Tencent
Hy4 preview
tencent/hy4-preview
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
RoleA chat model that spends extra steps before it answers.
$0.834
In / M
$2.5
Out / M
1.0M
Context
- AA intelligence index
- Not on listing
- Inputs
- text
- Outputs
- text
- Tools
- Listed
- Structured output
- Listed
- Reasoning
- Listed
- Weights
- Open · tencent/Hy4-preview
- Listed
- Aug 28, 2026
01 · What it's good at
Use it for this.
Three jobs this model is built for, and the ones to give to something else.
01
Harder questions where a quick draft is not enough
02
Agents that already support a reasoning effort
Skip it for
- Bulk transforms where you are paying for speed
- Classification you meant to threshold
02 · Example tasks
What you'd actually send it.
Real inputs, not a benchmark. Paste one into the snippet below to try it.
You send
Read the failing test and the module. Explain the cause, then propose the smallest fix.
Why this model
Reasoning models spend extra steps before answering.
03 · Your stack
Where it sits: Plan & reason.
Reasoning models still return text. The extra thinking is a budget knob, not a different kind of product. Turn it down when the task is a rewrite or a sort.
Layer 01
Retrieve
Layer 02 · this model
Plan & reason
Layer 03
Do the volume
Layer 04
Gate & route
Layer 05
Draw, speak, listen
04 · Wire it up
One request. Paste and run.
Uses OpenRouter, so one key works for every model on this site. Set OPENROUTER_API_KEY and swap the prompt for one of the tasks above.
// OpenRouter speaks the OpenAI Chat Completions format.
const res = await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "tencent/hy4-preview",
"messages": [
{
"role": "user",
"content": "Read this error and explain the most likely cause in three sentences: <paste error>"
}
],
"reasoning": {
"effort": "low"
}
}),
});
const data = await res.json();
console.log(data.choices[0].message.content);
05 · Watch out for
Gotchas.
This lesson is generated from the model type and the live listing. It has not been hand-reviewed yet.
Check the listing for supported parameters before you rely on tools or structured output.
Sources
Lessons are written from each model's listing and the linked docs. We don't publish our own benchmark numbers; the index above is Artificial Analysis, as shown on OpenRouter.