibaba Cloud API supports the Anthropic API protocol, allowing Qwen3.6-Plus to work with tools like Claude Code for an enhanced programming experience.

The new API version includes a preserve_thinking feature (disabled by default), which retains the intermediate thought process of the neural network from all previous dialogue stages. Developers recommend using it in agent scenarios, as continuous reasoning context makes responses more accurate and often reduces overall token consumption.

Alibaba Cloud Model Studio supports protocols compatible with OpenAI and Anthropic specifications.

For reference, the previous version of the AI model, Qwen-3.5, was released in February, marking the first introduction of native multimodality.