Ling

Ling is a general-purpose large language model series independently developed and open-sourced by Ant Group. Built on the MoE (Mixture of Experts) architecture, it has been validated on domestic heterogeneous computing platforms, achieved breakthrough at the trillion-parameter scale, and continues to evolve with long context modeling, multimodal understanding, and AI Agent collaborative reasoning capabilities.

Why Choose Ling?

Ling achieves key breakthroughs in 4 dimensions: inference efficiency, long context modeling, multimodal understanding, and training technology:

Inference Efficiency

Traditional Dense models require activating all parameters during inference, with computational overhead proportional to model size. Ling’s MoE architecture routes each token to activate only the most relevant expert subnetworks, compressing the actual computation to a minimal fraction while maintaining large-scale model capacity.

Long Context Support

Building on MoE’s efficient inference, the Ling series further advances long-sequence modeling.

• Ling-3.2-flash: Context window up to 1M, with native multimodal understanding.
• Ling-3.1-flash: Context window up to 1M.
• Ling-3.0-flash: Context window up to 256K.
• Long-range information retrieval without noticeable degradation: the model reliably retrieves information regardless of whether it appears at the beginning, middle, or end of the context.

Native Multimodal Understanding

The latest-generation native multimodal model in the Ling series, Ling-3.2-flash, is now released. With 560B total parameters and 25B activated parameters, it targets complex real-world tasks, focusing on four key capabilities: complex visual understanding, multimodal long-horizon Agent, 3D understanding & interaction, and medical multimodal — tightly integrating multimodal perception, deep reasoning, and autonomous execution:

• Native support for image, text, and video input: Goes beyond simple image captioning — multimodal information serves as a foundational input for reasoning, enabling deeper cross-modal understanding.
• Four key capability areas: Complex visual understanding, multimodal long-horizon Agent, 3D understanding & interaction, and medical multimodal — tightly integrating multimodal perception, deep reasoning, and autonomous execution.

The previously released Ling-3.0-flash-VL also deeply integrates visual understanding into the MoE architecture:

• Native support for image, text, and video input: Goes beyond simple image captioning — multimodal information serves as a foundational input for reasoning, enabling deeper cross-modal understanding.
• Visual feedback closed-loop mechanism: Advances tasks through a continuous “Observe → Act → Verify → Correct” cycle, allowing the model to continuously refine execution results based on visual feedback in scenarios such as medical report interpretation, frontend code generation, and GUI automation.

Model Selection Guide

The following is a capability comparison of Ling models at different scales to help you evaluate and select:

Selection Suggestions:

• Need to handle complex multimodal tasks such as complex visual understanding, multimodal long-horizon Agent, 3D understanding & interaction, or medical multimodal? Choose Ling-3.2-flash, with native multimodal understanding that tightly integrates multimodal perception, deep reasoning, and autonomous execution.
• Need a model as a personal assistant for office work, long-horizon development, or complex Agentic tasks? Choose Ling-3.1-flash. With around 560B total parameters, it maintains high completion rates across multi-step planning, tool-chain invocation, and long-running self-correction, backed by strong world knowledge.
• Looking to build workflows for low-cost, batch text processing or repetitive Agentic tasks? Or want real-time feedback? Start with Ling-3.0-flash — low cost, fast response, and effortless task handling.
• Need to handle images, videos, and other multimodal content, or build vision-related automation workflows? Choose Ling-3.0-flash-VL, which natively supports image, text, and video input and continuously refines execution results through a visual feedback closed-loop, ideal for image-to-web, GUI automation, and similar scenarios.
• For online service scenarios sensitive to inference latency and throughput, Ling-3.0-flash’s low activated parameter count gives it superior TTFT (Time to First Token) and TPS (Tokens Per Second) performance.
• Need on-device deployment, local offline execution, or extremely cost- and resource-constrained environments? Choose Ling-3.0-tiny — with only 1.3B activated parameters, it handles real-time interaction, lightweight code assistance, local knowledge base retrieval, and tool calling with ease.

