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:...
Context
262Ktokens
About 374 pages of text at once
Max output
128Ktokens
About 183 pages in one answer
Intelligence
—
No score published for this model.
Output speed
50tokens/s
A 500-word answer in about 14 s
From public market statistics for this model
First token
2.3s
Reasoning models start later
From public market statistics for this model
Health, 30 days
72.78%
5 of 30 days without a fault
IranRouter’s measurements
Price & cost
Every rate in Rial. A request pays only for the tokens it actually uses.
| Input | 361,811 | IRR / 1M tokens |
|---|---|---|
| Output | 1,447,244 | IRR / 1M tokens |
| Reasoning tokensThe output rate | 1,447,244 | IRR / 1M tokens |
| Cache read | 90,453 | IRR / 1M tokens |
Under these conditions, these rates replace the ones above:
00:00–16:00 UTC
| Input | 361,811 | IRR / 1M tokens |
|---|---|---|
| Output | 1,447,244 | IRR / 1M tokens |
| Cache read | 90,453 | IRR / 1M tokens |
16:00–00:00 UTC
| Input | 226,132 | IRR / 1M tokens |
|---|---|---|
| Output | 904,528 | IRR / 1M tokens |
| Cache read | 56,533 | IRR / 1M tokens |
With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.
What would this model cost you a month?
Monthly cost
58.61MIRR
1.95M IRR a day, 977 IRR each request
30 days at today’s rate.
Rial price over 90 days
It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.
Performance, 30 days
Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.
Daily health72.78%
Time to first token2.36 s
Output speed55 tokens/s
Place in the market
By usage across the global model market.
Daily rank#15
Share of the day’s tokens1.4%
Capabilities
- Input
- Text
- Output
- Text
Parameters it accepts
frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_pOther benchmarks
Design contests
- WebsitesElo: 1,180Win rate: 41%
- Code (overall)Elo: 1,175Win rate: 41%
- 3DElo: 1,173Win rate: 44%
- UI componentsElo: 1,158Win rate: 40%
2 moreShow less
- Game devElo: 1,134Win rate: 39%
- Data vizElo: 1,125Win rate: 36%
Start in a minute
The official OpenAI and Anthropic SDKs; only the address and the key change.
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://iranrouter.com/v1", api_key="ir-...", ) r = client.chat.completions.create( model="tencent/hy3", messages=[{"role": "user", "content": "Hello, introduce yourself"}], ) print(r.choices[0].message.content)
Peer models
Its family and models with a close score; the last column compares one message’s cost with this model.
Technical specs
- ID
tencent/hy3- Maker
- Tencent
- Tokenizer
- Other
- Released
- Jul 6, 2026
- Added to IranRouter
- Aug 14, 2026
- Context
- 262,144 tokens
- Max output
- 128,000 tokens
- Weights
- tencent/Hy3
Default parameters
top_p=1temperature=0.9Scores by Design Arena, as of Oct 31, 2026