Qwen3.5-Plus Integrations

Qwen3.5 is a next-generation open-weight multimodal large language model designed to power native vision-language agents. The flagship release, Qwen3.5-397B-A17B, combines a hybrid linear attention architecture with sparse mixture-of-experts, activating only 17 billion parameters per forward pass out of 397 billion total to maximize efficiency. It delivers strong benchmark performance across reasoning, coding, multilingual understanding, visual reasoning, and agent-based tasks. The model expands language support from 119 to 201 languages and dialects while introducing a 1M-token context window in its hosted version, Qwen3.5-Plus. Built for multimodal tasks, it processes text, images, and video with advanced spatial reasoning and tool integration. Qwen3.5 also incorporates scalable reinforcement learning environments to improve general agent capabilities. Designed for developers and enterprises, it enables efficient, tool-augmented, multimodal AI workflows.

Alibaba Cloud’s AI Scene Coding campaign introduces a cloud-based development environment designed to help developers write, test, and deploy software faster using advanced AI coding models. It provides access to powerful models such as Qwen3-Coder-Plus and integrates with popular developer tools, including Cline, Claude Code, Qwen Code, and OpenClaw, allowing engineers to use their preferred coding interfaces while leveraging Alibaba Cloud’s AI infrastructure. It is built to streamline software development by combining large language models with cloud computing resources so developers can generate code, analyze projects, and automate development workflows from a unified environment. These AI models are capable of understanding prompts, writing code, debugging programs, and assisting with complex development tasks, allowing applications to be built in minutes rather than through traditional manual coding cycles.

Model Studio is Alibaba Cloud’s one-stop generative AI platform that lets developers build intelligent, business-aware applications using industry-leading foundation models like Qwen-Max, Qwen-Plus, Qwen-Turbo, the Qwen-2/3 series, visual-language models (Qwen-VL/Omni), and the video-focused Wan series. Users can access these powerful GenAI models through familiar OpenAI-compatible APIs or purpose-built SDKs, no infrastructure setup required. It supports a full development workflow, experiment with models in the playground, perform real-time and batch inferences, fine-tune with tools like SFT or LoRA, then evaluate, compress, accelerate deployment, and monitor performance, all within an isolated Virtual Private Cloud (VPC) for enterprise-grade security. Customization is simplified via one-click Retrieval-Augmented Generation (RAG), enabling integration of business data into model outputs. Visual, template-driven interfaces facilitate prompt engineering and application design.

Tabbit Browser is an AI-native web browser designed to combine browsing, search, automation, and AI assistance directly inside the browsing experience. Instead of treating AI as a separate chatbot, the browser integrates AI tools that understand the context of the pages, files, and tabs a user is working with, allowing them to interact with content more intelligently while browsing. Users can add references such as text, screenshots, web pages, or files as context so the AI can generate precise answers and insights related to what they are currently viewing. It also allows switching between multiple advanced AI models, including GPT, Gemini, Claude, and others, so users can choose the model best suited for a particular task or workflow. A central feature of Tabbit is its ability to chat directly with web content. Users can highlight text, capture screenshots, or reference pages and ask the browser to summarize, explain, or analyze the information without leaving the page.