List of the Top 15 Foundation Models for Nebius Token Factory in 2026

Kimi K3 is Moonshot AI’s most advanced model, designed for high-end reasoning, software engineering, multimodal understanding, knowledge work, and agentic AI applications. The model has 2.8 trillion parameters and is built on Kimi Delta Attention, a hybrid linear attention mechanism created for long-context performance. It also uses Attention Residuals and supports a native context window of up to 1 million tokens. This makes Kimi K3 suitable for tasks involving large codebases, long research materials, enterprise documentation, multi-file analysis, legal documents, technical manuals, and complex workflows. Kimi K3 always has thinking mode enabled, with reasoning effort configured through the reasoning_effort field and maximum effort currently supported as the default. Developers can use the model through an OpenAI-compatible API, making it easier to integrate with existing SDKs, clients, and application infrastructure. The model supports streaming responses with separate reasoning and final-answer deltas, allowing applications to display reasoning progress and final content differently. Kimi K3 also supports strict structured output with JSON Schema, partial mode for continuing from a prefix, custom tool calling, required tool use, and dynamic tool loading through system messages. Its vision capabilities support image and video inputs through base64 or uploaded files, enabling analysis of visual content alongside text. Automatic context caching helps workflows that reuse long prefixes, such as large knowledge bases or persistent system context, without requiring developers to manage cache IDs manually. By combining frontier-scale parameters, long-context processing, visual input, structured outputs, tool orchestration, and developer-friendly API compatibility, Kimi K3 gives teams a strong foundation for advanced AI agents, coding assistants, research systems, enterprise automation, and multimodal applications.

Mistral AI is recognized as a pioneering startup in the field of artificial intelligence, with a particular emphasis on open-source generative technologies. The company offers a wide range of customizable, enterprise-grade AI solutions that can be deployed across multiple environments, including on-premises, cloud, edge, and individual devices. Notable among their offerings are "Le Chat," a multilingual AI assistant designed to enhance productivity in both personal and business contexts, and "La Plateforme," a resource for developers that streamlines the creation and implementation of AI-powered applications. Mistral AI's unwavering dedication to transparency and innovative practices has enabled it to carve out a significant niche as an independent AI laboratory, where it plays an active role in the evolution of open-source AI while also influencing relevant policy conversations. By championing the development of an open AI ecosystem, Mistral AI not only contributes to technological advancements but also positions itself as a leading voice within the industry, shaping the future of artificial intelligence. This commitment to fostering collaboration and openness within the AI community further solidifies its reputation as a forward-thinking organization.

DeepSeek-V3 is a remarkable leap forward in the realm of artificial intelligence, meticulously crafted to demonstrate exceptional prowess in understanding natural language, complex reasoning, and effective decision-making. By leveraging cutting-edge neural network architectures, this model assimilates extensive datasets along with sophisticated algorithms to tackle challenging issues in numerous domains such as research, development, business analytics, and automation. With a strong emphasis on scalability and operational efficiency, DeepSeek-V3 provides developers and organizations with groundbreaking tools that can greatly accelerate advancements and yield transformative outcomes. Additionally, its adaptability ensures that it can be applied in a multitude of contexts, thereby enhancing its significance across various sectors. This innovative approach not only streamlines processes but also opens new avenues for exploration and growth in artificial intelligence applications.

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.

DeepSeek-R1 represents a state-of-the-art open-source reasoning model developed by DeepSeek, designed to rival OpenAI's Model o1. Accessible through web, app, and API platforms, it demonstrates exceptional skills in intricate tasks such as mathematics and programming, achieving notable success on exams like the American Invitational Mathematics Examination (AIME) and MATH. This model employs a mixture of experts (MoE) architecture, featuring an astonishing 671 billion parameters, of which 37 billion are activated for every token, enabling both efficient and accurate reasoning capabilities. As part of DeepSeek's commitment to advancing artificial general intelligence (AGI), this model highlights the significance of open-source innovation in the realm of AI. Additionally, its sophisticated features have the potential to transform our methodologies in tackling complex challenges across a variety of fields, paving the way for novel solutions and advancements. The influence of DeepSeek-R1 may lead to a new era in how we understand and utilize AI for problem-solving.

Mistral 7B is a cutting-edge language model boasting 7.3 billion parameters, which excels in various benchmarks, even surpassing larger models such as Llama 2 13B. It employs advanced methods like Grouped-Query Attention (GQA) to enhance inference speed and Sliding Window Attention (SWA) to effectively handle extensive sequences. Available under the Apache 2.0 license, Mistral 7B can be deployed across multiple platforms, including local infrastructures and major cloud services. Additionally, a unique variant called Mistral 7B Instruct has demonstrated exceptional abilities in task execution, consistently outperforming rivals like Llama 2 13B Chat in certain applications. This adaptability and performance make Mistral 7B a compelling choice for both developers and researchers seeking efficient solutions. Its innovative features and strong results highlight the model's potential impact on natural language processing projects.

