Alibaba: Tongyi DeepResearch 30B A3B
This model is no longer available.Add AI to your application with Puter.js.
Explore Other Models
Model Card
Tongyi DeepResearch 30B A3B is an agentic large language model from Alibaba's Tongyi Lab, purpose-built for long-horizon, multi-step information-seeking and web research tasks. It uses a Mixture-of-Experts architecture with 30.5B total parameters but only 3.3B activated per token, keeping inference costs low.
The model achieves state-of-the-art results across agentic research benchmarks, scoring 32.9 on Humanity's Last Exam, 43.4 on BrowseComp, 70.9 on GAIA, 75.0 on xbench-DeepSearch, and 90.6 on FRAMES — outperforming OpenAI o3 and DeepSeek-V3.1 on most of these tasks.
It supports a 128K context window and two inference modes: a standard ReAct mode and a heavier iterative research mode for maximum performance. Best suited for developers building autonomous research agents, deep fact-finding pipelines, or complex multi-source synthesis workflows — especially where cost efficiency matters.
Context Window 131K
tokens
Max Output 131K
tokens
Input Cost $0.09
per million tokens
Output Cost $0.45
per million tokens
Release Date Sep 18, 2025
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 Alibaba
Qwen Image 3
Qwen Image 3 is Alibaba's third-generation text-to-image model from the Qwen team, released in July 2026 as a closed model with no public weights. It accepts prompts of up to 4,500 tokens, so a multi-panel layout such as an infographic grid or a nested interface mockup can be generated in a single pass. It renders text natively in 12 languages, including legible text as small as ten pixels and mathematical formulas with subscripts and superscripts. It also produces photorealistic detail such as skin pores and individual hair strands, and supports image editing that matches the original style. Alibaba has not published benchmarks for this release. Its predecessor, Qwen Image 2.0, ranked just behind GPT Image 2 and Nano Banana Pro on Alibaba's arena platform. It suits developers building posters, infographics, multilingual product visuals, and storyboards where long prompts and accurate text matter.
ImageQwen Image 3 Pro
Qwen Image 3 Pro is Alibaba's flagship third-generation text-to-image and image-editing model from the Qwen team. It entered an invitation-only cloud preview on July 21, 2026 and opened to all users on August 5. Alibaba lists support for prompts up to 4.5K tokens, dense layouts such as newspapers, menus, storyboards, and exam papers, and text rendering at sizes down to about 10 pixels. It renders text natively in 12 languages with more than 20 fonts, and it improves skin, hair, and material textures over earlier versions. On the Text-to-Image Arena leaderboard it debuted at #5 with a score of 1,263, up from Qwen Image 2.0 Pro at #15 with 1,191. It suits developers building posters, infographics, and multilingual design assets that need accurate text.
VideoHappyHorse 1.1 Text-to-Video
HappyHorse 1.1 Text-to-Video is a video generation model from Alibaba's ATH (Alibaba Token Hub) AI Innovation Unit, generating video and synchronized audio together in a single pass rather than adding sound afterward. It builds on HappyHorse 1.0, with Alibaba reporting improvements in motion dynamics, subject consistency, prompt adherence, visual quality, and audio generation. The model outputs clips from 3 to 15 seconds at 720p or 1080p, in 16:9, 9:16, 1:1, 4:3, or 3:4 aspect ratios, with lip-synced dialogue, ambient sound, and effects generated alongside the visuals. Following its release in June 2026, it ranked No. 2 across Artificial Analysis's Video Arena leaderboards, behind Google's Veo 3.1.
Frequently Asked Questions
Tongyi DeepResearch 30B A3B is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.09 |
| Output | $0.45 |
Tongyi DeepResearch 30B A3B was created by Alibaba and released on Sep 18, 2025.
Tongyi DeepResearch 30B A3B supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
Tongyi DeepResearch 30B A3B can generate up to 131K tokens in a single response.
Yes — the Tongyi DeepResearch 30B A3B 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