QwenCloud 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.

HappyHorse-1.1-T2V is a text-to-video model on QwenCloud built to generate high-quality videos from natural language prompts. The model supports video generation workflows where the input is text and the output is video. HappyHorse-1.1-T2V is designed with improved semantic understanding so it can more accurately interpret creative instructions. It also supports cinematic shot control, helping users guide the style, composition, and feel of generated scenes. Dynamic motion rendering helps the model produce smoother movement and more natural video sequences. The model is positioned to create richer details, stronger visual consistency, natural character actions, convincing scene atmosphere, and realistic physical dynamics. Developers can access HappyHorse-1.1-T2V through the QwenCloud API using the DashScope video synthesis endpoint. API requests can specify parameters such as resolution, aspect ratio, duration, and the text prompt. The model supports 480P, 720P, and 1080P video generation with per-second pricing, along with rate limits for requests, concurrency, and async queue tasks. HappyHorse-1.1-T2V is a hosted model rather than an open source model, and it can be tested through QwenCloud’s Try AI experience or integrated with an API key. By combining prompt-based video creation, cinematic control, motion quality, visual consistency, scalable API access, and configurable output settings, HappyHorse-1.1-T2V helps creators and developers turn ideas into generated video.

OpenAI is committed to ensuring that artificial general intelligence (AGI)—characterized by its ability to perform most tasks that are economically important with a level of autonomy that surpasses human capabilities—benefits all of humanity. Our primary goal is to create AGI that is both safe and beneficial; however, we also view our mission as a success if we empower others to reach this same objective. You can take advantage of our API for numerous language-based functions, such as semantic search, summarization, sentiment analysis, content generation, translation, and much more, all achievable with just a few examples or a clear instruction in English. A simple integration gives you access to our ever-evolving AI technology, enabling you to test the API's features through these sample completions and uncover a wide array of potential uses. As you explore, you may find innovative ways to harness this technology for your projects or business needs.

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.

Qwen is an advanced AI assistant and development platform powered by Alibaba Cloud’s cutting-edge Qwen model family, offering powerful multimodal reasoning and creativity tools for users at all skill levels. It provides a free and accessible interface through Qwen Chat, where anyone can generate images, analyze content, perform deep multi-step research, and build fully coded web pages simply by describing what they want. Using its VLo model, Qwen transforms ideas into detailed visuals and supports editing, style transfer, and complex multi-element image creation. Deep Research acts like an automated research partner, gathering information online, synthesizing insights, and generating structured reports in minutes. The Web Dev feature empowers users to create modern, ready-to-deploy websites with clean code using only natural language instructions. Qwen’s enhanced “Thinking” capabilities provide stronger logic, structured problem-solving, and real-time internet-aware analysis. Its Search tool retrieves precise results with contextual understanding, while multimodal intelligence enables Qwen to process images, audio, video, and text together for deeper comprehension. For developers, the Qwen API offers OpenAI-compatible endpoints, allowing seamless integration of Qwen’s reasoning, generation, and multimodal abilities into any application or product. This makes Qwen not only an AI assistant but also a versatile platform for builders and engineers. Across web, desktop, and mobile environments, Qwen delivers a unified, high-performance AI experience.

Qwen3.8-27B is an open-weights 27B-class model connected to Alibaba’s Qwen3.8 release, built for developers, researchers, and AI teams that need a capable but more deployable model size. Alibaba’s Qwen3.8 launch described the broader model family as optimized for coding and cowork scenarios, including software development, document processing, data analysis, and professional workflows. Reports state that Alibaba planned to open-source Qwen3.8-Max alongside Qwen3.8-27B, expanding access for developers and researchers. Qwen3.8-27B gives builders a smaller alternative to the 2.4T-parameter Qwen3.8-Max model, which third-party coverage describes as Qwen’s first Max-scale model planned for open weights. The model is well suited for coding assistance, local development, agent testing, workflow automation, data analysis, document understanding, and private AI experimentation. QwenCloud documentation lists Qwen3.8-Max as supporting a 1M context window, thinking, function calling, built-in tools, and structured output, showing the broader Qwen3.8 generation’s focus on advanced agent and application workflows. Qwen3.8-27B is especially useful for teams that want Qwen-family capabilities without the infrastructure demands of Max-scale deployment. Community posts around the release point to active interest in Hugging Face, Unsloth GGUF, Ollama, and local inference use cases. Third-party coverage also notes practical hardware discussions around quantized Qwen3.8-27B deployment, including claims that 4-bit variants can fit more easily on consumer or workstation GPUs. The model can be positioned for organizations that need open AI infrastructure, coding agents, local model evaluation, private deployments, and cost-controlled experimentation. By combining open-weight access, a practical 27B model size, Qwen3.8-era performance ambitions, coding-oriented workflows, and local deployment interest, Qwen3.8-27B gives developers a flexible foundation for building AI products and agents.