We are excited to unveil Mistral NeMo, our latest and most sophisticated small model, boasting an impressive 12 billion parameters and a vast context length of 128,000 tokens, all available under the Apache 2.0 license. In collaboration with NVIDIA, Mistral NeMo stands out in its category for its exceptional reasoning capabilities, extensive world knowledge, and coding skills. Its architecture adheres to established industry standards, ensuring it is user-friendly and serves as a smooth transition for those currently using Mistral 7B. To encourage adoption by researchers and businesses alike, we are providing both pre-trained base models and instruction-tuned checkpoints, all under the Apache license. A remarkable feature of Mistral NeMo is its quantization awareness, which enables FP8 inference while maintaining high performance levels. Additionally, the model is well-suited for a range of global applications, showcasing its ability in function calling and offering a significant context window. When benchmarked against Mistral 7B, Mistral NeMo demonstrates a marked improvement in comprehending and executing intricate instructions, highlighting its advanced reasoning abilities and capacity to handle complex multi-turn dialogues. Furthermore, its design not only enhances its performance but also positions it as a formidable option for multi-lingual tasks, ensuring it meets the diverse needs of various use cases while paving the way for future innovations.

Kimi K2 showcases a groundbreaking series of open-source large language models that employ a mixture-of-experts (MoE) architecture, featuring an impressive total of 1 trillion parameters, with 32 billion parameters activated specifically for enhanced task performance. With the Muon optimizer at its core, this model has been trained on an extensive dataset exceeding 15.5 trillion tokens, and its capabilities are further amplified by MuonClip’s attention-logit clamping mechanism, enabling outstanding performance in advanced knowledge comprehension, logical reasoning, mathematics, programming, and various agentic tasks. Moonshot AI offers two unique configurations: Kimi-K2-Base, which is tailored for research-level fine-tuning, and Kimi-K2-Instruct, designed for immediate use in chat and tool interactions, thus allowing for both customized development and the smooth integration of agentic functionalities. Comparative evaluations reveal that Kimi K2 outperforms many leading open-source models and competes strongly against top proprietary systems, particularly in coding tasks and complex analysis. Additionally, it features an impressive context length of 128 K tokens, compatibility with tool-calling APIs, and support for widely used inference engines, making it a flexible solution for a range of applications. The innovative architecture and features of Kimi K2 not only position it as a notable achievement in artificial intelligence language processing but also as a transformative tool that could redefine the landscape of how language models are utilized in various domains. This advancement indicates a promising future for AI applications, suggesting that Kimi K2 may lead the way in setting new standards for performance and versatility in the industry.

Kimi K2 Thinking is an advanced open-source reasoning model developed by Moonshot AI, specifically designed for complex, multi-step workflows where it adeptly merges chain-of-thought reasoning with the use of tools across various sequential tasks. It utilizes a state-of-the-art mixture-of-experts architecture, encompassing an impressive total of 1 trillion parameters, though only approximately 32 billion parameters are engaged during each inference, which boosts efficiency while retaining substantial capability. The model supports a context window of up to 256,000 tokens, enabling it to handle extraordinarily lengthy inputs and reasoning sequences without losing coherence. Furthermore, it incorporates native INT4 quantization, which dramatically reduces inference latency and memory usage while maintaining high performance. Tailored for agentic workflows, Kimi K2 Thinking can autonomously trigger external tools, managing sequential logic steps that typically involve around 200-300 tool calls in a single chain while ensuring consistent reasoning throughout the entire process. Its strong architecture positions it as an optimal solution for intricate reasoning challenges that demand both depth and efficiency, making it a valuable asset in various applications. Overall, Kimi K2 Thinking stands out for its ability to integrate complex reasoning and tool use seamlessly.

Kimi K2.5 is an advanced multimodal AI model engineered for high-performance reasoning, coding, and visual intelligence tasks. It natively supports both text and visual inputs, allowing applications to analyze images and videos alongside natural language prompts. The model achieves open-source state-of-the-art results across agent workflows, software engineering, and general-purpose intelligence tasks. With a massive 256K token context window, Kimi K2.5 can process large documents, extended conversations, and complex codebases in a single request. Its long-thinking capabilities enable multi-step reasoning, tool usage, and precise problem solving for advanced use cases. Kimi K2.5 integrates smoothly with existing systems thanks to full compatibility with the OpenAI API and SDKs. Developers can leverage features like streaming responses, partial mode, JSON output, and file-based Q&A. The platform supports image and video understanding with clear best practices for resolution, formats, and token usage. Flexible deployment options allow developers to choose between thinking and non-thinking modes based on performance needs. Transparent pricing and detailed token estimation tools help teams manage costs effectively. Kimi K2.5 is designed for building intelligent agents, developer tools, and multimodal applications at scale. Overall, it represents a major step forward in practical, production-ready multimodal AI.

