Happy Shrimp 1.0 Integrations

Qwen3.8-Max is a large-scale AI model from Qwen built for coding, coworking, research, long-horizon planning, and multimodal agent workflows. It is positioned as the most capable model in the Qwen family to date, with open weights announced for release after launch. The model uses a 2.4 trillion-parameter architecture with 95 billion active parameters and is available through QwenCloud. Qwen3.8-Max is designed to complete complex, open-ended goals end to end rather than only answer isolated prompts. In coding workflows, it can write and run code, create self-evolving harnesses, normalize requirements into issues, execute tasks through agents, run tests, trigger CI checks, and iterate through feedback. Its autonomous coding examples include a 10+ day project run, a research-paper reproduction and improvement loop, and a 24-hour online competition solution that beat most participating human teams. For professional work, Qwen3.8-Max is built to handle multi-step, tool-heavy workflows across compliance, design, food operations, engineering, rehabilitation, sports analytics, and quantitative research. The model also supports long-horizon decision-making, including autonomous chip-design optimization and extended e-commerce operations simulations. Its multimodal capabilities cover images, complex PDFs, long videos, visual production, interface inspection, frontend reconstruction, Blender visualization, interactive applications, and visual feedback loops. Qwen3.8-Max can be integrated through QwenCloud APIs and used with agent frameworks or coding assistants such as Claude Code, Codex, Qoder CLI, Qwen Code, and OpenClaw. By combining agentic coding, reasoning controls, multimodal understanding, visual self-correction, long-context workflows, tool use, and open-weight availability, Qwen3.8-Max helps developers and organizations build autonomous AI systems that can produce dependable deliverables.

Qwen-Image 3.0 marks the latest evolution of the groundbreaking image generation framework within the Qwen-Image series, specifically aiming to bridge the gap between visually compelling outputs and practical, information-rich designs. This iteration prioritizes three key goals: creating content with depth, maintaining authenticity in details, and leveraging extensive knowledge. Users can input prompts of up to 4.5K tokens, which facilitates comprehensive descriptions of complex layouts, accurate text, hierarchical designs, relational elements, styles, and various sections, all within a single query. Particularly impressive is its ability to generate intricate content types like multi-panel infographics, newspaper formats, storyboards, examination papers, presentation grids, academic papers, nested interfaces, posters, and other organized visuals seamlessly, eliminating the need for assembling individual images. Moreover, Qwen-Image 3.0 significantly improves text rendering, making it possible to display legible characters as small as 10 pixels, supporting twelve languages, and adeptly reproducing complex LaTeX equations, labels, text blocks, handwritten notes, and mixed-language formats. This blend of capabilities not only streamlines the image creation process but also positions it as a formidable resource for an array of creative and scholarly endeavors, offering users a versatile platform for their artistic and academic needs. With such comprehensive features, it is evident that Qwen-Image 3.0 stands out as a revolutionary tool in the realm of image generation.

Alibaba Cloud, a division of Alibaba Group (NYSE: BABA), provides a comprehensive array of global cloud computing services aimed at improving the online functionalities of its diverse international customer base, while also bolstering Alibaba Group's e-commerce framework. In a noteworthy development, Alibaba Cloud was appointed as the official Cloud Services Partner for the International Olympic Committee in January 2017. With a strong commitment to promoting cutting-edge cloud technologies and ensuring robust security protocols, the company aims to achieve its goal of making global business interactions easier for all. Catering to a wide spectrum of clients, including large corporations, emerging startups, individual developers, and public institutions, Alibaba Cloud operates its services in over 200 countries and regions around the globe. By focusing on innovation and prioritizing customer satisfaction, Alibaba Cloud distinguishes itself within the competitive cloud computing sector, continuously seeking ways to enhance its offerings and adapt to the evolving needs of its clients.

Model Studio stands out as Alibaba Cloud's all-encompassing generative AI platform, enabling developers to build smart applications tailored to business requirements through the use of leading foundation models such as Qwen-Max, Qwen-Plus, Qwen-Turbo, and the Qwen-2/3 series, along with visual-language models like Qwen-VL/Omni, and the video-focused Wan series. This platform allows users to seamlessly access these sophisticated GenAI models via user-friendly OpenAI-compatible APIs or dedicated SDKs, negating the necessity for any infrastructure setup. Model Studio provides a holistic development workflow that includes a dedicated playground for model experimentation, supports real-time and batch inferences, and offers fine-tuning techniques such as SFT or LoRA. After fine-tuning, users can assess and compress their models to enhance deployment speed and monitor performance—all within a secure, isolated Virtual Private Cloud (VPC) that prioritizes enterprise-level security. Additionally, the one-click Retrieval-Augmented Generation (RAG) feature simplifies the customization of models by allowing the integration of specific business data into their outputs. The platform's intuitive, template-driven interfaces also streamline prompt engineering and aid in application design, making the entire process more accessible for developers with diverse levels of expertise. Ultimately, Model Studio not only equips organizations to effectively harness the capabilities of generative AI, but it also fosters innovation by facilitating collaboration across teams and enhancing overall productivity.

