Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
At a glance
- Context window
- 262Ktokens
- Max output
- 128Ktokens
- Knowledge to
- —
- Released
- 2026
Capabilities
Benchmarks
Design Arena
| Category | Elo | Win rate |
|---|---|---|
| models · 3d | 1,205 | 43.8 |
| models · website | 1,194 | 41.3 |
| models · codecategories | 1,192 | 41.1 |
| models · uicomponent | 1,178 | 40.2 |
| models · gamedev | 1,159 | 38.6 |
| models · dataviz | 1,141 | 36.1 |
Source: Design Arena · as of Sep 16, 2026
Performance
Uptime on IranRouter
40.9%
Reference uptime
100%
Median latency
1,764 ms
Throughput
45 tok/s
IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.
Popularity
- Current rank
- #7
- Rank change, 7 days
- 0
Daily tokens · 90 days
977.5B
Ranked by daily token volume across the global model market; the figure above the chart is the daily average.
Supported parameters
Parameters this model accepts; anything else is ignored.
Quick start
from openai import OpenAI
client = OpenAI(
api_key="ir-...",
base_url="https://iranrouter.com/v1",
)
resp = client.chat.completions.create(
model="tencent/hy3",
messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)Only base_url and the key change; the rest of your code stays as it is.