InclusionAI: Ling 3.0 Tiny
This model is no longer available.Add AI to your application with Puter.js.
Explore Other Models
Model Card
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.
Context Window 262K
tokens
Max Output 33K
tokens
Input Cost $0
per million tokens
Output Cost $0
per million tokens
Tool Use Yes
Release Date Aug 6, 2026
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 VL
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.
ChatLing 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.
Frequently Asked Questions
Ling 3.0 Tiny is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0 |
| Output | $0 |
Ling 3.0 Tiny was created by InclusionAI and released on Aug 6, 2026.
Ling 3.0 Tiny supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Ling 3.0 Tiny can generate up to 33K tokens in a single response.
Yes, Ling 3.0 Tiny supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Ling 3.0 Tiny 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