Qwen3.5-Omni, a cutting-edge multimodal AI model developed by Alibaba, integrates the comprehension and creation of text, images, audio, and video into a unified system, enhancing the intuitiveness and immediacy of human-AI interactions. Unlike traditional models that treat each type of input separately, this pioneering technology is designed from the outset with extensive audiovisual datasets, which allows it to handle complex inputs such as lengthy audio files, videos, and spoken instructions all at once while maintaining high performance across different formats. It supports long-context inputs of up to 256K tokens and can process more than ten hours of audio or extended video content, positioning it as a top choice for demanding real-world applications. A key feature of this model is its advanced voice interaction capabilities, which include comprehensive speech dialogue systems, emotional tone modulation, and voice cloning, enabling remarkably natural conversations that can vary in volume and adjust speaking styles dynamically. Additionally, this adaptability guarantees users a uniquely tailored and captivating interaction experience, making it suitable for a wide array of applications. Overall, Qwen3.5-Omni represents a significant advancement in the field of AI, pushing the boundaries of what is achievable in multimodal communication.

Wan3.0 is a comprehensive video generation platform developed by Qwen Cloud that combines multiple creative features within a single interface, including the ability to convert text into video, turn images into video, and create videos inspired by references, alongside capabilities for editing, duplication, and motion guidance. This versatile model supports an array of inputs like audio, images, text, and videos, which empowers creators to shape the generation process using diverse sources beyond simple text prompts. With the capacity to create videos lasting up to 30 seconds, it provides omni-modal reference support, thereby enhancing user creativity by facilitating the integration of visual elements, movements, characters, and various artistic cues into the final output. Additionally, Wan3.0 can process files, analyze web pages, and interpret complex images during its creation phase. Its image-to-video functionality allows for both first-frame and first-and-last-frame generation, offering users the ability to dictate the beginning of a sequence or anchor both ends of a shot, thus significantly enriching the storytelling potential of the generated videos. Moreover, this all-encompassing model fosters innovative creative possibilities by enabling the effortless combination of different media types throughout the video production workflow, ultimately transforming the way creators engage with their projects.

Qwen3.8-Flash-Next is a pioneering open-weight multimodal Mixture-of-Experts architecture that offers an initial look at the design meant for its successor, Qwen4. This model has been expertly crafted to enhance various aspects such as attention mechanisms, residual pathways, embeddings, and optimization strategies, thereby increasing its overall functionality, enhancing computational efficiency, expanding its model capacity, and ensuring stability during training. Its unique hybrid structure combines Gated DeltaNet, which effectively condenses historical information, with Qwen Sparse Attention, facilitating the selection of meaningful context on a micro-block scale to reduce both attention and indexing expenses for lengthy sequences. The Gated Residual feature enhances the residual pathway by incorporating four streams, which helps in dynamically regulating the information flow across different layers. Moreover, the N-gram Embedding cleverly merges large-scale local-pattern memory with minimal computational overhead for each token, with the capability to transfer to host memory for added efficiency. The entire model is built around a main network comprising 125 billion parameters, supplemented by an additional 51 billion parameters specifically for N-gram embeddings, activating only 6 billion parameters for each token processed. This advanced framework underscores the continuous evolution in machine learning architectures, laying the groundwork for exciting future innovations, and it exemplifies the increasing sophistication and potential of multimodal models in various applications.

Step 5 Preview epitomizes the apex of StepFun’s offerings for agentic tasks, specifically designed for practical applications in the realms of software engineering and professional knowledge, with particular excellence in financial settings. This model is adept at processing text, images, and videos, featuring an impressive 1M-token context window that suits tasks requiring extensive data, tool utilization, and continuous advancement toward specific objectives. It can effectively analyze extensive documents, amalgamate information from diverse sources, and leverage conversation threads for efficient cross-document queries and research organization. In the field of programming and software development, it showcases proficiency in a range of programming languages, assisting with debugging, code adjustments, verification tasks, and test generation. Moreover, its sophisticated multi-step agent capabilities allow applications to leverage tools for information retrieval, document analysis, detailed research, and the development of analytical reports. The model's multimodal understanding enables it to integrate images, videos, and text, facilitating tasks like chart analysis and responding to queries based on screenshots. This extensive suite of capabilities not only enhances productivity but also solidifies Step 5 Preview as an essential tool for professionals across a multitude of industries, ensuring they remain at the forefront of their respective fields.