Kimi K2.6 is a cutting-edge agentic AI model developed by Moonshot AI, designed to improve practical application, programming efficiency, and complex reasoning abilities beyond its forerunners, K2 and K2.5. Utilizing a Mixture-of-Experts framework, this model embodies the multimodal, agent-centric principles of the Kimi series, seamlessly combining language understanding, coding skills, and tool application into a unified system capable of planning and executing sophisticated workflows. It boasts advanced reasoning capabilities and superior agent planning, allowing it to break down tasks, coordinate multiple tools, and address challenges involving numerous files or steps with heightened accuracy and efficiency. Furthermore, it excels in tool-calling functions, ensuring a reliable connection with external platforms like web searches or APIs, while incorporating built-in validation systems to confirm the correctness of execution formats. Significantly, Kimi K2.6 marks a transformative advancement in the AI landscape, establishing new benchmarks for the intricacy and dependability of automated processes, and paving the way for future innovations in the field.

We are excited to unveil an open-source AI model that offers the ability to be fine-tuned, distilled, and deployed across a wide range of platforms. Our latest instruction-tuned model is available in three different sizes: 8B, 70B, and 405B, allowing you to select an option that best fits your unique needs. The open ecosystem we provide accelerates your development journey with a variety of customized product offerings tailored to meet your specific project requirements. You can choose between real-time inference and batch inference services, depending on what your project requires, giving you added flexibility to optimize performance. Furthermore, downloading model weights can significantly enhance cost efficiency per token while you fine-tune the model for your application. To further improve performance, you can leverage synthetic data and seamlessly deploy your solutions either on-premises or in the cloud. By taking advantage of Llama system components, you can also expand the model's capabilities through the use of zero-shot tools and retrieval-augmented generation (RAG), promoting more agentic behaviors in your applications. Utilizing the extensive 405B high-quality data enables you to fine-tune specialized models that cater specifically to various use cases, ensuring that your applications function at their best. In conclusion, this empowers developers to craft innovative solutions that not only meet efficiency standards but also drive effectiveness in their respective domains, leading to a significant impact on the technology landscape.

The latest iteration in the Llama series, Llama 3.3, marks a notable leap forward in the realm of language models, designed to improve AI's abilities in both understanding and communication. It features enhanced contextual reasoning, more refined language generation, and state-of-the-art fine-tuning capabilities that yield remarkably accurate, human-like responses for a wide array of applications. This version benefits from a broader training dataset, advanced algorithms that allow for deeper comprehension, and reduced biases when compared to its predecessors. Llama 3.3 excels in various domains such as natural language understanding, creative writing, technical writing, and multilingual conversations, making it an invaluable tool for businesses, developers, and researchers. Furthermore, its modular design lends itself to adaptable deployment across specific sectors, ensuring consistent performance and flexibility even in expansive applications. With these significant improvements, Llama 3.3 is set to transform the benchmarks for AI language models and inspire further innovations in the field. It is an exciting time for AI development as this new version opens doors to novel possibilities in human-computer interaction.

The NVIDIA Llama Nemotron family includes a range of advanced language models optimized for intricate reasoning tasks and a diverse set of agentic AI functions. These models excel in fields such as sophisticated scientific analysis, complex mathematics, programming, adhering to detailed instructions, and executing tool interactions. Engineered with flexibility in mind, they can be deployed across various environments, from data centers to personal computers, and they incorporate a feature that allows users to toggle reasoning capabilities, which reduces inference costs during simpler tasks. The Llama Nemotron series is tailored to address distinct deployment needs, building on the foundation of Llama models while benefiting from NVIDIA's advanced post-training methodologies. This results in a significant accuracy enhancement of up to 20% over the original models and enables inference speeds that can reach five times faster than other leading open reasoning alternatives. Such impressive efficiency not only allows for tackling more complex reasoning challenges but also enhances decision-making processes and substantially decreases operational costs for enterprises. Furthermore, the Llama Nemotron models stand as a pivotal leap forward in AI technology, making them ideal for organizations eager to incorporate state-of-the-art reasoning capabilities into their operations and strategies.

Llama, a leading-edge foundational large language model developed by Meta AI, is designed to assist researchers in expanding the frontiers of artificial intelligence research. By offering streamlined yet powerful models like Llama, even those with limited resources can access advanced tools, thereby enhancing inclusivity in this fast-paced and ever-evolving field. The development of more compact foundational models, such as Llama, proves beneficial in the realm of large language models since they require considerably less computational power and resources, which allows for the exploration of novel approaches, validation of existing studies, and examination of potential new applications. These models harness vast amounts of unlabeled data, rendering them particularly effective for fine-tuning across diverse tasks. We are introducing Llama in various sizes, including 7B, 13B, 33B, and 65B parameters, each supported by a comprehensive model card that details our development methodology while maintaining our dedication to Responsible AI practices. By providing these resources, we seek to empower a wider array of researchers to actively participate in and drive forward the developments in the field of AI. Ultimately, our goal is to foster an environment where innovation thrives and collaboration flourishes.