InclusionAI: Ling 3.0 Flash
Access Ling 3.0 Flash from InclusionAI using Puter.js AI API.
Get Started// 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"
}).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"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="inclusionai/ling-3.0-flash",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "inclusionai/ling-3.0-flash",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
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.
Context Window 262K
tokens
Max Output 33K
tokens
Input Cost $0.02
per million tokens
Output Cost $0.06
per million tokens
Release Date Jul 23, 2026
Output Speed 424
tokens / sec
Latency 1.37s
time to first token
Model Playground
Try Ling 3.0 Flash instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Ling 3.0 Flash performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 85.5% |
| Humanity's Last Exam Cross-domain reasoning | 23.7% |
| SciCode Scientific programming | 41.1% |
| LCR Long-context reasoning | 67.0% |
Scores sourced from Artificial Analysis.
Find other InclusionAI models →
Ling 3.0 Tiny
Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, Ant Group's AI initiative, the smallest member of the Ling 3.0 family, with 7.9 billion total parameters and 1.3 billion active per token. It supports switchable Thinking and Instant modes, letting a caller trade reasoning depth against response speed, and a 262,144-token context window. InclusionAI positions it for lightweight, resource-sensitive workloads such as task agents, mobile and browser UI automation, code assistance, and other high-frequency, low-latency requests. This differs from its larger sibling Ling 3.0 Flash (5.1B active parameters, general-purpose use) and Ling 2.6 1T (63B active parameters, complex tasks with a 1M-token context). On Artificial Analysis's Intelligence Index, Ling 3.0 Tiny scores 25, above the median of 8 for models in its price tier, and ranks 6th out of 56 models in that class. It supports native function calling. This free-tier listing is offered through OpenRouter.
ChatRing 2.6 1T
Ring 2.6 1T is a trillion-parameter open-weights reasoning model from InclusionAI (Ant Group), released under the MIT license. It uses a Mixture-of-Experts architecture with approximately 63B active parameters per token and supports a 262K context window with up to 66K output tokens. The model offers adaptive reasoning effort through "high" and "xhigh" modes, letting developers tune thinking depth against token cost based on task complexity. It is purpose-built for agentic workflows, coding agents, tool use, and long-horizon multi-step task execution. Ring 2.6 1T scores 95.83 on AIME 2026, 88.27 on GPQA Diamond, and 87.60 on PinchBench in agent mode — surpassing GPT-5.4 and Gemini 3.1 Pro on that benchmark. A strong pick for developers building autonomous agent systems or complex reasoning pipelines.
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 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.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Ling 3.0 Flash to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.02 |
| Output | $0.06 |
Ling 3.0 Flash was created by InclusionAI and released on Jul 23, 2026.
Ling 3.0 Flash supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Ling 3.0 Flash can generate up to 33K tokens in a single response.
Ling 3.0 Flash scores 37.8 on the Artificial Analysis Intelligence Index, outperforming 85% of tracked models. On coding, it scores 50.6 (outperforms 65% of models).
Yes — the Ling 3.0 Flash 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.
Get started with Puter.js
Add Ling 3.0 Flash to your app without worrying about API keys or setup.
Read the Docs View Tutorials