Qwen3.7-Plus represents a cutting-edge multimodal agent model that effectively merges vision and language into a flexible foundation for intelligent agents. Building on the agentic capabilities of Qwen3.7, it expands its functionality to encompass visual understanding, reasoning, grounded interactions, and the utilization of diverse multimodal tools, enabling agents to interpret, analyze, and navigate through text, images, documents, screens, and complex real-world environments. This model is specifically designed for dynamic tasks that extend beyond simple question answering, facilitating a range of activities such as visual searches, document comprehension, evaluations of charts and tables, screen analysis, GUI interactions, image-based reasoning, and workflows that integrate perception, planning, and action. Qwen3.7-Plus strengthens the connection between linguistic reasoning and visual signals, equipping users to ask questions about images, interpret intricate multimodal data, extract structured information, and generate replies that blend contextual and visual components, thereby enhancing the potential for interactive AI applications. With these advancements, users are empowered to engage in more complex and refined interactions with the system, transforming it into a highly effective tool for a multitude of practical uses across various fields. The model’s ability to adapt to different scenarios further solidifies its relevance in today’s rapidly evolving technological landscape.

Qwen3.8-Omni-Flash is a groundbreaking omnimodal model designed to significantly boost the efficiency of agents operating in productivity-focused settings, transitioning from basic understanding of multimodal inputs to actively performing tasks, utilizing diverse tools, and engaging in creative projects. Built upon the sophisticated Qwen3.8-Flash-Next architecture, it adeptly handles text, images, audio, and video inputs with an extraordinary context window of up to 1 million tokens, while maintaining strong performance in text-centric applications. This model transcends traditional coding and knowledge-based tasks, enriching workflows related to audio and video through capabilities such as video editing, crafting music videos, providing film commentary, summarizing audiovisual content, and facilitating real-time discussions. It particularly excels at enhancing the interpretation of long-form audio and video through organized descriptions, enabling agents to gather compelling evidence, grasp meeting content, and conduct thorough research focused on video materials. Users are empowered to specify parameters including subject matter, time frame, level of detail, and output format for video assessments, allowing for comprehensive overviews and customized analyses. This adaptability positions it as an indispensable resource for both professionals and creatives eager to optimize their productivity across a variety of multimedia platforms, ensuring that every project reaches its full potential. Furthermore, the model's seamless integration into diverse workflows opens up new possibilities for collaboration and innovation in content creation.

Qwen-Image-2.1 represents a cutting-edge advancement in the domain of converting text to images and modifying existing images, forming part of the Qwen series that is meticulously designed to strike an effective balance among image quality, inference efficiency, and overall flexibility. This sophisticated model boasts a visual generation framework that encompasses 7 billion parameters and employs 32 Single-Stream DiT layers, featuring a streamlined architecture that combines mixed-granularity attention with prefix KV cache reuse, which ensures the production of high-quality images while keeping computational requirements low. It natively supports the creation of both standard images and transparent RGBA files, enabling seamless editing of transparent layers and facilitating the extraction of subjects from photos, all within a unified system. For complex editing tasks, Qwen-Image-2.1 can accommodate up to ten reference images, allowing for intricate multi-subject setups, and it accepts local editing requests through methods such as circles, painted notes, or distinct masks, all while preserving the fidelity of individuals and products during modifications. Significant improvements have been made in typography, portrait lighting, realistic texture rendering, and intricate detailing, resulting in outputs that are not only aesthetically appealing but also exhibit a high level of polish. Furthermore, the model’s adaptability across a range of image generation applications distinctly positions it as a leader in the field of image synthesis technology, showcasing its potential for diverse creative endeavors. As such, it opens up new possibilities for artists and designers looking to enhance their visual projects.

Qwen 4 is Alibaba’s forthcoming next-generation foundation model and the planned successor to the company’s Qwen3.x model family. Alibaba announced Qwen 4 at the 2026 Apsara Conference on September 22 and confirmed that the model is currently in training. The company has not yet disclosed Qwen 4’s architecture, parameter count, context length, training-compute requirements, benchmark scores, pricing, licensing terms, or release schedule. Qwen 4 is being developed as Alibaba expands its broader AI stack across foundation models, multimodal systems, AI infrastructure, and agent-oriented cloud services. A major research direction surrounding Alibaba’s next generation of models is recursive self-improvement based on real-world tasks and empirical feedback. The company has already experimented with this approach using Qwen3.8-Max, allowing the model to participate in automated pipeline design, data validation, experimentation, error diagnosis, and post-training optimization. Alibaba reported that Qwen3.8-Max completed 33 iterative cycles during one such experiment and increased its Artificial Analysis score from 40 to 45. In a separate chip-design experiment, a Qwen model performed more than 10,000 EDA tool calls during over 60 hours of automated improvement work, illustrating Alibaba’s interest in long-horizon agentic tasks. These demonstrations describe the research program surrounding future Qwen development rather than confirmed features of Qwen 4 itself. Alibaba has also announced a longer-term roadmap in which Qwen 4.5 and Qwen 5 models are projected to reach between 5 trillion and 10 trillion parameters. Qwen 4 therefore remains a pre-release model, with detailed capabilities and access information expected to become clearer when Alibaba publishes its formal launch materials.