Happy Shrimp 1.0 Integrations

Qwen3.8-Max is Qwen’s most capable model to date, built as a Max-class AI model for coding, work, research, long-horizon tasks, and multimodal agents. It scales to 2.4 trillion parameters with 95 billion active parameters and is available through QwenCloud. The model is designed to complete complex, open-ended tasks end to end with greater reliability and minimal human involvement. Qwen3.8-Max supports autonomous coding workflows, agentic development, research reproduction, visual reasoning, document understanding, video analysis, and real-world productivity tasks. It can integrate with popular agent frameworks and coding assistants, including Claude Code, Codex, Qoder CLI, Qwen Code, and OpenClaw. Built for developers, researchers, enterprises, and AI agent builders, Qwen3.8-Max helps teams automate sophisticated work across code, documents, tools, interfaces, and multimodal content.

Qwen-Image 3.0 is the third-generation foundational image generation model in the Qwen-Image series, built to move AI imagery from visually appealing output toward practical, information-rich creation. Its capabilities center on three goals, rich content, authentic details, and deep knowledge. The model accepts prompts of up to 4.5K tokens, giving users room to describe complex layouts, exact copy, hierarchy, relationships, styles, and multiple sections in one request. It can generate dense content such as multi-panel infographics, newspaper pages, storyboards, examination sheets, presentation grids, academic pages, nested interfaces, posters, and other structured visuals in one pass rather than assembling separate images. Qwen-Image 3.0 strengthens text rendering with legible characters as small as 10 pixels, support for 12 languages, and the ability to reproduce complex LaTeX formulas, labels, paragraphs, handwritten annotations, and mixed-language layouts.

As a business unit of Alibaba Group (NYSE: BABA), Alibaba Cloud provides a comprehensive suite of global cloud computing services to power both our international customers’ online businesses and Alibaba Group’s own e-commerce ecosystem. In January 2017, Alibaba Cloud became the official Cloud Services Partner of the International Olympic Committee. By harnessing, and improving on, the latest cloud technology and security systems, we tirelessly work towards our vision - to make it easier for you to do business anywhere, with anyone in the world. Alibaba Cloud provides cloud computing services for large and small businesses, individual developers, and the public sector in over 200 countries and regions.

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.

Qwen3.5-Omni is a next-generation, fully multimodal AI model developed by Alibaba that natively understands and generates text, images, audio, and video within a single unified system, enabling more natural and real-time human-AI interaction. Unlike traditional models that treat modalities separately, it is trained from the ground up on massive audiovisual datasets, allowing it to process complex inputs such as long audio streams, video, and spoken instructions simultaneously while maintaining strong performance across all formats. It supports long-context inputs of up to 256K tokens and can handle over 10 hours of audio or extended video sequences, making it suitable for demanding real-world applications. A key feature is its advanced voice interaction capabilities, including end-to-end speech dialogue, emotional tone control, and voice cloning, enabling highly natural conversational experiences that can whisper, shout, or adapt speaking style dynamically.

Wan3.0 is an all-in-one video generation model from Qwen Cloud that unifies multiple creative capabilities in a single system, including text-to-video, image-to-video, reference-to-video, editing, replication, and driving. It supports audio, image, text, and video inputs and produces video output, allowing creators to guide generation with several types of source material instead of relying on text prompts alone. The model can generate videos up to 30 seconds long and supports omni-modal reference, giving users more flexibility when carrying visual, motion, character, or other creative cues into a new result. Wan3.0 can also parse files, web pages, and complex images as part of the generation workflow. Its image-to-video capabilities include first-frame and first-and-last-frame generation, making it possible to define how a sequence begins or anchor both ends of a shot.

Qwen3.7-Plus is a multimodal agent model that unifies vision and language into a single, versatile agent foundation. Building on Qwen3.7’s agentic intelligence, it extends Qwen’s capabilities into visual understanding, visual reasoning, grounded interaction, and multimodal tool use, enabling agents to perceive, analyze, and act across text, images, documents, screens, and complex real-world contexts. It is designed for tasks that require more than static question answering, including visual search, document comprehension, chart and table analysis, screen understanding, GUI interaction, image-grounded reasoning, and agent workflows that combine perception with planning and execution. Qwen3.7-Plus strengthens the connection between language reasoning and visual evidence, allowing users to ask questions about images, interpret dense multimodal inputs, extract structured information, and generate responses that reflect both context and visual details.