Tencent: Hy3 · Tencent
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent with 21B active parameters and 192 experts. Built for complex reasoning, agentic workflows, and real-world production use. Features configurable reasoning effort for tasks requiring deep analytical thinking.
About Tencent: Hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent with 21B active parameters and 192 experts. Built for complex reasoning, agentic workflows, and real-world production use. Features configurable reasoning effort for tasks requiring deep analytical thinking.
Where it shines: Configurable reasoning effort · Efficient MoE architecture · Production-ready design.
How to use Tencent: Hy3
-
1
Type or upload
Type what you want in the box above — or upload the file if the tool asks for one.
-
2
Generate
Click the main button. Wait 2-30 seconds depending on the model and input size.
-
3
Download or share
Download the result or share the direct link. No watermark, ready to use.
Frequently asked questions
How much does it cost to use Tencent: Hy3?
Tencent: Hy3 is a Pro model: it costs 10 tokens per use (~$0.05 real cost for us). You need a Pro plan ($9/month → 15,000 tokens) or a one-shot pack. If you already have tokens in the free account, you can also spend them directly.
How many Tencent: Hy3 uses do the Pro plan include?
Pro ($9/month) gives you 15,000 recurring tokens, at 10 tokens per Tencent: Hy3 use, that's ~1,500 full uses per cycle. If you run out, one-shot packs (5,000 / 25,000 / 80,000 tokens) add to the balance without expiring before one year.
What makes Tencent: Hy3 special?
Tencent (Hunyuan) opens up the weights of competitive models in chat, code, and video — strong in Asian languages, with specific strengths in adaptive configurable reasoning, moe-efficient architecture, and production-optimized.
How fast does Tencent: Hy3 respond?
Tencent: Hy3 has a balanced speed: 5-15 seconds per response — neither the fastest nor the slowest in the catalog. The actual time also depends on the length of the prompt and the load of the datacenter — models with huge context take longer when you enter very long texts.
How do I use Tencent: Hy3 in ia.gratis?
You can use Tencent: Hy3 from /chat/ by selecting Tencent: Hy3 in the picker, or via the REST API with `model=hy3` in the POST body. Quick summary: tencent Hy3: 295B parameter MoE model for advanced reasoning and agent flows. The internal model identifier is `hy3` — useful when integrating by API.