Tencent: Hy3
Try Hy3 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: "tencent/hy3"
}).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: "tencent/hy3"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Tencent Hy3 is the official release of Tencent Hunyuan's Hy3 series, a hybrid fast-and-slow-thinking Mixture-of-Experts model with 295B total parameters and 21B active per query, following the earlier hy3-preview. It supports a 262K-token context window and up to 131K output tokens.
Compared to the preview, Tencent reports agent and coding capability gains of 20-30%, a hallucination rate cut from 12.5% to 5.4%, and commonsense error rates nearly halved. It scores 78 on SWE-bench Verified, 57.9 on SWE-bench Pro, and 90.4 on GPQA Diamond, and Tencent says it matches flagship models with two to five times its parameter count.
Hy3 ships under Apache 2.0 and already powers Tencent products like WorkBuddy/CodeBuddy and Yuanbao, with a reported 90% task resolution rate on Tencent's internal WorkBuddy platform. It's a good fit for developers building coding agents, tool-using workflows, and long-context reasoning pipelines who want strong performance at a lower active-parameter cost.
Context Window 203K
tokens
Max Output 131K
tokens
Input Cost $0.13
per million tokens
Output Cost $0.53
per million tokens
Release Date Jul 6, 2026
Output Speed 86
tokens / sec
Latency 2.93s
time to first token
Try Hy3 for free
Try Hy3 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Hy3 performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 89.7% |
| Humanity's Last Exam Cross-domain reasoning | 33.5% |
| SciCode Scientific programming | 48.6% |
| LCR Long-context reasoning | 79.0% |
Scores sourced from Artificial Analysis.
Find other Tencent models →
Hy4 Flash
Hy4 Flash is a multimodal large language model from Tencent Hunyuan, released as a lower-cost, faster variant of Hy4. It accepts text and image input, produces text output, supports tool calling, and has a 1,024,000-token context window with up to 64,000 output tokens. Tencent recommends it for everyday work such as deep search, document processing, slides, simple front-end development, and computer use, and recommends Hy4 for long-horizon software engineering. On Terminal-Bench 4.0, Tencent reports 19.2 for Hy4 Flash against 44.4 for Hy4. In Plotly's data analysis benchmark (a single run per model), it scored 39 of 43 for $0.13 per run, compared with 42 for Hy4 at $2.11. It suits developers who want long context, image understanding, and tool calling at a fraction of Hy4's price.
ChatHy4
Hy4 is the official release of Tencent Hunyuan's Hy4 model series, the successor to Hy4 Preview. Tencent reports substantial improvements over the preview, with the largest gains in agentic capabilities and long-horizon, real-world productivity tasks. Unlike the text-only preview, Hy4 accepts both text and image input and returns text. It supports a context window of about 1M tokens and up to 65,536 output tokens, with tool calling, structured outputs, and configurable reasoning effort (none, low, or high). It suits developers building coding agents, multi-step tool-use workflows, and productivity applications that need long context and image understanding via API.
ChatHy4 Preview
Tencent Hy4 Preview is an open-weight Mixture-of-Experts model from Tencent's Hunyuan team, the successor to Hy3. It has 770B total parameters with 49B active per token, and supports a context window over 1M tokens. It's released under the Apache 2.0 license and supports tool calling. In Tencent's internal blind evaluation across 203 engineering tasks judged by 163 experts, Hy4 Preview scored 2.99 out of 4.00, ahead of GLM-5.3 (2.92) and Kimi K3 (2.94). It scores 85.4 on Terminal-Bench 2.1, surpassing DeepSeek V4 Pro, and 82.9 on SWE-bench Multilingual, up from Hy3's 75.8. On DeepSWE, its score rose from Hy3's 28.0 to 64.3. It's aimed at coding agents, software engineering, office and document generation, and scientific research workflows via API.
Frequently Asked Questions
You can access Hy3 by Tencent 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.
Hy3 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.
Hy3 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 | $0.13 |
| Output | $0.53 |
Hy3 was created by Tencent and released on Jul 6, 2026.
Hy3 supports a context window of 203K tokens. For reference, that is roughly equivalent to 406 pages of text.
Hy3 can generate up to 131K tokens in a single response.
Yes — the Hy3 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 Hy3 to your app for free
Developers can integrate Hy3 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.