IranRouter
All models
Tencent

Tencent: Hy3

Available

by Tencent

tencent/hy3Usage rank #7

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

CapabilitiesReasoningToolsStructured output
InputText
OutputText
ReasoningSupportedhighlownone

Benchmarks

Design Arena

CategoryEloWin rate
models · 3d1,20543.8
models · website1,19441.3
models · codecategories1,19241.1
models · uicomponent1,17840.2
models · gamedev1,15938.6
models · dataviz1,14136.1

Source: Design Arena · as of Sep 16, 2026

Performance

Uptime on IranRouter

40.9%

Aug 18Sep 16

Reference uptime

100%

Aug 18Sep 16

Median latency

1,764 ms

Aug 18Sep 16

Throughput

45 tok/s

Aug 18Sep 16

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

Jun 18Sep 15

Ranked by daily token volume across the global model market; the figure above the chart is the daily average.

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

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.