Qwen-7B represents the seventh iteration in Alibaba Cloud's Qwen language model lineup, also referred to as Tongyi Qianwen, featuring 7 billion parameters. This advanced language model employs a Transformer architecture and has undergone pretraining on a vast array of data, including web content, literature, programming code, and more. In addition, we have launched Qwen-7B-Chat, an AI assistant that enhances the pretrained Qwen-7B model by integrating sophisticated alignment techniques. The Qwen-7B series includes several remarkable attributes: Its training was conducted on a premium dataset encompassing over 2.2 trillion tokens collected from a custom assembly of high-quality texts and codes across diverse fields, covering both general and specialized areas of knowledge. Moreover, the model excels in performance, outshining similarly-sized competitors on various benchmark datasets that evaluate skills in natural language comprehension, mathematical reasoning, and programming challenges. This establishes Qwen-7B as a prominent contender in the AI language model landscape. In summary, its intricate training regimen and solid architecture contribute significantly to its outstanding adaptability and efficiency in a wide range of applications.

Qwen2 is a comprehensive array of advanced language models developed by the Qwen team at Alibaba Cloud. This collection includes various models that range from base to instruction-tuned versions, with parameters from 0.5 billion up to an impressive 72 billion, demonstrating both dense configurations and a Mixture-of-Experts architecture. The Qwen2 lineup is designed to surpass many earlier open-weight models, including its predecessor Qwen1.5, while also competing effectively against proprietary models across several benchmarks in domains such as language understanding, text generation, multilingual capabilities, programming, mathematics, and logical reasoning. Additionally, this cutting-edge series is set to significantly influence the artificial intelligence landscape, providing enhanced functionalities that cater to a wide array of applications. As such, the Qwen2 models not only represent a leap in technological advancement but also pave the way for future innovations in the field.

Qwen Studio is an advanced artificial intelligence platform created by Alibaba Cloud that gives users centralized access to powerful large language models, multimodal AI systems, and intelligent automation tools for both personal and enterprise use. The platform is built around the Qwen family of AI models and provides capabilities such as AI chat, coding assistance, document analysis, image understanding, voice interaction, video processing, and AI-powered content generation through a cloud-based interface. Users can interact with text, images, audio, and video simultaneously, allowing Qwen Studio to support complex multimodal workflows for research, development, customer support, education, productivity, and creative projects. Developers and businesses can integrate Qwen Studio into their own applications and services using APIs that are compatible with industry-standard development frameworks and AI tooling environments. The platform supports advanced reasoning, natural language understanding, code generation, automation workflows, and intelligent task execution designed to simplify complex operational and technical processes. Qwen Studio also allows organizations to experiment with both open-source and proprietary Qwen models, giving teams flexibility to optimize performance, scalability, and deployment requirements based on their use cases. The system includes browser-based tools for AI experimentation, prompt engineering, application development, workflow testing, and content generation without requiring organizations to build and manage their own AI infrastructure. Users can generate reports, summarize documents, analyze uploaded files, create images, automate repetitive workflows, and interact with AI copilots capable of supporting business operations and software development tasks.

Qwen3-Coder is a sophisticated coding model available in multiple sizes, with its standout 480B-parameter Mixture-of-Experts variant (featuring 35B active parameters) capable of handling 256K-token contexts that can be expanded to 1M, showcasing superior performance in Agentic Coding, Browser-Use, and Tool-Use tasks, effectively competing with Claude Sonnet 4. The model undergoes a pre-training phase that utilizes a staggering 7.5 trillion tokens, of which 70% consist of code, alongside synthetic data improved from Qwen2.5-Coder, thereby boosting its coding proficiency and overall functionality. Its post-training phase benefits from extensive execution-driven reinforcement learning across 20,000 parallel environments, allowing it to tackle complex multi-turn software engineering tasks like SWE-Bench Verified without requiring test-time scaling. Furthermore, the open-source Qwen Code CLI, adapted from Gemini Code, enables the implementation of Qwen3-Coder in agentic workflows through customized prompts and function calling protocols, ensuring seamless integration with platforms like Node.js and OpenAI SDKs. This blend of powerful features and versatile accessibility makes Qwen3-Coder an invaluable asset for developers aiming to elevate their coding endeavors and streamline their workflows effectively. As a result, it serves as a pivotal resource in the rapidly evolving landscape of programming tools.

