// 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>
# 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="tencent/hy3",
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": "tencent/hy3",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
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 262K
tokens
Max Output 131K
tokens
Input Cost $0.14
per million tokens
Output Cost $0.58
per million tokens
Release Date Jul 6, 2026
Output Speed 190
tokens / sec
Latency 1.79s
time to first token
Model Playground
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 | 86.7% |
| Humanity's Last Exam Cross-domain reasoning | 25.5% |
| SciCode Scientific programming | 41.2% |
| IFBench Instruction following | 63.1% |
| LCR Long-context reasoning | 54.7% |
| Terminal-Bench Hard Agentic terminal tasks | 34.1% |
| τ²-Bench Tool use / agents | 92.7% |
Scores sourced from Artificial Analysis.
Find other Tencent models →
Hy 3 Preview
Tencent Hy3 is a 295B-parameter Mixture-of-Experts reasoning model developed by Tencent's Hunyuan team, with only 21B parameters active per query. It supports a 256K-token context window and configurable reasoning levels (disabled, low, high), letting you trade off latency and depth per request. Hy3 is particularly strong on coding and agentic tasks. It scores 74.4% on SWE-bench Verified for real-world bug fixing and 67.1% on BrowseComp for complex web research. Its MoE architecture delivers competitive performance against much larger models — matching Kimi-K2.5 (1T+ parameters) on agent benchmarks at a fraction of the compute cost. Best suited for developers building agentic workflows, code generation pipelines, and multi-step reasoning applications where cost-efficiency matters.
ChatHunyuan A13B Instruct
Hunyuan A13B Instruct is an open-source large language model from Tencent built on a fine-grained Mixture-of-Experts (MoE) architecture, with 80B total parameters and 13B active during inference. It natively supports a 256K-token context window. It performs competitively with OpenAI o1 and DeepSeek R1 across math, science, and reasoning benchmarks, scoring 87.3 on AIME 2024, 89.1 on BBH, and 84.7 on ZebraLogic. Hunyuan A13B particularly excels at agentic tasks and tool use, leading on benchmarks like BFCL-v3 (78.3) and ComplexFuncBench (61.2). It's a strong choice for developers building agent workflows, long-context applications, or cost-sensitive reasoning pipelines.
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.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Hy3 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 | $0.14 |
| Output | $0.58 |
Hy3 was created by Tencent and released on Jul 6, 2026.
Hy3 supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Hy3 can generate up to 131K tokens in a single response.
Hy3 scores 33.6 on the Artificial Analysis Intelligence Index, outperforming 85% of tracked models.
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.
Get started with Puter.js
Add Hy3 to your app without worrying about API keys or setup.
Read the Docs View Tutorials