InclusionAI: Ling 3.0 Flash VL
Try Ling 3.0 Flash VL for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "inclusionai/ling-3.0-flash-vl"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "inclusionai/ling-3.0-flash-vl"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Ling 3.0 Flash VL is InclusionAI's (Ant Group) native multimodal vision-language model, sharing Ling 3.0 Flash's Mixture-of-Experts architecture with 124B total parameters and about 5.5B active per token. It adds image and video understanding through a hybrid backbone mixing Kimi Delta Attention and gated multi-head latent attention layers, plus a VideoRoPE position encoding for tracking motion across video frames.
InclusionAI reports the model routes visual input through the same reasoning and self-verification pipeline used for text, spanning object counting, chart and document reading, multi-step reasoning with visual evidence, and interface understanding for task automation. It scores 42 on the Artificial Analysis Intelligence Index (v4.1.1), four points above Ling 3.0 Flash's 38.
This paid tier is served at a 131,072-token context (versus 262,144 on the free tier) and supports function calling, useful for agentic workflows like GUI automation or document-analysis agents that combine visual input with tool use.
Context Window 131K
tokens
Max Output 33K
tokens
Input Cost $0.06
per million tokens
Output Cost $0.18
per million tokens
Input text, image, video
modalities
Tool Use Yes
Release Date Sep 10, 2026
Try Ling 3.0 Flash VL for free
Try Ling 3.0 Flash VL instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Ling 3.0 Flash VL performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 86.2% |
| Humanity's Last Exam Cross-domain reasoning | 22.0% |
| SciCode Scientific programming | 44.2% |
| LCR Long-context reasoning | 78.3% |
Scores sourced from Artificial Analysis.
Find other InclusionAI models →
Ling 3.1 Flash
Ling 3.1 Flash is a Mixture-of-Experts language model from InclusionAI (Ant Group), announced on September 30, 2026 as the next fast-tier model after Ling 3.0 Flash. It has 560 billion total parameters with about 25 billion active per token. InclusionAI positions it for agent tasks, search, office software, and specialist applications. It is designed for a context window of up to one million tokens, while the current free trial is limited to 256,000 tokens. The API accepts reasoning, tool-related, and sampling parameters such as temperature and seed. At the time of the announcement, the benchmark figures came only from Ant Group, and no independent evaluations had been published, so this entry lists no scores. InclusionAI has said it plans to enable the full context window and release the model as open source after the trial. It suits developers who want to test a large, low-cost model for agent and long-document workloads.
ChatLing 3.0 Flash
Ling 3.0 Flash is InclusionAI's (Ant Group) successor to Ling 2.6 Flash, a hybrid-reasoning Mixture-of-Experts model with 124B total parameters and about 5.1B active per token. It stacks five Kimi Delta Attention (KDA) layers per one Multi-Head Latent Attention (MLA) layer, combining efficient long-range memory with precise attention, and supports both thinking and non-thinking modes. According to InclusionAI, with roughly 1/8 of the total parameters and 1/12 of the active parameters of its 1T-parameter flagship model, Ling 3.0 Flash matches or beats that flagship on most of the benchmarks the company reported. It natively supports a 262K-token context window, with InclusionAI designing it to scale toward 1M context; the paid tier here is served at 131K context. It targets high-frequency agentic workflows such as coding agents, tool use, document processing, and long multi-turn conversations, where per-token cost and latency matter.
ChatLing 2.6 1T
Ling 2.6 1T is InclusionAI's trillion-parameter flagship non-reasoning model, built by Ant Group's AGI initiative. It uses a Mixture-of-Experts architecture with approximately 50 billion active parameters per token, employing a "fast thinking" approach that reduces token costs to roughly a quarter of comparable models while maintaining top-tier output quality. The model targets advanced coding, complex reasoning, and large-scale agent workflows. It achieves state-of-the-art results on benchmarks like AIME 2025 and SWE-bench Verified, and ranks first among open-source models on ArtifactsBench for front-end code generation. On the Artificial Analysis Intelligence Index, it scores 34 — far above the median of 13 for comparable open-weight non-reasoning models. With a 262K context window and strong tool-use capabilities out of the box, Ling 2.6 1T is a strong fit for developers building autonomous agents or cost-sensitive pipelines that need flagship-level reasoning without a dedicated thinking model.
Frequently Asked Questions
You can access Ling 3.0 Flash VL by InclusionAI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Ling 3.0 Flash VL is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Ling 3.0 Flash VL is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.06 |
| Output | $0.18 |
Ling 3.0 Flash VL was created by InclusionAI and released on Sep 10, 2026.
Ling 3.0 Flash VL supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
Ling 3.0 Flash VL can generate up to 33K tokens in a single response.
Ling 3.0 Flash VL accepts the following input types: text, image, video. It produces: text.
Yes, Ling 3.0 Flash VL supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Ling 3.0 Flash VL scores 24.6 on the Artificial Analysis Intelligence Index, outperforming 75% of tracked models. On coding, it scores 57.0 (outperforms 65% of models).
Yes — the Ling 3.0 Flash VL API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Ling 3.0 Flash VL to your app for free
Developers can integrate Ling 3.0 Flash VL for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.