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-3.0-flash: Native 256K context window, extendable up to 1M.
• Ling-2.6-1T: Supports up to 1M context window natively; the official API currently exposes a 256K context window.
• 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 first native multimodal model in the Ling series, Ling-3.0-flash-VL, is now released and open-sourced, deeply integrating 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:

• For most general-purpose text scenarios, start with Ling-3.0-flash — it delivers higher efficiency under the same compute resources, handles complex tasks with greater ease, and significantly reduces cost.
• 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.
• Need to handle ultra-long documents, complex multi-hop reasoning, or Agent task chains? Choose Ling-2.6-1T, which leverages the innovative MLA and Linear Attention Hybrid architecture to bypass cumbersome “slow thinking” and achieve efficient inference through a “fast thinking” mechanism, reaching results with minimal token overhead and dramatically reducing output cost.
• 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-3.0-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-2.6-1T

Ling-2.6-1T is the latest-generation flagship model in the Ling series. It uses a Hybrid architecture combining MLA and Linear Attention, with approximately 1T total parameters and 63B activated parameters, supports a 1M ultra-long context, and delivers a strong balance between flagship-level intelligence and token efficiency.

Advantages:

• Fast thinking replaces lengthy reasoning chains, preserving 1T parameter level capability at lower token cost.
• Stronger coding and Agent capabilities, achieving open-source SOTA on execution-focused benchmarks such as AIME26 and SWE-bench Verified.
• Highly compatible with mainstream Agent frameworks including Claude Code, OpenCode, and OpenClaw, covering multi-tool, multi-step, and multi-constraint scenarios.

Use Cases:

• Multi-step tasks and agent tasks
• Code completion, project delivery, and bug fixing
• Data visualization projects such as slides and reports
• Long-context knowledge management and automated workflows

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.