Qwen-Image is a state-of-the-art multimodal diffusion transformer (MMDiT) foundation model that excels in generating images, rendering text, editing, and understanding visual content. This model is particularly noted for its ability to seamlessly integrate intricate text elements, utilizing both alphabetic and logographic scripts in images while ensuring precision in typography. It accommodates a diverse array of artistic expressions, ranging from photorealistic imagery to impressionism, anime, and minimalist aesthetics. Beyond mere creation, Qwen-Image boasts sophisticated editing capabilities such as style transfer, object addition or removal, enhancement of details, in-image text adjustments, and the manipulation of human poses with straightforward prompts. Additionally, the model’s built-in vision comprehension functions—like object detection, semantic segmentation, depth and edge estimation, novel view synthesis, and super-resolution—significantly bolster its capacity for intelligent visual analysis. Accessible via well-known libraries such as Hugging Face Diffusers, it is also equipped with tools for prompt enhancement, supporting multiple languages and thereby broadening its utility for creators in various disciplines. Overall, Qwen-Image’s extensive functionalities render it an invaluable resource for both artists and developers eager to delve into the confluence of visual art and technological innovation, making it a transformative tool in the creative landscape.

Qwen-Image 2.0 marks the latest evolution in the Qwen series of AI models, skillfully combining image generation with editing capabilities into a unified framework that delivers outstanding visual content alongside superior typography and layout features informed by natural language prompts. This model enables users to create images from text and modify existing images through a sophisticated 7 billion-parameter architecture that operates with remarkable efficiency, producing outputs at a native resolution of 2048×2048 pixels while adeptly managing complex prompts of up to around 1,000 tokens. Consequently, creators can easily generate detailed infographics, posters, slides, comics, and photorealistic images featuring precisely rendered text in English and other languages embedded within the visuals. By providing a single model, users enjoy the convenience of not requiring multiple tools for both image creation and alteration, which streamlines the iterative process of concept development and visual enhancement. Additionally, the model's improvements in text rendering, layout design, and high-definition detail are designed to exceed the capabilities of previous open-source models, establishing a new benchmark for quality in the industry. This forward-thinking approach not only simplifies workflows but also broadens the scope of creative opportunities available to users in various sectors, enhancing their ability to express ideas visually. Ultimately, Qwen-Image 2.0 empowers users to explore their creativity without the constraints of traditional image creation tools.

Qwen-Audio-3.0-TTS-Plus is the advanced iteration of Qwen-Audio-3.0-TTS, crafted to significantly improve the naturalness and fidelity of voice outputs when prioritizing quality over rapidity. This version supports 16 languages and provides exceptional accuracy for multiple Chinese dialects, facilitating strong multilingual comprehension. A key highlight is its ability to preserve speaker characteristics across all languages, enabling cloned voices to remain both recognizable and consistent in a variety of linguistic environments. Developers are empowered to use simple natural-language commands, removing the complexity of manually tweaking acoustic settings, while having the ability to effortlessly manage emotions, roles, pacing, projection, and tone. Moreover, inline tags offer precise control over non-verbal cues like breaths, laughter, and shifts in emotion, making it ideal for applications in narration, gaming, character dialogue, and dubbing projects. This model not only enhances audio production quality but also provides a versatile solution that can adapt to a wide range of creative needs, ensuring an immersive experience for listeners.

Qwen-Audio-3.0-TTS-Flash is a real-time adaptation of Qwen-Audio-3.0-TTS, tailored for interactive environments with an initial packet delay of approximately 300 milliseconds. This version supports 16 languages and provides enhanced audio fidelity for multiple Chinese dialects. In multilingual evaluations, Flash stands out with the lowest average word and character error rates in its class, measured at 3.87, showcasing remarkable clarity while preserving the distinct characteristics of various speakers across different languages. Developers have the convenience of managing output through simple language instructions, eliminating the need for manual adjustment of acoustic settings; this feature empowers them to fine-tune elements such as emotion, role, scenario, pace, projection, and tone using intuitive commands. Furthermore, inline tags facilitate the integration of specific non-verbal cues, making the model exceptionally suitable for a broad range of applications, such as conversational agents, storytelling, gaming, dubbing, and other expressive speech situations. Notably, the voice cloning capabilities are adept at functioning effectively even with suboptimal reference audio; this is achieved through targeted acoustic simulation that minimizes background noise and reverberation while preserving the tonal qualities of the original voice. As a result, this cutting-edge technology not only enhances versatility but also enriches the overall audio experience across diverse platforms and applications, making it a valuable tool for developers and content creators alike.