Model Details

Next, let’s dive into the technical characteristics and Use Cases of each model:

Ling-3.2-flash

Ling-3.2-flash is the latest-generation native multimodal model in the Ling series, with 560B total parameters and 25B activated parameters. The context window is capped at 1M, with native support for image, text, and video input. The model targets complex real-world tasks, focusing on four key capabilities: complex visual understanding, multimodal long-horizon Agent, 3D understanding & interaction, and medical multimodal — tightly integrating multimodal perception, deep reasoning, and autonomous execution.

Advantages:

• Native multimodal understanding: Fuses vision and language capabilities at the architectural level, supporting image, text, and video input without relying on external vision modules
• Four key capabilities: Focuses on complex visual understanding, multimodal long-horizon Agent, 3D understanding & interaction, and medical multimodal — tightly integrating multimodal perception, deep reasoning, and autonomous execution
• Balance of high capacity and low compute overhead: Retains 560B model capacity while keeping per-step activation at around 25B, balancing model capability with inference efficiency
• 1M context window: Supports long document and long video analysis for demanding context scenarios

Use Cases:

• Complex visual understanding: Deeply understands image and video content, supporting visual reasoning and analysis tasks
• Multimodal long-horizon Agent: Maintains goal alignment across multi-step tasks, making decisions and executing based on multimodal information
• 3D understanding & interaction: Understands 3D scenes and spatial relationships, supporting 3D-related interaction tasks
• Medical multimodal: Medical imaging understanding and report interpretation, assisting professional medical analysis

Ling-3.1-flash

Ling-3.1-flash is a hybrid reasoning model in the Ling series, optimized for long-horizon real-world tasks and agent / Agent scenarios. The model has around 560B total parameters, activating about 25B parameters per token; the context window is capped at 1M.

Advantages:

• Balance of high capacity and low compute overhead: Retains 560B model capacity while keeping per-step activation at around 25B, balancing model capability with inference efficiency; balances world knowledge and response performance, suitable as an everyday assistant for a variety of tasks.
• Long-horizon state maintenance and self-correction: Built for multi-step tasks lasting hours or longer, it consistently maintains goal alignment across multiple rounds of tool calling and environment interaction, and adjusts its path in time based on intermediate results.

Use Cases:

• Everyday office collaboration. Handles the full chain from vague requirements to delivered output, including research synthesis, data analysis, and report and presentation creation.
• Software development. Suited for complex development tasks such as cross-language refactoring, performance optimization, and codebase hotspot analysis and interpretation.
• Professional consulting and analysis. Suited for comprehensive analysis, synthesis, information and metric interpretation, and recommended actions and reports across multiple professional domains under fragmented information.

Ling-3.0-flash-VL

Ling-3.0-flash-VL is the first native multimodal large model in the Ling series, extended from Ling-3.0-flash’s MoE (Mixture of Experts) architecture. It features 124B total parameters with 5.5B activated per inference, natively supports image, text, and video input, with a 256K token context window. The model is now open-sourced on Hugging Face and ModelScope.

Advantages:

• Native multimodal understanding: Fuses vision and language capabilities at the architectural level, supporting image, text, and video input without relying on external vision modules
• Visual feedback closed-loop mechanism: Introduces a continuous “Observe → Act → Verify → Correct” cycle, enabling the model to continuously refine execution results based on visual feedback, significantly improving task reliability and accuracy. Unlike one-shot image-to-output generation, this mechanism transforms the process into a dynamic, self-correcting workflow in scenarios such as medical report interpretation, frontend code generation, and GUI automation
• Arbitrary-resolution visual encoder: Introduces an arbitrary-resolution visual encoder and VideoRoPE, maintaining low-latency responses in real-time video conversations, multi-turn visual interactions, and long-duration tasks
• Deep architectural synergy: Language backbone retains the 42-layer hybrid architecture (KDA and Gated MLA alternating at a 5:1 ratio), activating only 5.5B parameters per inference from 124B total — balancing high performance with cost efficiency
• 256K context window: Supports long document and long video analysis for demanding context scenarios

Use Cases:

• Visual feedback programming: Understands layout and component relationships from screenshots or reference images to generate frontend code, with self-correction via rendered output comparison to produce highly faithful web pages
• GUI automation: As a GUI Agent, recognizes interface structures and performs cross-tool operations, effortlessly handling diverse productivity scenarios
• Professional report interpretation: Possesses medical domain expertise while supporting cross-document and cross-format data integration and risk flagging — suitable for specialized document analysis such as health checkup report interpretation
• Real-time video learning & explanation: Enhanced subject-matter knowledge and visual reasoning capabilities enable snapshot-based learning, real-time video explanations, and video knowledge extraction, creating an interactive “watch and ask” learning companion. This experience is already available to users in the “灵光” (Ling Guang) app
• Multimodal office automation: Handles comprehensive office tasks involving images, documents, and videos via MCP interfaces

Ling-3.0-flash

• Ling-3.0-flash is the latest-generation cost-effective model in the Ling series, with 124B total parameters, 5.1B activated parameters, a native 256K context window extendable up to 1M.
• Compared to the previous flash model, Ling-3.0-flash delivers significantly enhanced stability in long-horizon tasks, markedly higher tool calling accuracy, and substantially improved compatibility with common Harness environments. In coding tasks, Ling-3.0-flash features greatly optimized spatial understanding, capable of constructing physical scene grids and relative positions. Additionally, thanks to its hybrid Reasoning mode, task success rates across varying difficulty levels have all improved.

Advantages:

• Cost-effective: lower activation, higher throughput — lower cost and higher efficiency per unit task, handling complex tasks with greater ease
• Seamless switching between thinking and non-thinking modes — engage deep thinking for complex tasks, or disable it for high-volume production and low-latency scenarios
• High TPS for high-frequency tasks: peak inference speed reaches 1000 tokens/s with TTFT < 100ms, enabling more reading, checking, and thinking within the same time unit for more iterations and more accurate results
• Stable tool calling: under the RL strong-check mechanism, long-horizon tool calling stability is significantly improved with reliable instruction following
• Native 256K context window, extendable up to 1M, with full tool calling and Agent capabilities

Use Cases:

• Office automation, office collaboration, and Cowork
• Human-AI collaboration: agile and efficient daily code development under human guidance
• High-concurrency batch data processing and analysis scenarios, such as resume screening, document review, knowledge base organization, and data cleaning
• Scenarios requiring high response speed, such as digital human live-streaming, streaming media interaction, and real-time translation

Ling-3.0-tiny

• Ling-3.0-tiny is a lightweight hybrid reasoning model in the Ling series designed for edge deployment scenarios, with 7.9B total parameters and only 1.3B activated parameters. It supports on-device deployment and local offline execution, and will be open-sourced in the near future.
• With minimal activated parameters, it delivers real-world task execution capability, combining mathematical reasoning, instruction following, and low hallucination, achieving balanced performance across scientific reasoning, code, real-world tasks, and long context.

Advantages:

• Ultra-lightweight: only 1.3B activated parameters, deployable on edge devices and resource-constrained environments with low inference latency and minimal compute overhead
• Comprehensive capability coverage: practical performance in mathematical reasoning, instruction following, code generation, and tool calling — “tiny” does not mean compromised capability
• Native tool-use support, enabling lightweight automation scenarios such as mobile device and browser UI automation
• Local offline execution support, ideal for privacy-sensitive private deployments where data must not leave the device

Use Cases:

• On-device applications and local offline inference, such as local knowledge base retrieval and content generation
• Lightweight code assistants, local web page translation, and other high-frequency low-latency tasks
• Task agents in enterprise private deployments and model foundations for vertical scenarios
• Tool calling and UI automation for real-time control scenarios

Ling’s Evolution

Ling has undergone a complete technical evolution from computing platform validation to Agent capability breakthroughs:

Technology Ecosystem

Based on the Ling foundation model, we have built a complete technology ecosystem covering the full pipeline from training to deployment:

• High-Performance Operator Library: Open-sourced high-performance training and inference operator system, covering core components such as MoE routing and attention computation, supporting full-pipeline optimization from pre-training to online inference.
• Vertical Domain Models: Domain-adapted models for specialized scenarios such as healthcare and finance, with superior performance on domain knowledge-intensive tasks.
• Open Source Community: All research results open-sourced to the Inclusion AI  community, continuously co-building the ecosystem with developers.

Quick Start

1. Create API Key: Obtain access credentials.
2. Make Your First Call: Complete your first API request in 5 minutes.
3. Explore More Capabilities: Learn more about advanced features such as inference optimization and long context.