Back to models
Tencent
Hy3 Preview
MoEotherReleased Apr 2026
Tencent's flagship open-weight Mixture-of-Experts model from the Hunyuan family with 295B total parameters and 21B active. Integrates fast and slow thinking modes with configurable reasoning effort. Designed for agentic workflows, cross-file code refactoring, long-document analysis, and multi-step tool use.
Capabilities
chatcompletionfunction-callingcode-generationreasoning
Modalities
textcode
Context Window
256K tokens
Providers
2
available
Available from 2 providers
Cheapest
OpenRouter
$0.00/1M tokens
OpenRouter, SiliconFlow
Providers (2)
Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.
| Provider | Pricing (per 1M) | Rate Limits | Regions | Health | Latency |
|---|---|---|---|---|---|
| OpenRouter | In: FreeOut: Free | 20 RPM / 200K TPM | us-east-1 | Healthy | 0ms |
| SiliconFlow | In: $0.14Out: $0.28 | 300 RPM / 500K TPM | ap-east-1global | Healthy | 0ms |
Quick Start
Use this model via OpenRouter with an OpenAI-compatible SDK.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const response = await client.chat.completions.create({
model: "tencent/hy3-preview",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);Using OpenRouter API • OpenAI-compatible SDK