Wan2.7-T2V is an advanced model from Qwen Cloud that revolutionizes the process of transforming text prompts into cinematic videos, expertly combining synchronized audio with multi-shot storytelling within a streamlined workflow. It produces videos that range in duration from 2 to 15 seconds and provides users with resolution options of 720P or 1080P, while accommodating various aspect ratios, including 16:9, 9:16, 1:1, 4:3, and 3:4. The model is designed to enhance narrative capabilities, fostering deeper emotional engagement in storylines, creating impactful action sequences, and employing dynamically rhythmic editing to elevate storytelling. Developers can define multiple scenes within a single prompt by using timed segments, allowing for a consistent portrayal of the main subject throughout transitions. Furthermore, it supports custom audio inputs, which empowers creators to incorporate narration, dialogue, music, or additional sound elements into the output. With prompts that can be as lengthy as 5,000 characters, teams have sufficient space to detail intricate scenes, specify camera angles, illustrate character movements, describe environmental elements, and manage the overall pacing of the video. This remarkable versatility makes the model highly appealing for a wide range of creative endeavors, effectively serving the needs of both experienced filmmakers and enthusiastic content creators alike, ultimately pushing the boundaries of video creation.

CosyVoice is an advanced model for voice cloning and speech synthesis created by Qwen Cloud, which belongs to the CosyVoice series and focuses on improving professional text-to-speech applications by significantly enhancing audio quality, naturalness, expressiveness, and accuracy in voice cloning. This innovative model can produce a customized voice that closely matches the reference audio with just a short recording period of 10–20 seconds of clear speech for optimal results, although it is essential to provide a minimum of five seconds of uninterrupted speech. Additionally, it features capabilities for real-time streaming of text-to-speech synthesis, allowing applications to effectively process text and generate audio with minimal initial delays. The model supports a range of languages, including Chinese, English, French, German, Japanese, Korean, and Russian, and it provides language suggestions during the enrollment phase to aid in accurate voice identification. Accepted recording formats include WAV, MP3, or M4A, with a requirement for the speech to be clear and free from background noise, music, or other speakers to achieve the best results. In summary, CosyVoice emerges as a robust solution for crafting personalized voice experiences across various languages and contexts, making it an essential tool for those in need of high-quality voice synthesis. Its versatility and advanced features make it an attractive option for both personal and professional applications alike.

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.

Qwen-Image-3.0-Pro is a sophisticated image generation model that converts both text and image inputs into detailed, informative visuals designed for practical uses beyond just aesthetic value. It can handle prompts of up to 4.5K tokens and supports complex layouts, allowing for the seamless creation of intricate compositions like newspapers, storyboards, menus, and examinations in a single output. This model emphasizes authenticity and detail, achieving text rendering with precision down to 10 pixels while capturing subtle visual nuances such as micro-expressions, skin textures, and individual hair strands, rivaling professional photography standards. Moreover, Qwen-Image-3.0-Pro incorporates a wealth of knowledge into its generation, offering native text rendering in 12 languages and compatibility with over 20 different fonts for enhanced versatility. The model also realistically simulates widely-used digital interfaces, including web pages, gaming environments, and live-stream scenarios, effectively integrating external information to enrich the final image. Its extensive capabilities make it an indispensable resource for a wide array of creative and functional applications, appealing to professionals in various fields. This adaptability ensures that users can produce high-quality visuals tailored to their specific needs.

Qwen3.8-2.4T-A95B emerges as the largest open model in the Qwen3.8 series, presenting advanced Qwen-Max-class capabilities in a format that is accessible to the public. Built on the robust foundation of Qwen3.5, this model offers marked improvements in performance across various domains, including coding, professional applications, research, and complex, extended agentic tasks, underscoring its ability to reliably execute intricate, multi-step workflows to completion. With its innovative mixture-of-experts architecture, it features a remarkable total of 2.4 trillion parameters, of which 95 billion are activated, utilizing 512 experts and allowing for simultaneous engagement of 10 routed experts alongside one shared expert. The model supports a native context length of 262,144 tokens, extendable to about 1.01 million tokens, thereby enabling considerable adaptability for diverse applications. Additionally, enhancements in agent execution, such as superior autonomous planning and improved responsiveness to environmental cues, enhance its overall efficiency. Its extensive compatibility with popular agent frameworks and development tools further aids in smooth integration into current systems, making it an appealing option for both developers and researchers. This versatility is particularly beneficial for those seeking to leverage advanced AI capabilities in their projects.