InclusionAI: Ring 2.6 1T
This model is no longer available.Add AI to your application with Puter.js.
Explore Other Models
Model Card
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.
Context Window 262K
tokens
Max Output 66K
tokens
Input Cost $0.08
per million tokens
Output Cost $0.63
per million tokens
Release Date May 8, 2026
Output Speed 122
tokens / sec
Latency 2.06s
time to first token
Code Example
Add AI to your app with the Puter.js AI API — no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").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").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From InclusionAI
Find other InclusionAI models →
Ling 3.0 Flash Sante
Ling 3.0 Flash Sante is InclusionAI's (Ant Group) health and medicine fine-tune of Ling 3.0 Flash. It keeps the base model's hybrid Mixture-of-Experts architecture, pairing Kimi Delta Attention with Multi-Head Latent Attention, with 124B total parameters and about 5.1B active per token, and a 262,144-token context window. The fine-tune targets medical knowledge reasoning, clinical safety, and evidence-based retrieval, along with long-horizon medical workflows such as multi-step clinical question answering. It retains the base model's general reasoning, coding, and agentic capabilities, and supports function calling for tool-based workflows. InclusionAI has not published domain-specific benchmark scores for this fine-tune. It suits developers building clinical decision-support tools, medical literature search, or other health-focused assistants; outputs should still be reviewed by qualified professionals rather than used as medical advice.
ChatLing 3.0 Flash Fin
Ling 3.0 Flash Fin is InclusionAI's (Ant Group) finance-domain fine-tune of Ling 3.0 Flash, developed with financial institutions and domain experts. It keeps the base model's Mixture-of-Experts architecture, 124B total parameters with about 5.1B active per token, and a 262,144-token context window. The model is built for real-world investment workflows, including source-grounded financial search, multi-document reasoning across regulatory filings and earnings reports, valuation modeling, and spreadsheet operations. It handles multi-step financial tasks and long-horizon planning while retaining the base model's general coding, math, and reasoning ability. InclusionAI evaluated it on finance-specific benchmarks including FinFIRST, FinCRAFT, and SpreadsheetBench, reporting it competitive with similarly sized and larger general-purpose models on tool-intensive financial tasks. It supports function calling for agent-style workflows that call external data or calculation tools. It suits developers building investment research assistants, financial document analysis tools, or other finance-specific agents. InclusionAI notes that outputs require professional review and are not investment advice.
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.
Frequently Asked Questions
You can access Ring 2.6 1T 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 Ring 2.6 1T 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 | $0.08 |
| Output | $0.63 |
Ring 2.6 1T was created by InclusionAI and released on May 8, 2026.
Ring 2.6 1T supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Ring 2.6 1T can generate up to 66K tokens in a single response.
Ring 2.6 1T scores 23.7 on the Artificial Analysis Intelligence Index, outperforming 70% of tracked models. On coding, it scores 42.8 (outperforms 47% of models).
Yes — the Ring 2.6 1T 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 AI to your application without worrying about API keys or setup.
Explore Models View Tutorials