Ling 2.6 Flash
Ling 2.6 Flash is the latest cost-effective model in the Ling series, built on a Mixture of Experts architecture with 104B total parameters and 7.4B activated parameters. It is designed to achieve an optimal balance between inference performance and compute cost, making it suitable for general-purpose scenarios where strong reasoning capability, high throughput, and efficient deployment matter. Ling’s MoE architecture routes each token to activate only the most relevant expert subnetworks, compressing actual computation to a minimal fraction while maintaining large-scale model capacity. Ling 2.6 Flash provides a native 256K context window and can process approximately 200,000 characters of long-form input, with reliable long-range information retrieval whether key information appears at the beginning, middle, or end of the context. Its aggregate benchmark performance is comparable to or exceeds 40B-class Dense models.
Learn more
Ling 2.6
Ling 2.6 is a general-purpose large language model series independently developed and open-sourced by Ant Group, built on a Mixture of Experts architecture and designed for inference efficiency, long context modeling, training technology, and AI Agent collaborative reasoning. Ling’s MoE architecture routes each token to activate only the most relevant expert subnetworks, compressing actual computation to a minimal fraction while maintaining large-scale model capacity. The Ling 2.6 series further advances long-sequence modeling, with Ling-2.6-1T supporting up to a 1M native context window and the official API exposing a 256K context window, while Ling-2.6-flash provides a native 256K context window capable of processing approximately 200,000 characters of long-form input. The models are designed for reliable long-range information retrieval, with no noticeable degradation whether information appears at the beginning, middle, or end of the context.
Learn more
Hy3
Hy3 preview is Tencent Hy’s most intelligent model in the Hy series to date, built as a 295B-parameter Mixture-of-Experts model with 21B activated parameters, 3.8B MTP layer parameters, and support for up to a 256K token context window. As the first model trained on Tencent Hy’s rebuilt infrastructure, Hy3 preview is designed to improve real-world usability across complex reasoning, instruction following, context learning, coding, agent capabilities, and overall inference performance. It integrates both fast and slow thinking capabilities, allowing direct responses for simpler tasks and deeper reasoning for complex math, coding, and reasoning work. The model is built around well-rounded capabilities across long-context understanding, instruction following, tool use, and agent workflows, with evaluation focused not only on standard benchmarks but also on authentic business and development scenarios.
Learn more
MiniMax M3
MiniMax M3 is an open-weight multimodal AI model designed for coding, agentic workflows, long-context reasoning, and complex automation tasks. The model combines frontier-level coding performance, native multimodal understanding, and a context window of up to 1 million tokens. MiniMax M3 uses MiniMax Sparse Attention to improve long-context efficiency while reducing compute requirements for large-scale inputs. It supports text, image, and video understanding, making it useful for workflows that combine code, documents, visual references, and tool-driven tasks. The model is built for repository-scale reasoning, software engineering, autonomous task execution, tool calling, and multi-step agent workflows. MiniMax M3 helps developers, AI teams, and enterprises build capable agents that can reason across large contexts and work with multimodal information.
Learn more
